To Örebro University

oru.seÖrebro University Publications
Change search
Refine search result
12 1 - 50 of 59
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Antonova, Rika
    et al.
    Robotics, Perception and Learning, CSC, Royal Institute of Technology, Stockholm, Sweden.
    Kokic, Mia
    Robotics, Perception and Learning, CSC, Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Robotics, Perception and Learning, CSC, Royal Institute of Technology, Stockholm, Sweden.
    Kragic, Danica
    Robotics, Perception and Learning, CSC, Royal Institute of Technology, Stockholm, Sweden.
    Global Search with Bernoulli Alternation Kernel for Task-oriented Grasping Informed by Simulation2018In: Proceedings of Machine Learning Research: Conference on Robot Learning 2018, PMLR , 2018, Vol. 87, p. 641-650Conference paper (Refereed)
    Abstract [en]

    We develop an approach that benefits from large simulated datasets and takes full advantage of the limited online data that is most relevant. We propose a variant of Bayesian optimization that alternates between using informed and uninformed kernels. With this Bernoulli Alternation Kernel we ensure that discrepancies between simulation and reality do not hinder adapting robot control policies online. The proposed approach is applied to a challenging real-world problem of task-oriented grasping with novel objects. Our further contribution is a neural network architecture and training pipeline that use experience from grasping objects in simulation to learn grasp stability scores. We learn task scores from a labeled dataset with a convolutional network, which is used to construct an informed kernel for our variant of Bayesian optimization. Experiments on an ABB Yumi robot with real sensor data demonstrate success of our approach, despite the challenge of fulfilling task requirements and high uncertainty over physical properties of objects.

  • 2.
    Arnekvist, Isac
    et al.
    Robotics, Perception, and Learning lab, Royal Institute of Technology, Stockholm, Sweden.
    Kragic, Danica
    Robotics, Perception, and Learning lab, Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology. Robotics, Perception, and Learning lab, Royal Institute of Technology, Stockholm, Sweden.
    VPE: Variational Policy Embedding for Transfer Reinforcement Learning2019In: 2019 International Conference on Robotics and Automation (ICRA) / [ed] Howard, A; Althoefer, K; Arai, F; Arrichiello, F; Caputo, B; Castellanos, J; Hauser, K; Isler, V Kim, J; Liu, H; Oh, P; Santos, V; Scaramuzza, D; Ude, A; Voyles, R; Yamane, K; Okamura, A, IEEE , 2019, p. 36-42Conference paper (Refereed)
    Abstract [en]

    Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and data collection is expensive, making retraining undesirable. Simulation training allows for feasible training times, but on the other hand suffer from a reality-gap when applied in real-world settings. This raises the need of efficient adaptation of policies acting in new environments.

    We consider the problem of transferring knowledge within a family of similar Markov decision processes. We assume that Q-functions are generated by some low-dimensional latent variable. Given such a Q-function, we can find a master policy that can adapt given different values of this latent variable. Our method learns both the generative mapping and an approximate posterior of the latent variables, enabling identification of policies for new tasks by searching only in the latent space, rather than the space of all policies. The low-dimensional space, and master policy found by our method enables policies to quickly adapt to new environments. We demonstrate the method on both a pendulum swing-up task in simulation, and for simulation-to-real transfer on a pushing task.

  • 3.
    Arnekvist, Isac
    et al.
    Robotics, Perception, and Learning lab, Royal Institute of Technology, Stockholm, Sweden.
    Kragic, Danica
    Robotics, Perception, and Learning lab, Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Robotics, Perception, and Learning lab, Royal Institute of Technology, Stockholm, Sweden.
    VPE: Variational Policy Embedding for Transfer Reinforcement Learning2018Manuscript (preprint) (Other academic)
  • 4.
    Bekiroglu, Yasemin
    et al.
    School of Mechanical Engineering, University of Birmingham, Birmingham, UK.
    Damianou, Andreas
    Department of Computer Science, University of Sheffield, Sheffield, UK.
    Detry, Renaud
    Centre for Autonomous Systems, CSC, Royal Institute of Technology, Sweden.
    Stork, Johannes Andreas
    Centre for Autonomous Systems, CSC, Royal Institute of Technology, Sweden.
    Kragic, Danica
    Centre for Autonomous Systems, CSC, Royal Institute of Technology, Sweden.
    Ek, Carl Henrik
    Centre for Autonomous Systems, CSC, Royal Institute of Technology, Sweden.
    Probabilistic consolidation of grasp experience2016In: 2016 IEEE International Conference on Robotics and Automation (ICRA), IEEE conference proceedings, 2016, p. 193-200Conference paper (Refereed)
    Abstract [en]

    We present a probabilistic model for joint representation of several sensory modalities and action parameters in a robotic grasping scenario. Our non-linear probabilistic latent variable model encodes relationships between grasp-related parameters, learns the importance of features, and expresses confidence in estimates. The model learns associations between stable and unstable grasps that it experiences during an exploration phase. We demonstrate the applicability of the model for estimating grasp stability, correcting grasps, identifying objects based on tactile imprints and predicting tactile imprints from object-relative gripper poses. We performed experiments on a real platform with both known and novel objects, i.e., objects the robot trained with, and previously unseen objects. Grasp correction had a 75% success rate on known objects, and 73% on new objects. We compared our model to a traditional regression model that succeeded in correcting grasps in only 38% of cases.

  • 5.
    Dominguez, David Caceres
    et al.
    Örebro University, School of Science and Technology.
    Iannotta, Marco
    Örebro University, School of Science and Technology.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    Schaffernicht, Erik
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology.
    A Stack-of-Tasks Approach Combined With Behavior Trees: A New Framework for Robot Control2022In: IEEE Robotics and Automation Letters, E-ISSN 2377-3766, Vol. 7, no 4, p. 12110-12117Article in journal (Refereed)
    Abstract [en]

    Stack-of-Tasks (SoT) control allows a robot to simultaneously fulfill a number of prioritized goals formulated in terms of (in)equality constraints in error space. Since this approach solves a sequence of Quadratic Programs (QP) at each time-step, without taking into account any temporal state evolution, it is suitable for dealing with local disturbances. However, its limitation lies in the handling of situations that require non-quadratic objectives to achieve a specific goal, as well as situations where countering the control disturbance would require a locally suboptimal action. Recent works address this shortcoming by exploiting Finite State Machines (FSMs) to compose the tasks in such a way that the robot does not get stuck in local minima. Nevertheless, the intrinsic trade-off between reactivity and modularity that characterizes FSMs makes them impractical for defining reactive behaviors in dynamic environments. In this letter, we combine the SoT control strategy with Behavior Trees (BTs), a task switching structure that addresses some of the limitations of the FSMs in terms of reactivity, modularity and re-usability. Experimental results on a Franka Emika Panda 7-DOF manipulator show the robustness of our framework, that allows the robot to benefit from the reactivity of both SoT and BTs.

