oru.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Grosinger, Jasmin
Publications (9 of 9) Show all publications
Grosinger, J. (2019). On Making Robots Proactive. (Doctoral dissertation). Örebro: Örebro University
Open this publication in new window or tab >>On Making Robots Proactive
2019 (English)Doctoral thesis, monograph (Other academic)
Abstract [en]

The question addressed in this thesis is: Can we make robots proactive? Proactivity is understood as self-initiated, anticipatory action. This entails the ability to generate own goals and pursue them. Our work is based on the assumption that proactivity makes robots more acceptable in human-inhabited environments. Proactive behavior is opposed to reactive behavior which is merely responding to external events and explicit requests (by the user). We approach the question of how to make robots proactive by first identifying the necessary cognitive capabilities, how they relate and interact. We find that to enable proactive behavior one needs to bridge the gap between context, planning, acting and goal reasoning. We then propose a model of opportunity which formalizes and relates these cognitive capabilities in order to create proactivity. In order to make the model of opportunity computational we introduce a framework called equilibrium maintenance. We show formally and empirically that the framework can make robots act in a proactive way. We can make guarantees about the behavior of a robot acting based on equilibrium maintenance: we prove that given certain assumptions a system employing our framework is kept within desirable states. Equilibrium maintenance is instantiated in different scenarios, both theoretically and in practice by deploying it in a number of systems including both robots and humans. More specifically, we conduct experimental runs in simulation in the domain of robotic disaster management and we implement the framework on a real robot in a domestic environment. The latter is done by integration in different levels, from conceptual examples to closing the loop with a full robotic system. Empirical results confirm that equilibrium maintenance creates proactive behavior and leads to preferable outcomes.

Place, publisher, year, edition, pages
Örebro: Örebro University, 2019. p. 179
Series
Örebro Studies in Technology, ISSN 1650-8580 ; 87
Keywords
Proactive robots, Goal Reasoning, Knowledge representation and reasoning, Fuzzy logic
National Category
Computer Sciences
Identifiers
urn:nbn:se:oru:diva-77548 (URN)978-91-7529-312-7 (ISBN)
Public defence
2019-12-06, Örebro universitet, Långhuset, Hörsal L1, Fakultetsgatan 1, Örebro, 13:15 (English)
Opponent
Supervisors
Available from: 2019-10-23 Created: 2019-10-23 Last updated: 2019-11-13Bibliographically approved
Grosinger, J., Pecora, F. & Saffiotti, A. (2019). Robots that Maintain Equilibrium: Proactivity by Reasoning About User Intentions and Preferences. Pattern Recognition Letters, 118, 85-93
Open this publication in new window or tab >>Robots that Maintain Equilibrium: Proactivity by Reasoning About User Intentions and Preferences
2019 (English)In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 118, p. 85-93Article in journal (Refereed) Published
Abstract [en]

Robots need to exhibit proactive behavior if they are to be accepted in human-centered environments. A proactive robot must reason about the actions it can perform, the state of the environment, the state and the intentions of its users, and what the users deem desirable. This paper proposes a computational framework for proactive robot behavior that formalizes the above ingredients. The framework is grounded on the notion of Equilibrium Maintenance: current and future states are continuously evaluated to identify opportunities for acting that steer the system into more desirable states. We show that this process leads a robot to proactively generate its own goals and enact them, and that the obtained behavior depends on a model of user intentions, preferences, and the temporal horizon used in prediction. A number of examples show that our framework accounts for even slight variations in user preference models and perceived user intentions. We also show how the level of informedness of the system is easily customizable.