  • 6.
    Güler, Püren
    et al.
    Örebro University, Örebro, Sweden.
    Stork, Johannes A.
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology.
    Visual state estimation in unseen environments through domain adaptation and metric learning2022In: Frontiers in Robotics and AI, E-ISSN 2296-9144, Vol. 9, article id 833173Article in journal (Refereed)
    Abstract [en]

    In robotics, deep learning models are used in many visual perception applications, including the tracking, detection and pose estimation of robotic manipulators. The state of the art methods however are conditioned on the availability of annotated training data, which may in practice be costly or even impossible to collect. Domain augmentation is one popular method to improve generalization to out-of-domain data by extending the training data set with predefined sources of variation, unrelated to the primary task. While this typically results in better performance on the target domain, it is not always clear that the trained models are capable to accurately separate the signals relevant to solving the task (e.g., appearance of an object of interest) from those associated with differences between the domains (e.g., lighting conditions). In this work we propose to improve the generalization capabilities of models trained with domain augmentation by formulating a secondary structured metric-space learning objective. We concentrate on one particularly challenging domain transfer task-visual state estimation for an articulated underground mining machine-and demonstrate the benefits of imposing structure on the encoding space. Our results indicate that the proposed method has the potential to transfer feature embeddings learned on the source domain, through a suitably designed augmentation procedure, and on to an unseen target domain.

  • 7. Hang, Kaiyu
    et al.
    Li, Miao
    Stork, Johannes Andreas
    Bekiroglu, Yasemin
    Billard, Aude
    Kragic, Danica
    Hierarchical Fingertip Space for Synthesizing Adaptable Fingertip Grasps2014Conference paper (Other academic)
  • 8.
    Hang, Kaiyu
    et al.
    Computer Vision and Active Perception Laboratory, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Li, Miao
    Learning Algorithms and Systems Laboratory, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland.
    Stork, Johannes Andreas
    Computer Vision and Active Perception Laboratory, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Bekiroglu, Yasemin
    Department of Mechanical Engineering, School of Engineering, University of Birmingham, Birmingham, UK.
    Pokorny, Florian T.
    Computer Vision and Active Perception Laboratory, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Billard, Aude
    Learning Algorithms and Systems Laboratory, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland.
    Kragic, Danica
    Computer Vision and Active Perception Laboratory, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Hierarchical fingertip space: A unified framework for grasp planning and in-hand grasp adaptation2016In: IEEE Transactions on robotics, ISSN 1552-3098, E-ISSN 1941-0468, Vol. 32, no 4, p. 960-972Article in journal (Refereed)
    Abstract [en]

    We present a unified framework for grasp planning and in-hand grasp adaptation using visual, tactile, and proprioceptive feedback. The main objective of the proposed framework is to enable fingertip grasping by addressing problems of changed weight of the object, slippage, and external disturbances. For this purpose we introduce the Hierarchical Fingertip Space as a representation enabling optimization for both efficient grasp synthesis and online finger gaiting. Grasp synthesis is followed by a grasp adaptation step that consists of both grasp force adaptation through impedance control and regrasping/finger gaiting when the former is not sufficient. Experimental evaluation is conducted on an Allegro hand mounted on a Kuka LWR arm.

  • 9.
    Hang, Kaiyu
    et al.
    Department of Mechanical Engineering and Material Science, Yale University, New Haven, CT, USA.
    Lyu, Ximin
    Hong Kong University of Science and Technology, Hong Kong, China.
    Song, Haoran
    Hong Kong University of Science and Technology, Hong Kong, China.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology. RPL, KTH Royal Institute of Technology, Stockholm, Sweden.
    Dollar, Aaron
    Department of Mechanical Engineering and Material Science, Yale University, New Haven, CT, USA.
    Kragic, Danica
    RPL, KTH Royal Institute of Technology, Stockholm, Sweden.
    Zhang, Fu
    The University of Hong Kong, Hong Kong, China.
    Perching and resting: A paradigm for UAV maneuvering with modularized landing gears2019In: Science Robotics, E-ISSN 2470-9476, Vol. 4, no 28, article id eaau6637Article in journal (Refereed)
    Abstract [en]

    Perching helps small unmanned aerial vehicles (UAVs) extend their time of operation by saving battery power. However, most strategies for UAV perching require complex maneuvering and rely on specific structures, such as rough walls for attaching or tree branches for grasping. Many strategies to perching neglect the UAV’s mission such that saving battery power interrupts the mission. We suggest enabling UAVs with the capability of making and stabilizing contacts with the environment, which will allow the UAV to consume less energy while retaining its altitude, in addition to the perching capability that has been proposed before. This new capability is termed “resting.” For this, we propose a modularized and actuated landing gear framework that allows stabilizing the UAV on a wide range of different structures by perching and resting. Modularization allows our framework to adapt to specific structures for resting through rapid prototyping with additive manufacturing. Actuation allows switching between different modes of perching and resting during flight and additionally enables perching by grasping. Our results show that this framework can be used to perform UAV perching and resting on a set of common structures, such as street lights and edges or corners of buildings. We show that the design is effective in reducing power consumption, promotes increased pose stability, and preserves large vision ranges while perching or resting at heights. In addition, we discuss the potential applications facilitated by our design, as well as the potential issues to be addressed for deployment in practice.

  • 10.
    Hang, Kaiyu
    et al.
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Kragic, Danica
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Hierarchical fingertip space for multi-fingered precision grasping2014In: 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE Press, 2014, p. 1641-1648Conference paper (Refereed)
    Abstract [en]

    Dexterous in-hand manipulation of objects benefits from the ability of a robot system to generate precision grasps. In this paper, we propose a concept of Fingertip Space and its use for precision grasp synthesis. Fingertip Space is a representation that takes into account both the local geometry of object surface as well as the fingertip geometry. As such, it is directly applicable to the object point cloud data and it establishes a basis for the grasp search space. We propose a model for a hierarchical encoding of the Fingertip Space that enables multilevel refinement for efficient grasp synthesis. The proposed method works at the grasp contact level while not neglecting object shape nor hand kinematics. Experimental evaluation is performed for the Barrett hand considering also noisy and incomplete point cloud data.

  • 11.
    Hang, Kaiyu
    et al.
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Pokorny, Florian T.
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Kragic, Danica
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Combinatorial optimization for hierarchical contact-level grasping2014In: 2014 IEEE International Conference on Robotics and Automation (ICRA), IEEE, 2014, p. 381-388Conference paper (Refereed)
    Abstract [en]

    We address the problem of generating force-closed point contact grasps on complex surfaces and model it as a combinatorial optimization problem. Using a multilevel refinement metaheuristic, we maximize the quality of a grasp subject to a reachability constraint by recursively forming a hierarchy of increasingly coarser optimization problems. A grasp is initialized at the top of the hierarchy and then locally refined until convergence at each level. Our approach efficiently addresses the high dimensional problem of synthesizing stable point contact grasps while resulting in stable grasps from arbitrary initial configurations. Compared to a sampling-based approach, our method yields grasps with higher grasp quality. Empirical results are presented for a set of different objects. We investigate the number of levels in the hierarchy, the computational complexity, and the performance relative to a random sampling baseline approach.

  • 12.
    Hang, Kaiyu
    et al.
    Robotics, Perception, and Learning Lab, KTH Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Robotics, Perception, and Learning Lab, KTH Royal Institute of Technology, Stockholm, Sweden.
    Pollard, Nancy S.
    Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA.
    Kragic, Danica
    Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA.
    A Framework For Optimal Grasp Contact Planning2017In: IEEE Robotics and Automation Letters, E-ISSN 2377-3766, Vol. 2, no 2, p. 704-711Article in journal (Refereed)
    Abstract [en]

    We consider the problem of finding grasp contacts that are optimal under a given grasp quality function on arbitrary objects. Our approach formulates a framework for contact-level grasping as a path finding problem in the space of supercontact grasps. The initial supercontact grasp contains all grasps and in each step along a path grasps are removed. For this, we introduce and formally characterize search space structure and cost functions under which minimal cost paths correspond to optimal grasps. Our formulation avoids expensive exhaustive search and reduces computational cost by several orders of magnitude. We present admissible heuristic functions and exploit approximate heuristic search to further reduce the computational cost while maintaining bounded suboptimality for resulting grasps. We exemplify our formulation with point-contact grasping for which we define domain specific heuristics and demonstrate optimality and bounded suboptimality by comparing against exhaustive and uniform cost search on example objects. Furthermore, we explain how to restrict the search graph to satisfy grasp constraints for modeling hand kinematics. We also analyze our algorithm empirically in terms of created and visited search states and resultant effective branching factor.

  • 13.
    Haustein, J A
    et al.
    Royal Institute of Technology, Stockholm, Sweden.
    Arnekvist, I
    Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Royal Institute of Technology, Stockholm, Sweden.
    Hang, K
    Yale University, New Haven, USA.
    Kragic, D
    Royal Institute of Technology, Stockholm, Sweden.
    Non-prehensile Rearrangement Planning with Learned Manipulation States and Actions2018Conference paper (Other academic)
    Abstract [en]

    In this work we combine sampling-based motion planning with reinforcement learning and generative modeling to solve non-prehensile rearrangement problems. Our algorithm explores the composite configuration space of objects and robot as a search over robot actions, forward simulated in a physics model. This search is guided by a generative model that provides robot states from which an object can be transported towards a desired state, and a learned policy that provides corresponding robot actions. As an efficient generative model, we apply Generative Adversarial Networks.

  • 14.
    Haustein, J A
    et al.
    KTH Royal Institute of Technology, Stockholm, Sweden.
    Hang, K
    Yale University, New Haven, USA.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    Kragic, D
    KTH Royal Institute of Technology, Stockholm, Sweden.
    Object placement planning and optimization for robot manipulatorsManuscript (preprint) (Other academic)
    Abstract [en]

    We address the problem of motion planning for a robotic manipulator with the task to place a grasped object in a cluttered environment. In this task, we need to locate a collision-free pose for the object that a) facilitates the stable placement of the object, b) is reachable by the robot manipulator and c) optimizes a user-given placement objective. Because of the placement objective, this problem is more challenging than classical motion planning where the target pose is defined from the start. To solve this task, we propose an anytime algorithm that integrates sampling-based motion planning for the robot manipulator with a novel hierarchical search for suitable placement poses. We evaluate our approach on a dual-arm robot for two different placement objectives, and observe its effectiveness even in challenging scenarios.

  • 15.
    Haustein, J. A.
    et al.
    KTH Royal Institute of Technology, Division of Robotics, Perception and Learning (RPL), CAS, CSC, Stockholm, Sweden.
    Hang, K.
    Yale University, Department of Mechanical Engineering and Material Science, New Haven, United States.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    Kragic, D.
    KTH Royal Institute of Technology, Division of Robotics, Perception and Learning (RPL), CAS, CSC, Stockholm, Sweden.
    Object Placement Planning and optimization for Robot Manipulators2019In: IEEE International Conference on Intelligent Robots and Systems, Institute of Electrical and Electronics Engineers (IEEE), 2019, p. 7417-7424Conference paper (Refereed)
    Abstract [en]

    We address the problem of planning the placement of a rigid object with a dual-arm robot in a cluttered environment. In this task, we need to locate a collision-free pose for the object that a) facilitates the stable placement of the object, b) is reachable by the robot and c) optimizes a user-given placement objective. In addition, we need to select which robot arm to perform the placement with. To solve this task, we propose an anytime algorithm that integrates sampling-based motion planning with a novel hierarchical search for suitable placement poses. Our algorithm incrementally produces approach motions to stable placement poses, reaching placements with better objective as runtime progresses. We evaluate our approach for two different placement objectives, and observe its effectiveness even in challenging scenarios.

  • 16.
    Haustein, Joshua A.
    et al.
    Robotics, Perception and Learning Lab (RPL), CAS, EECS, KTH Royal Institute of Technology, Stockholm, Sweden.
    Arnekvist, Isac
    Robotics, Perception and Learning Lab (RPL), CAS, EECS, KTH Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Robotics, Perception and Learning Lab (RPL), CAS, EECS, KTH Royal Institute of Technology, Stockholm, Sweden.
    Hang, Kaiyu
    GRAB Lab, Yale University, New Haven, USA.
    Kragic, Danica
    Robotics, Perception and Learning Lab (RPL), CAS, EECS, KTH Royal Institute of Technology, Stockholm, Sweden.
    Learning Manipulation States and Actions for Efficient Non-prehensile Rearrangement Planning2019Manuscript (preprint) (Other academic)
  • 17.
    Hoang, Dinh-Cuong
    et al.
    CT Department, FPT University, Hanoi, Vietnam.
    Stork, Johannes A.
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology. Department of Computing and Software, McMaster University, Hamilton ON, Canada.
    Voting and Attention-Based Pose Relation Learning for Object Pose Estimation From 3D Point Clouds2022In: IEEE Robotics and Automation Letters, E-ISSN 2377-3766, Vol. 7, no 4, p. 8980-8987Article in journal (Refereed)
    Abstract [en]

    Estimating the 6DOF pose of objects is an important function in many applications, such as robot manipulation or augmented reality. However, accurate and fast pose estimation from 3D point clouds is challenging, because of the complexity of object shapes, measurement noise, and presence of occlusions. We address this challenging task using an end-to-end learning approach for object pose estimation given a raw point cloud input. Our architecture pools geometric features together using a self-attention mechanism and adopts a deep Hough voting scheme for pose proposal generation. To build robustness to occlusion, the proposed network generates candidates by casting votes and accumulating evidence for object locations. Specifically, our model learns higher-level features by leveraging the dependency of object parts and object instances, thereby boosting the performance of object pose estimation. Our experiments show that our method outperforms state-of-the-art approaches in public benchmarks including the Sileane dataset 135 and the Fraunhofer IPA dataset [36]. We also deploy our proposed method to a real robot pick-and-place based on the estimated pose.

  • 18.
    Hoang, Dinh-Cuong
    et al.
    Örebro University, School of Science and Technology. ICT Department, FPT University, Hanoi, Vietnam.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology.
    Context-Aware Grasp Generation in Cluttered Scenes2022In: 2022 International Conference on Robotics and Automation (ICRA), IEEE, 2022, p. 1492-1498Conference paper (Refereed)
    Abstract [en]

    Conventional methods to autonomous grasping rely on a pre-computed database with known objects to synthesize grasps, which is not possible for novel objects. On the other hand, recently proposed deep learning-based approaches have demonstrated the ability to generalize grasp for unknown objects. However, grasp generation still remains a challenging problem, especially in cluttered environments under partial occlusion. In this work, we propose an end-to-end deep learning approach for generating 6-DOF collision-free grasps given a 3D scene point cloud. To build robustness to occlusion, the proposed model generates candidates by casting votes and accumulating evidence for feasible grasp configurations. We exploit contextual information by encoding the dependency of objects in the scene into features to boost the performance of grasp generation. The contextual information enables our model to increase the likelihood that the generated grasps are collision-free. Our experimental results confirm that the proposed system performs favorably in terms of predicting object grasps in cluttered environments in comparison to the current state of the art methods.