Place, publisher, year, edition, pages
Elsevier, 2019
Keywords
Robot proactivity, Equilibrium maintenance, Goal reasoning, Fuzzy models
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-65667 (URN)10.1016/j.patrec.2018.05.014 (DOI)000457976400010 ()2-s2.0-85048078578 (Scopus ID)
Funder
Swedish Research Council, PGR00193
Note

Funding Agency:

Semantic Robots Research Profile (Swedish Knowledge Foundation)

Available from: 2018-03-12 Created: 2018-03-12 Last updated: 2019-02-19Bibliographically approved
Grosinger, J., Pecora, F. & Saffiotti, A. (2017). Proactivity through equilibrium maintenance with fuzzy desirability. In: 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC): . Paper presented at IEEE International Conference on Systems, Man and Cybernetics (SMC 2017), Banff, AB, Canada, October 5-8, 2017. Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>Proactivity through equilibrium maintenance with fuzzy desirability
2017 (English)In: 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Institute of Electrical and Electronics Engineers (IEEE), 2017Conference paper, Published paper (Refereed)
Abstract [en]

Proactive cognitive agents need to be capable ofboth generating their own goals and enacting them. In thispaper, we cast this problem as that ofmaintaining equilibrium,that is, seeking opportunities to act that keep the system indesirable states while avoiding undesirable ones. We characterizedesirability of states as graded preferences, using mechanismsfrom the field of fuzzy logic. As a result, opportunities for anagent to act can also be graded, and their relative preferencecan be used to infer when and how to act. This paper providesa formal description of our computational framework, andillustrates how the use of degrees of desirability leads to well-informed choices of action.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2017
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:oru:diva-59447 (URN)10.1109/SMC.2017.8122932 (DOI)000427598702027 ()2-s2.0-85044369004 (Scopus ID)978-1-5386-1645-1 (ISBN)978-1-5386-1644-4 (ISBN)978-1-5386-1646-8 (ISBN)
Conference
IEEE International Conference on Systems, Man and Cybernetics (SMC 2017), Banff, AB, Canada, October 5-8, 2017
Note

Funding Agencies:

Italian Ministry of Foreign Affairs and International Cooperation (MAECI)  

Italian Ministry of Education, Universities and Research (MIUR)  

Swedish Research Council (VR Project WearAmI)  PGR00193 

Semantic Robots Research Profile (Swedish Knowledge Foundation) 

Available from: 2017-09-04 Created: 2017-09-04 Last updated: 2018-04-19Bibliographically approved
Grosinger, J., Pecora, F. & Saffiotti, A. (2016). Making Robots Proactive through Equilibrium Maintenance. In: 25th International Joint Conference on Artificial Intelligence: . Paper presented at 25th International Joint Conference on Artificial Intelligence, New York City, USA, 9-5 July, 2016.
Open this publication in new window or tab >>Making Robots Proactive through Equilibrium Maintenance
2016 (English)In: 25th International Joint Conference on Artificial Intelligence, 2016Conference paper, Published paper (Refereed)
National Category
Computer Sciences Robotics Computer Vision and Robotics (Autonomous Systems)
Research subject
Computer Science; Informatics
Identifiers
urn:nbn:se:oru:diva-51100 (URN)
Conference
25th International Joint Conference on Artificial Intelligence, New York City, USA, 9-5 July, 2016
Available from: 2016-06-30 Created: 2016-06-30 Last updated: 2018-01-10Bibliographically approved
Bruno, B., Grosinger, J., Mastrogiovanni, F., Pecora, F., Saffiotti, A., Sathyakeerthy, S. & Sgorbissa, A. (2015). Multi-modal sensing for human activity recognition. In: Proceedings of the 24th IEEE International Symposium on Robot and Human Interactive Communication, Kobe, Japan, Aug 31 - Sept 4, 2015: . Paper presented at 24th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), Kobe, Japan, August 31 - September 4, 2015 (pp. 594-600). New York: IEEE conference proceedings
Open this publication in new window or tab >>Multi-modal sensing for human activity recognition
Show others...
2015 (English)In: Proceedings of the 24th IEEE International Symposium on Robot and Human Interactive Communication, Kobe, Japan, Aug 31 - Sept 4, 2015, New York: IEEE conference proceedings , 2015, p. 594-600Conference paper, Published paper (Refereed)
Abstract [en]