    Download full text (pdf)
    Context-Aware Grasp Generation in Cluttered Scenes
  • 19.
    Iannotta, Marco
    et al.
    Örebro University, School of Science and Technology.
    Dominguez, David Caceres
    Örebro University, School of Science and Technology.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    Schaffernicht, Erik
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology.
    Heterogeneous Full-body Control of a Mobile Manipulator with Behavior Trees2022In: IROS 2022 Workshop on Mobile Manipulation and Embodied Intelligence (MOMA): Challenges and  Opportunities, 2022Conference paper (Refereed)
    Abstract [en]

    Integrating the heterogeneous controllers of a complex mechanical system, such as a mobile manipulator, within the same structure and in a modular way is still challenging. In this work we extend our framework based on Behavior Trees for the control of a redundant mechanical system to the problem of commanding more complex systems that involve multiple low-level controllers. This allows the integrated systems to achieve non-trivial goals that require coordination among the sub-systems.

    Download full text (pdf)
    Heterogeneous Full-body Control of a Mobile Manipulator with Behavior Trees
  • 20.
    Isac, Arnekvist
    et al.
    KTH Royal Institute of Technology, Stockholm, Sweden.
    J. Frederico, Carvalho
    Univrses AB, Stockholm, Sweden.
    Kragic, Danica
    KTH Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    The effect of Target Normalization and Momentum on Dying ReLU2020In: The 32nd annual workshop of the Swedish Artificial Intelligence Society (SAIS), 2020Conference paper (Refereed)
    Abstract [en]

    Optimizing parameters with momentum, normalizing data values, and using rectified linear units (ReLUs) are popular choices in neural network (NN) regression. Although ReLUs are popular, they can collapse to a constant function and" die", effectively removing their contribution from the model. While some mitigations are known, the underlying reasons of ReLUs dying during optimization are currently poorly understood. In this paper, we consider the effects of target normalization and momentum on dying ReLUs. We find empirically that unit variance targets are well motivated and that ReLUs die more easily, when target variance approaches zero. To further investigate this matter, we analyze a discrete-time linear autonomous system, and show theoretically how this relates to a model with a single ReLU and how common properties can result in dying ReLU. We also analyze the gradients of a single-ReLU model to identify saddle points and regions corresponding to dying ReLU and how parameters evolve into these regions when momentum is used. Finally, we show empirically that this problem persist, and is aggravated, for deeper models including residual networks.

  • 21.
    Ivan, Jean-Paul A.
    et al.
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology.
    Stork, Johannes A.
    Örebro University, School of Science and Technology.
    Online Distance Field Priors for Gaussian Process Implicit Surfaces2022In: IEEE Robotics and Automation Letters, E-ISSN 2377-3766, Vol. 7, no 4, p. 8996-9003Article in journal (Refereed)
    Abstract [en]

    Gaussian process (GP) implicit surface models provide environment and object representations which elegantly address noise and uncertainty while remaining sufficiently flexible to capture complex geometry. However, GP models quickly become intractable as the size of the observation set grows-a trait which is difficult to reconcile with the rate at which modern range sensors produce data. Furthermore, naive applications of GPs to implicit surface models allocate model resources uniformly, thus using precious resources to capture simple geometry. In contrast to prior work addressing these challenges though model sparsification, spatial partitioning, or ad-hoc filtering, we propose introducing model bias online through the GP's mean function. We achieve more accurate distance fields using smaller models by creating a distance field prior from features which are easy to extract and have analytic distance fields. In particular, we demonstrate this approach using linear features. We show the proposed distance field halves model size in a 2D mapping task using data from a SICK S300 sensor. When applied to a single 3D scene from the TUM RGB-D SLAM dataset, we achieve a fivefold reduction in model size. Our proposed prior results in more accurate GP implicit surfaces, while allowing existing models to function in larger environments or with larger spatial partitions due to reduced model size.

  • 22.
    Kokic, Mia
    et al.
    Robotics, Perception, and Learning lab, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Robotics, Perception, and Learning lab, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Haustein, Joshua A.
    Robotics, Perception, and Learning lab, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Kragic, Danica
    Robotics, Perception, and Learning lab, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Affordance detection for task-specific grasping using deep learning2017In: 2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids), IEEE conference proceedings, 2017, p. 91-98Conference paper (Refereed)
    Abstract [en]

    In this paper we utilize the notion of affordances to model relations between task, object and a grasp to address the problem of task-specific robotic grasping. We use convolutional neural networks for encoding and detecting object affordances, class and orientation, which we utilize to formulate grasp constraints. Our approach applies to previously unseen objects from a fixed set of classes and facilitates reasoning about which tasks an object affords and how to grasp it for that task. We evaluate affordance detection on full-view and partial-view synthetic data and compute task-specific grasps for objects that belong to ten different classes and afford five different tasks. We demonstrate the feasibility of our approach by employing an optimization-based grasp planner to compute task-specific grasps.

  • 23.
    Luber, Matthias
    et al.
    Social Robotics Lab, Department of Computer Science, University of Freiburg, Germany.
    Stork, Johannes Andreas
    Social Robotics Lab, Department of Computer Science, University of Freiburg, Germany.
    Tipaldi, Gian Diego
    Social Robotics Lab, Department of Computer Science, University of Freiburg, Germany.
    Arras, Kai O.
    Social Robotics Lab, Department of Computer Science, University of Freiburg, Germany.
    People tracking with human motion predictions from social forces2010In: 2010 IEEE International Conference on Robotics and Automation, Proceedings, IEEE conference proceedings, 2010, p. 464-469Conference paper (Refereed)
    Abstract [en]

    For many tasks in populated environments, robots need to keep track of current and future motion states of people. Most approaches to people tracking make weak assumptions on human motion such as constant velocity or acceleration. But even over a short period, human behavior is more complex and influenced by factors such as the intended goal, other people, objects in the environment, and social rules. This motivates the use of more sophisticated motion models for people tracking especially since humans frequently undergo lengthy occlusion events. In this paper, we consider computational models developed in the cognitive and social science communities that describe individual and collective pedestrian dynamics for tasks such as crowd behavior analysis. In particular, we integrate a model based on a social force concept into a multi-hypothesis target tracker. We show how the refined motion predictions translate into more informed probability distributions over hypotheses and finally into a more robust tracking behavior and better occlusion handling. In experiments in indoor and outdoor environments with data from a laser range finder, the social force model leads to more accurate tracking with up to two times fewer data association errors.

  • 24.
    Marzinotto, Alejandro
    et al.
    Computer Vision and Active Perception Lab., Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Computer Vision and Active Perception Lab., Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Rope through Loop Insertion for Robotic Knotting: A Virtual Magnetic Field Formulation2016Report (Other academic)
    Abstract [en]

    Inserting an end of a rope through a loop is a common and important action that is required for creating most types of knots. To perform this action, we need to pass the end of the rope through an area that is enclosed by another segment of rope. As for all knotting actions, the robot must for this exercise control over a semi-compliant and flexible body whose complex 3d shape is difficult to perceive and follow. Additionally, the target loop often deforms during the insertion. We address this problem by defining a virtual magnetic field through the loop's interior and use the Biot Savart law to guide the robotic manipulator that holds the end of the rope. This approach directly defines, for any manipulator position, a motion vector that results in a path that passes through the loop. The motion vector is directly derived from the position of the loop and changes as soon as it moves or deforms. In simulation, we test the insertion action against dynamic loop deformation of different intensity. We also combine insertion with grasp and release actions, coordinated by a hybrid control system, to tie knots in simulation and with a NAO robot.

  • 25.
    Marzinotto, Alejandro
    et al.
    Computer Vision and Active Perception Lab., Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Computer Vision and Active Perception Lab., Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Dimarogonas, Dimos V.
    Computer Vision and Active Perception Lab., Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Kragic, Danica
    Computer Vision and Active Perception Lab., Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Cooperative grasping through topological object representation2014In: 2014 IEEE-RAS International Conference on Humanoid Robots, IEEE, 2014, p. 685-692Conference paper (Refereed)
    Abstract [en]

    We present a cooperative grasping approach based on a topological representation of objects. Using point cloud data we extract loops on objects suitable for generating entanglement. We use the Gauss Linking Integral to derive controllers for multi-agent systems that generate hooking grasps on such loops while minimizing the entanglement between robots. The approach copes well with noisy point cloud data, it is computationally simple and robust. We demonstrate the method for performing object grasping and transportation, through a hooking maneuver, with two coordinated NAO robots.

  • 26.
    Mitsioni, Ioanna
    et al.
    Division of Robotics, Perception and Learning (RPL), CAS, EECS, KTH Royal Institute of Technology, Stockholm, Sweden.
    Karayiannidis, Yiannis
    Division of Systems and Control, Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    Kragic, Danica
    Division of Robotics, Perception and Learning (RPL), CAS, EECS, KTH Royal Institute of Technology, Stockholm, Sweden.
    Data-Driven Model Predictive Control for Food-CuttingManuscript (preprint) (Other academic)
    Abstract [en]

    Modelling of contact-rich tasks is challenging and cannot be entirely solved using classical control approaches due to the difficulty of constructing an analytic description of the contact dynamics. Additionally, in a manipulation task like food-cutting, purely learning-based methods such as Reinforcement Learning, require either a vast amount of data that is expensive to collect on a real robot, or a highly realistic simulation environment, which is currently not available. This paper presents a data-driven control approach that employs a recurrent neural network to model the dynamics for a Model Predictive Controller. We extend on previous work that was limited to torque-controlled robots by incorporating Force/Torque sensor measurements and formulate the control problem so that it can be applied to the more common velocity controlled robots. We evaluate the performance on objects used for training, as well as on unknown objects, by means of the cutting rates achieved and demonstrate that the method can efficiently treat different cases with only one dynamic model. Finally we investigate the behavior of the system during force-critical instances of cutting and illustrate its adaptive behavior in difficult cases.

  • 27.
    Mitsioni, Ioanna
    et al.
    KTH Royal Institute of Technology, Stockholm, Sweden.
    Karayiannidis, Yiannis
    Chalmers University of Technology , Gothenburg, Sweden; KTH Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    Kragic, Danica
    KTH Royal Institute of Technology, Stockholm, Sweden.
    Data-Driven Model Predictive Control for the Contact-Rich Task of Food Cutting2019In: IEEE-RAS International Conference on Humanoid Robots, IEEE Computer Society, 2019, p. 244-250, article id 9035011Conference paper (Refereed)
    Abstract [en]

    Modelling of contact-rich tasks is challenging and cannot be entirely solved using classical control approaches due to the difficulty of constructing an analytic description of the contact dynamics. Additionally, in a manipulation task like food-cutting, purely learning-based methods such as Reinforcement Learning, require either a vast amount of data that is expensive to collect on a real robot, or a highly realistic simulation environment, which is currently not available. This paper presents a data-driven control approach that employs a recurrent neural network to model the dynamics for a Model Predictive Controller. We build upon earlier work limited to torque-controlled robots and redefine it for velocity controlled ones. We incorporate force/torque sensor measurements, reformulate and further extend the control problem formulation. We evaluate the performance on objects used for training, as well as on unknown objects, by means of the cutting rates achieved and demonstrate that the method can efficiently treat different cases with only one dynamic model. Finally we investigate the behavior of the system during force-critical instances of cutting and illustrate its adaptive behavior in difficult cases.

  • 28.
    Pokorny, Florian T.
    et al.
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Kragic, Danica
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Grasping Objects with Holes: A Topological Approach2013In: 2013 IEEE International Conference on Robotics and Automation, IEEE conference proceedings, 2013, p. 1100-1107Conference paper (Refereed)
    Abstract [en]

    This work proposes a topologically inspired approach for generating robot grasps on objects with `holes'. Starting from a noisy point-cloud, we generate a simplicial representation of an object of interest and use a recently developed method for approximating shortest homology generators to identify graspable loops. To control the movement of the robot hand, a topologically motivated coordinate system is used in order to wrap the hand around such loops. Finally, another concept from topology - namely the Gauss linking integral - is adapted to serve as evidence for secure caging grasps after a grasp has been executed. We evaluate our approach in simulation on a Barrett hand using several target objects of different sizes and shapes and present an initial experiment with real sensor data.

  • 29.
    Rietz, Finn
    et al.
    Örebro University, School of Science and Technology. Department of Informatics, University of Hamburg, Hamburg, Germany.
    Magg, Sven
    Hamburger Informatik Technologie-Center, Universität Hamburg, Hamburg, Germany.
    Heintz, Fredrik
    Department of Computer and Information Science, Linköping University, Linköping, Sweden.
    Stoyanov, Todor
    Örebro University, School of Science and Technology.
    Wermter, Stefan
    Department of Informatics, University of Hamburg, Hamburg, Germany.
    Stork, Johannes A
    Örebro University, School of Science and Technology.
    Hierarchical goals contextualize local reward decomposition explanations2023In: Neural Computing & Applications, ISSN 0941-0643, E-ISSN 1433-3058, Vol. 35, no 23, p. 16693-16704Article in journal (Refereed)
    Abstract [en]

    One-step reinforcement learning explanation methods account for individual actions but fail to consider the agent's future behavior, which can make their interpretation ambiguous. We propose to address this limitation by providing hierarchical goals as context for one-step explanations. By considering the current hierarchical goal as a context, one-step explanations can be interpreted with higher certainty, as the agent's future behavior is more predictable. We combine reward decomposition with hierarchical reinforcement learning into a novel explainable reinforcement learning framework, which yields more interpretable, goal-contextualized one-step explanations. With a qualitative analysis of one-step reward decomposition explanations, we first show that their interpretability is indeed limited in scenarios with multiple, different optimal policies-a characteristic shared by other one-step explanation methods. Then, we show that our framework retains high interpretability in such cases, as the hierarchical goal can be considered as context for the explanation. To the best of our knowledge, our work is the first to investigate hierarchical goals not as an explanation directly but as additional context for one-step reinforcement learning explanations.