Robots for the elderly are a particular category of home assistive robots, aiming at assisting the elderly inthe execution of daily life tasks to extend their independent life. To this aim, such robots should be able to determine the level of independence of the user and track its evolution over time, to adapt the assistance to the person capabilities and needs. Human Activity Recognition systems employ various sensing strategies, relying on environmental or wearable sensors,to recognize various daily life activities which provide insights on the health status of a person. The main contribution of the article is the design of an heterogeneous information management framework, allowing for the description of a wide variety of human activities in terms of multi-modal environmental and wearable sensing data and providing accurate knowledge about the user activity to any assistive robot.

Place, publisher, year, edition, pages
New York: IEEE conference proceedings, 2015
Keywords
Detecting and Understanding Human Activity, Assistive Robotics, Multi-modal Situation Awareness and Spatial Cognition
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-45483 (URN)10.1109/ROMAN.2015.7333653 (DOI)000380393600100 ()2-s2.0-84954052931 (Scopus ID)978-1-4673-6704-2 (ISBN)
Conference
24th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), Kobe, Japan, August 31 - September 4, 2015
Available from: 2015-08-06 Created: 2015-08-06 Last updated: 2018-01-11Bibliographically approved
Di Rocco, M., Sathyakeerthy, S., Grosinger, J., Pecora, F., Saffiotti, A., Bonaccorsi, M., . . . Dario, P. (2014). A Planner for Ambient Assisted Living: From High-Level Reasoning to Low-Level Robot Execution and Back. In: Papers from the AAAI Spring Symposium: . Paper presented at AAAI Spring Symposium on Qualitative Representations for Robots. March 23-25, 2014. Palo Alto, USA.. AAAI Press
Open this publication in new window or tab >>A Planner for Ambient Assisted Living: From High-Level Reasoning to Low-Level Robot Execution and Back
Show others...
2014 (English)In: Papers from the AAAI Spring Symposium, AAAI Press, 2014Conference paper, Published paper (Refereed)
Abstract [en]

Robot ecologies are a growing paradigm in which oneor several robotic systems are integrated into a smartenvironment. Robotic ecologies hold great promises forelderly assistance. Planning the activities of these systems,however, is not trivial, and requires considerationof issues like temporal and information dependenciesamong different parts of the ecology, exogenous actions,and multiple, dynamic goals. We describe a plannerable to cope with the above challenges. We showin particular how this planner has been incorporatedin closed-loop into a full robotic system that performsdaily tasks in support of elderly people. The full robotecology is deployed in a test apartment inside a real residentialbuilding, and it is currently undergoing an extensiveuser evaluation.

Place, publisher, year, edition, pages
AAAI Press, 2014
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-41649 (URN)
Conference
AAAI Spring Symposium on Qualitative Representations for Robots. March 23-25, 2014. Palo Alto, USA.
Projects
Robot-Era
Funder
EU, FP7, Seventh Framework Programme, 288899
Available from: 2015-01-15 Created: 2015-01-15 Last updated: 2018-09-06Bibliographically approved
Grosinger, J., Pecora, F. & Saffiotti, A. (2014). Find Out Why Reading This Paper is an Opportunity of Type Opp0. In: CogRob 2014: The 9th International Workshop on Cognitive Robotics. Paper presented at CogRob 2014: The 9th International Workshop on Cognitive Robotics, Prague, Czech Republic, August 18-19, 2014.
Open this publication in new window or tab >>Find Out Why Reading This Paper is an Opportunity of Type Opp0
2014 (English)In: CogRob 2014: The 9th International Workshop on Cognitive Robotics, 2014, , p. 6Conference paper, Published paper (Refereed)
Abstract [en]

Under what conditions should a cognitive robot act? How do we define “opportunities” for robot action? How can we characterize their properties? This paper offers an apparatus to frame thediscussion. Starting from a simple introductory example, we specifyan initial version of a formal framework of opportunity which relates current and future states and beneficial courses of action in a certain time horizon. An opportunity reasoning algorithm is presented,which opens up various new questions about the different types of opportunity and how to interleave opportunity reasoning and action execution. An implementation of this algorithm is tested in a simple experiment including a real mobile robot in a smart home environment and a user.