  • 30.
    Rietz, Finn
    et al.
    Örebro University, School of Science and Technology.
    Schaffernicht, Erik
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    Towards Task-Prioritized Policy Composition2022Conference paper (Refereed)
    Abstract [en]

    Combining learned policies in a prioritized, ordered manner is desirable because it allows for modular design and facilitates data reuse through knowledge transfer. In control theory, prioritized composition is realized by null-space control, where low-priority control actions are projected into the null-space of high-priority control actions. Such a method is currently unavailable for Reinforcement Learning. We propose a novel, task-prioritized composition framework for Reinforcement Learning, which involves a novel concept: The indifferent-space of Reinforcement Learning policies. Our framework has the potential to facilitate knowledge transfer and modular design while greatly increasing data efficiency and data reuse for Reinforcement Learning agents. Further, our approach can ensure high-priority constraint satisfaction, which makes it promising for learning in safety-critical domains like robotics. Unlike null-space control, our approach allows learning globally optimal policies for the compound task by online learning in the indifference-space of higher-level policies after initial compound policy construction. 

  • 31.
    Song, Haoran
    et al.
    Robotics Institute, Hong Kong University of Science and Technology, Hong Kong, China.
    Haustein, Joshua A.
    Centre for Autonomous Systems, EECS, KTH Royal Institute of Technology, Stockholm, Sweden.
    Yuan, Weihao
    Robotics Institute, Hong Kong University of Science and Technology, Hong Kong, China.
    Hang, Kaiyu
    Department of Mechanical Engineering and Material Science, Yale University, New Haven Connecticut, USA.
    Wang, Michael Yu
    Robotics Institute, Hong Kong University of Science and Technology, Hong Kong, China.
    Kragic, Danica
    Centre for Autonomous Systems, EECS, KTH Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    Multi-Object Rearrangement with Monte Carlo Tree Search: A Case Study on Planar Nonprehensile SortingManuscript (preprint) (Other academic)
    Abstract [en]

    In this work, we address a planar non-prehensile sorting task. Here, a robot needs to push many densely packed objects belonging to different classes into a configuration where these classes are clearly separated from each other. To achieve this, we propose to employ Monte Carlo tree search equipped with a task-specific heuristic function. We evaluate the algorithm on various simulated sorting tasks and observe its effectiveness in reliably sorting up to 40 convex objects. In addition, we observe that the algorithm is capable to also sort non-convex objects, as well as convex objects in the presence of immovable obstacles.

  • 32.
    Song, Haoran
    et al.
    Robotics Institute, Hong Kong University of Science and Technology, Hong Kong, China.
    Haustein, Joshua A.
    Centre for AutonomousSystems, EECS, KTH Royal Institute of Technology, Stockholm, Sweden.
    Yuan, Weihao
    Robotics Institute, Hong Kong University of Science and Technology, Hong Kong, China.
    Hang, Kaiyu
    Department of Mechanical Engineering and Material Science, Yale University, New Haven, Connecticut, USA.
    Wang, Michael Yu
    Robotics Institute, Hong Kong University of Science and Technology, Hong Kong, China.
    Kragic, Danica
    Centre for AutonomousSystems, EECS, KTH Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    Multi-Object Rearrangement with Monte Carlo Tree Search: A Case Study on Planar Nonprehensile Sorting2020Conference paper (Refereed)
    Abstract [en]

    In this work, we address a planar non-prehensile sorting task. Here, a robot needs to push many densely packed objects belonging to different classes into a configuration where these classes are clearly separated from each other. To achieve this, we propose to employ Monte Carlo tree search equipped with a task-specific heuristic function. We evaluate the algorithm on various simulated and real-world sorting tasks. We observe that the algorithm is capable of reliably sorting large number of convex and non-convex objects, as well as convex objects in the presence of immovable obstacles.

  • 33.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    Preparing to adapt is key for Olympic curling robots2020In: Science robotics, E-ISSN 2470-9476, Vol. 5, no 46, article id eabe2547Article in journal (Refereed)
    Abstract [en]

    Continued advances in machine learning could enable robots to solve tasks on a human level and adapt to changing conditions.

  • 34.
    Stork, Johannes Andreas
    et al.
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Ek, Carl Henrik
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Bekiroglu, Yasemin
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Kragic, Danica
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Learning Predictive State Representation for In-Hand Manipulation2015In: 2015 IEEE International Conference on Robotics and Automation (ICRA), IEEE conference proceedings, 2015, p. 3207-3214Conference paper (Refereed)
    Abstract [en]

    We study the use of Predictive State Representation (PSR) for modeling of an in-hand manipulation task through interaction with the environment. We extend the original PSR model to a new domain of in-hand manipulation and address the problem of partial observability by introducing new kernel-based features that integrate both actions and observations. The model is learned directly from haptic data and is used to plan series of actions that rotate the object in the hand to a specific configuration by pushing it against a table. Further, we analyze the model's belief states using additional visual data and enable planning of action sequences when the observations are ambiguous. We show that the learned representation is geometrically meaningful by embedding labeled action-observation traces. Suitability for planning is demonstrated by a post-grasp manipulation example that changes the object state to multiple specified target configurations.

  • 35.
    Stork, Johannes Andreas
    et al.
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Ek, Carl Henrik
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Kragic, Danica
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Learning Predictive State Representations for planning2015In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE Press, 2015, p. 3427-3434Conference paper (Refereed)
    Abstract [en]

    Predictive State Representations (PSRs) allow modeling of dynamical systems directly in observables and without relying on latent variable representations. A problem that arises from learning PSRs is that it is often hard to attribute semantic meaning to the learned representation. This makes generalization and planning in PSRs challenging. In this paper, we extend PSRs and introduce the notion of PSRs that include prior information (P-PSRs) to learn representations which are suitable for planning and interpretation. By learning a low-dimensional embedding of test features we map belief points of similar semantic to the same region of a subspace. This facilitates better generalization for planning and semantical interpretation of the learned representation. In specific, we show how to overcome the training sample bias and introduce feature selection such that the resulting representation emphasizes observables related to the planning task. We show that our P-PSRs result in qualitatively meaningful representations and present quantitative results that indicate improved suitability for planning.

  • 36.
    Stork, Johannes Andreas
    et al.
    Royal Institute of Technology, Stockholm, Sweden.
    Ek, Carl Henrik
    Royal Institute of Technology, Stockholm, Sweden.
    Kragic, Danica
    Royal Institute of Technology, Stockholm, Sweden.
    Learning Predictive State Representations for planning2015Conference paper (Other academic)
  • 37.
    Stork, Johannes Andreas
    et al.
    Centre for Autonomous Systems, Computer Vision and Active Perception Lab, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Pokorny, Florian T.
    Centre for Autonomous Systems, Computer Vision and Active Perception Lab, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    Kragic, Danica
    Centre for Autonomous Systems, Computer Vision and Active Perception Lab, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden.
    A topology-based object representation for clasping, latching and hooking2013In: 2013 13TH IEEE-RAS INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS), IEEE conference proceedings, 2013, p. 138-145Conference paper (Refereed)
    Abstract [en]

    We present a loop-based topological object representation for objects with holes. The representation is used to model object parts suitable for grasping, e.g. handles, and it incorporates local volume information about these. Furthermore, we present a grasp synthesis framework that utilizes this representation for synthesizing caging grasps that are robust under measurement noise. The approach is complementary to a local contact-based force-closure analysis as it depends on global topological features of the object. We perform an extensive evaluation with four robotic hands on synthetic data. Additionally, we provide real world experiments using a Kinect sensor on two robotic platforms: a Schunk dexterous hand attached to a Kuka robot arm as well as a Nao humanoid robot. In the case of the Nao platform, we provide initial experiments showing that our approach can be used to plan whole arm hooking as well as caging grasps involving only one hand.

  • 38.
    Stork, Johannes Andreas
    et al.
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, CSC, KTH Royal Institute of Technology, Stockholm, Sweden.
    Pokorny, Florian T.
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, CSC, KTH Royal Institute of Technology, Stockholm, Sweden.
    Kragic, Danica
    Computer Vision and Active Perception Lab, Centre for Autonomous Systems, CSC, KTH Royal Institute of Technology, Stockholm, Sweden.
    Integrated motion and clasp planning with virtual linking2013In: 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE Press, 2013, p. 3007-3014Conference paper (Refereed)
    Abstract [en]

    In this work, we address the problem of simultaneous clasp and motion planning on unknown objects with holes. Clasping an object enables a rich set of activities such as dragging, toting, pulling and hauling which can be applied to both soft and rigid objects. To this end, we define a virtual linking measure which characterizes the spacial relation between the robot hand and object. The measure utilizes a set of closed curves arising from an approximately shortest basis of the object's first homology group. We define task spaces to perform collision-free motion planing with respect to multiple prioritized objectives using a sampling-based planing method. The approach is tested in simulation using different robot hands and various real-world objects.

  • 39.
    Stork, Johannes Andreas
    et al.
    Royal Institute of Technology, Stockholm, Sweden.
    Pokorny, Florian T.
    Royal Institute of Technology, Stockholm, Sweden.
    Kragic, Danica
    Royal Institute of Technology, Stockholm, Sweden.
    Towards Postural Synergies for Caging Grasps2013Conference paper (Other academic)
  • 40. Stork, Johannes Andreas
    et al.
    Silva, Jens
    Spinello, Luciano
    Arras, Kai O.
    Audio-Based Human Activity Recognition with Robots2011Conference paper (Other academic)
  • 41.
    Stork, Johannes Andreas
    et al.
    Social Robotics Lab, Department of Computer Science, University of Freiburg, Freiburg im Breisgau, Germany.
    Spinello, Luciano
    Social Robotics Lab, Department of Computer Science, University of Freiburg, Freiburg im Breisgau, Germany.
    Silva, Jens
    Social Robotics Lab, Department of Computer Science, University of Freiburg, Freiburg im Breisgau, Germany.
    Arras, Kai O.
    Social Robotics Lab, Department of Computer Science, University of Freiburg, Freiburg im Breisgau, Germany.
    Audio-Based Human Activity Recognition Using Non-Markovian Ensemble Voting2012In: 2012 IEEE RO-MAN: The 21st IEEE International Symposium on Robot and Human Interactive Communication, IEEE conference proceedings, 2012, p. 509-514Conference paper (Refereed)
    Abstract [en]

    Human activity recognition is a key component for socially enabled robots to effectively and naturally interact with humans. In this paper we exploit the fact that many human activities produce characteristic sounds from which a robot can infer the corresponding actions. We propose a novel recognition approach called Non-Markovian Ensemble Voting (NEV) able to classify multiple human activities in an online fashion without the need for silence detection or audio stream segmentation. Moreover, the method can deal with activities that are extended over undefined periods in time. In a series of experiments in real reverberant environments, we are able to robustly recognize 22 different sounds that correspond to a number of human activities in a bathroom and kitchen context. Our method outperforms several established classification techniques.

  • 42.
    Stork, Johannes Andreas
    et al.
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology.
    Ensemble of Sparse Gaussian Process Experts for Implicit Surface Mapping with Streaming Data2020In: IEEE International Conference on Robotics and Automation, IEEE, 2020, p. 10758-10764, article id 9196620Conference paper (Refereed)
    Abstract [en]

    Creating maps is an essential task in robotics and provides the basis for effective planning and navigation. In this paper, we learn a compact and continuous implicit surface map of an environment from a stream of range data with known poses. For this, we create and incrementally adjust an ensemble of approximate Gaussian process (GP) experts which are each responsible for a different part of the map. Instead of inserting all arriving data into the GP models, we greedily trade-off between model complexity and prediction error. Our algorithm therefore uses less resources on areas with few geometric features and more where the environment is rich in variety. We evaluate our approach on synthetic and real-world data sets and analyze sensitivity to parameters and measurement noise. The results show that we can learn compact and accurate implicit surface models under different conditions, with a performance …

  • 43.
    Thippur, Akshaya
    et al.
    RPL (CVAP), KTH Royal Institute of Technology, Stockholm, Sweden.
    Stork, Johannes Andreas
    RPL (CVAP), KTH Royal Institute of Technology, Stockholm, Sweden.
    Jensfelt, Patric
    RPL (CVAP), KTH Royal Institute of Technology, Stockholm, Sweden.
    Non-Parametric Spatial Context Structure Learning for Autonomous Understanding of Human Environments2017In: 2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), IEEE conference proceedings, 2017, p. 1317-1324Conference paper (Refereed)
    Abstract [en]

    Autonomous scene understanding by object classification today, crucially depends on the accuracy of appearance based robotic perception. However, this is prone to difficulties in object detection arising from unfavourable lighting conditions and vision unfriendly object properties. In our work, we propose a spatial context based system which infers object classes utilising solely structural information captured from the scenes to aid traditional perception systems. Our system operates on novel spatial features (IFRC) that are robust to noisy object detections; It also caters to on-the-fly learned knowledge modification improving performance with practise. IFRC are aligned with human expression of 3D space, thereby facilitating easy HRI and hence simpler supervised learning. We tested our spatial context based system to successfully conclude that it can capture spatio structural information to do joint object classification to not only act as a vision aide, but sometimes even perform on par with appearance based robotic vision.

  • 44.
    Yang, Quantao
    et al.
    Örebro University, School of Science and Technology.
    Dürr, Alexander
    Department of Computer Science, Faculty of Engineering (LTH), Lund University, Lund, Sweden.
    Topp, Elin Anna
    Department of Computer Science, Faculty of Engineering (LTH), Lund University, Lund, Sweden.
    Stork, Johannes A.
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology. Department of Computing and Software, McMaster University, Hamilton ON, Canada .
    Variable Impedance Skill Learning for Contact-Rich Manipulation2022In: IEEE Robotics and Automation Letters, E-ISSN 2377-3766, Vol. 7, no 3, p. 8391-8398Article in journal (Refereed)
    Abstract [en]

    Contact-rich manipulation tasks remain a hard problem in robotics that requires interaction with unstructured environments. Reinforcement Learning (RL) is one potential solution to such problems, as it has been successfully demonstrated on complex continuous control tasks. Nevertheless, current state-of-the-art methods require policy training in simulation to prevent undesired behavior and later domain transfer even for simple skills involving contact. In this paper, we address the problem of learning contact-rich manipulation policies by extending an existing skill-based RL framework with a variable impedance action space. Our method leverages a small set of suboptimal demonstration trajectories and learns from both position, but also crucially impedance-space information. We evaluate our method on a number of peg-in-hole task variants with a Franka Panda arm and demonstrate that learning variable impedance actions for RL in Cartesian space can be deployed directly on the real robot, without resorting to learning in simulation.