Publisher
p. 6
Keywords
Cognitive Robotics, Robot Action, Decision Making, Autonomous Systems, Planning
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:oru:diva-40202 (URN)
Conference
CogRob 2014: The 9th International Workshop on Cognitive Robotics, Prague, Czech Republic, August 18-19, 2014
Projects
Robot-Era
Funder
EU, FP7, Seventh Framework Programme, 288899
Available from: 2015-01-07 Created: 2015-01-07 Last updated: 2019-10-02Bibliographically approved
Grosinger, J., Pecora, F. & Saffiotti, A. (2014). Robots and Bananas: Exploring Deliberation in Cognitive Robots. In: AI and Robotics: Papers from the AAAI-14 Workshop. Paper presented at Workshops at the Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI-14, Quebec, Canada, July 27-28, 2014.
Open this publication in new window or tab >>Robots and Bananas: Exploring Deliberation in Cognitive Robots
2014 (English)In: AI and Robotics: Papers from the AAAI-14 Workshop, 2014, , p. 2Conference paper, Published paper (Refereed)
Abstract [en]

Under what conditions should a cognitive robot act? How do we define “opportunities” for robot action? How can we characterize their properties? In this po-sition paper, we offer an initial apparatus to formalize opportunities and to frame this discussion.

Publisher
p. 2
Keywords
Cognitive Robotics, Robot Action, Decision Making, Autonomous Systems, Planning
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:oru:diva-40200 (URN)
Conference
Workshops at the Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI-14, Quebec, Canada, July 27-28, 2014
Projects
Robot-Era
Available from: 2015-01-07 Created: 2015-01-07 Last updated: 2019-04-11Bibliographically approved
Grosinger, J., Vetere, F. & Fitzpatrick, G. (2012). Agile Life: addressing knowledge and social motivations for active aging. In: Proceedings of the 24th Australian Computer-Human Interaction Conference: . Paper presented at 24th Australian Computer-Human Interaction Conference, Melbourne, 26-30 November, 2012 (pp. 162-165). Association for Computing Machinery (ACM)
Open this publication in new window or tab >>Agile Life: addressing knowledge and social motivations for active aging
2012 (English)In: Proceedings of the 24th Australian Computer-Human Interaction Conference, Association for Computing Machinery (ACM), 2012, p. 162-165Conference paper, Published paper (Refereed)
Abstract [en]

Despite the inter-relationship between physical, cognitive and social factors for older people, the frequency of physical activity typically decreases with age. In this paper, we focus on two specific issues related to physical activity and older people - overcoming the knowledgebarrier and promoting social motivation. We develop a tablet-based prototype called Agile Life that provides ‘Physical Activity Information Chunks’ (PAICs) and also promotes awareness of friends’ activities and opportunities to join in. The results of a user study, including a think-aloud walkthrough and an adapted technology probe, suggest that the social engagement with friends is a strong motivator but that the content of information chunks need to be carefully tailored to the participant. We provide suggestions for further developing an activity application for this age group.

Place, publisher, year, edition, pages
Association for Computing Machinery (ACM), 2012
Keywords
Active Aging, Exercise, Older adults. Persuasive, technology, Physical activity, Tablet, Technology Probe, User-centered design.
National Category
Computer Sciences
Identifiers
urn:nbn:se:oru:diva-40891 (URN)10.1145/2414536.2414566 (DOI)2-s2.0-84872304292 (Scopus ID)9781450314381 (ISBN)
Conference
24th Australian Computer-Human Interaction Conference, Melbourne, 26-30 November, 2012
Available from: 2015-01-12 Created: 2015-01-12 Last updated: 2018-03-05Bibliographically approved
Organisations

Search in DiVA

Show all publications