    Download full text (pdf)
    Variable Impedance Skill Learning for Contact-Rich Manipulation
  • 45.
    Yang, Quantao
    et al.
    Örebro University, School of Science and Technology.
    Dürr, Alexander
    Department of Computer Science, Lund University, Sweden.
    Topp, Elin Anna
    Department of Computer Science, Lund University, Sweden.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology.
    Learning Impedance Actions for Safe Reinforcement Learning in Contact-Rich Tasks2021In: NeurIPS 2021 Workshop on Deployable Decision Making in Embodied Systems (DDM), 2021Conference paper (Other academic)
    Abstract [en]

    Reinforcement Learning (RL) has the potential of solving complex continuous control tasks, with direct applications to robotics. Nevertheless, current state-of-the-art methods are generally unsafe to learn directly on a physical robot as exploration by trial-and-error can cause harm to the real world systems. In this paper, we leverage a framework for learning latent action spaces for RL agents from demonstrated trajectories. We extend this framework by connecting it to a variable impedance Cartesian space controller, allowing us to learn contact-rich tasks safely and efficiently. Our method learns from trajectories that incorporate both positional, but also crucially impedance-space information. We evaluate our method on a number of peg-in-hole task variants with a Franka Panda arm and demonstrate that learning variable impedance actions for RL in Cartesian space can be safely deployed on the real robot directly, without resorting to learning in simulation and a subsequent policy transfer.

    Download full text (pdf)
    Learning Impedance Actions for Safe Reinforcement Learning in Contact-Rich Tasks
  • 46.
    Yang, Quantao
    et al.
    Örebro University, School of Science and Technology.
    Stork, Johannes A.
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology.
    Learn from Robot: Transferring Skills for Diverse Manipulation via Cycle Generative Networks2023In: 2023 IEEE 19th International Conference on Automation Science and Engineering (CASE), IEEE conference proceedings, 2023Conference paper (Refereed)
    Abstract [en]

    Reinforcement learning (RL) has shown impressive results on a variety of robot tasks, but it requires a large amount of data for learning a single RL policy. However, in manufacturing there is a wide demand of reusing skills from different robots and it is hard to transfer the learned policy to different hardware due to diverse robot body morphology, kinematics, and dynamics. In this paper, we address the problem of transferring policies between different robot platforms. We learn a set of skills on each specific robot and represent them in a latent space. We propose to transfer the skills between different robots by mapping latent action spaces through a cycle generative network in a supervised learning manner. We extend the policy model learned on one robot with a pre-trained generative network to enable the robot to learn from the skill of another robot. We evaluate our method on several simulated experiments and demonstrate that our Learn from Robot (LfR) method accelerates new skill learning.

  • 47.
    Yang, Quantao
    et al.
    Örebro University, School of Science and Technology.
    Stork, Johannes A.
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology. Department of Computing and Software, McMaster University, Canada.
    MPR-RL: Multi-Prior Regularized Reinforcement Learning for Knowledge Transfer2022In: IEEE Robotics and Automation Letters, E-ISSN 2377-3766, Vol. 7, no 3, p. 7652-7659Article in journal (Refereed)
    Abstract [en]

    In manufacturing, assembly tasks have been a challenge for learning algorithms due to variant dynamics of different environments. Reinforcement learning (RL) is a promising framework to automatically learn these tasks, yet it is still not easy to apply a learned policy or skill, that is the ability of solving a task, to a similar environment even if the deployment conditions are only slightly different. In this letter, we address the challenge of transferring knowledge within a family of similar tasks by leveraging multiple skill priors. We propose to learn prior distribution over the specific skill required to accomplish each task and compose the family of skill priors to guide learning the policy for a new task by comparing the similarity between the target task and the prior ones. Our method learns a latent action space representing the skill embedding from demonstrated trajectories for each prior task. We have evaluated our method on a task in simulation and a set of peg-in-hole insertion tasks and demonstrate better generalization to new tasks that have never been encountered during training. Our Multi-Prior Regularized RL (MPR-RL) method is deployed directly on a real world Franka Panda arm, requiring only a set of demonstrated trajectories from similar, but crucially not identical, problem instances.

  • 48.
    Yang, Quantao
    et al.
    Örebro University, School of Science and Technology.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology.
    Null space based efficient reinforcement learning with hierarchical safety constraints2021In: 2021 European Conference on Mobile Robots (ECMR), IEEE, 2021Conference paper (Refereed)
    Abstract [en]

    Reinforcement learning is inherently unsafe for use in physical systems, as learning by trial-and-error can cause harm to the environment or the robot itself. One way to avoid unpredictable exploration is to add constraints in the action space to restrict the robot behavior. In this paper, we proposea null space based framework of integrating reinforcement learning methods in constrained continuous action spaces. We leverage a hierarchical control framework to decompose target robotic skills into higher ranked tasks (e. g., joint limits and obstacle avoidance) and lower ranked reinforcement learning task. Safe exploration is guaranteed by only learning policies in the null space of higher prioritized constraints. Meanwhile multiple constraint phases for different operational spaces are constructed to guide the robot exploration. Also, we add penalty loss for violating higher ranked constraints to accelerate the learning procedure. We have evaluated our method on different redundant robotic tasks in simulation and show that our null space based reinforcement learning method can explore and learn safely and efficiently.

    Download full text (pdf)
    Null space based efficient reinforcement learning with hierarchical safety constraints
  • 49.
    Yang, Quantao
    et al.
    Örebro University, School of Science and Technology.
    Stork, Johannes Andreas
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology.
    Transferring Knowledge for Reinforcement Learning in Contact-Rich Manipulation2022Conference paper (Refereed)
    Abstract [en]

    In manufacturing, assembly tasks have been a challenge for learning algorithms due to variant dynamics of different environments. Reinforcement learning (RL) is a promising framework to automatically learn these tasks, yet it is still not easy to apply a learned policy or skill, that is the ability of solving a task, to a similar environment even if the deployment conditions are only slightly different. In this paper, we address the challenge of transferring knowledge within a family of similar tasks by leveraging multiple skill priors. We propose to learn prior distribution over the specific skill required to accomplish each task and compose the family of skill priors to guide learning the policy for a new task by comparing the similarity between the target task and the prior ones. Our method learns a latent action space representing the skill embedding from demonstrated trajectories for each prior task. We have evaluated our method on a set of peg-in-hole insertion tasks and demonstrate better generalization to new tasks that have never been encountered during training. 

  • 50.
    Yang, Yuxuan
    et al.
    Örebro University, School of Science and Technology.
    Stork, Johannes A.
    Örebro University, School of Science and Technology.
    Stoyanov, Todor
    Örebro University, School of Science and Technology.
    Particle Filters in Latent Space for Robust Deformable Linear Object Tracking2022In: IEEE Robotics and Automation Letters, E-ISSN 2377-3766, Vol. 7, no 4, p. 12577-12584Article in journal (Refereed)
    Abstract [en]

    Tracking of deformable linear objects (DLOs) is important for many robotic applications. However, achieving robust and accurate tracking is challenging due to the lack of distinctive features or appearance on the DLO, the object's high-dimensional state space, and the presence of occlusion. In this letter, we propose a method for tracking the state of a DLO by applying a particle filter approach within a lower-dimensional state embedding learned by an autoencoder. The dimensionality reduction preserves state variation, while simultaneously enabling a particle filter to accurately track DLO state evolution with a practically feasible number of particles. Compared to previous works, our method requires neither running a high-fidelity physics simulation, nor manual designs of constraints and regularization. Without the assumption of knowing the initial DLO state, our method can achieve accurate tracking even under complex DLO motions and in the presence of severe occlusions.

12 1 - 50 of 59
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf