Planners for real robotic systems should not only reason about abstract actions, but also about aspects related to physical execution such as kinematics and geometry. We present an approach to hybrid task and motion planning, in which state-based forward-chaining task planning is tightly coupled with motion planning and other forms of geometric reasoning. Our approach is centered around the problem of geometric backtracking that arises in hybrid task and motion planning: in order to satisfy the geometric preconditions of the current action, a planner may need to reconsider geometric choices, such as grasps and poses, that were made for previous actions. Geometric backtracking is a necessary condition for completeness, but it may lead to a dramatic computational explosion due to the large size of the space of geometric states. We explore two avenues to deal with this issue: the use of heuristics based on different geometric conditions to guide the search, and the use of geometric constraints to prune the search space. We empirically evaluate these different approaches, and demonstrate that they improve the performance of hybrid task and motion planning. We demonstrate our hybrid planning approach in two domains: a real, humanoid robotic platform, the DLR Justin robot, performing object manipulation tasks; and a simulated autonomous forklift operating in a warehouse.

We propose a constraint-based approach to address a class of problems encountered in combined task and motion planning (CTAMP), which we call kinematically constrained problems. CTAMP is a hybrid planning process in which task planning and geometric reasoning are interleaved. During this process, symbolic action sequences generated by a task planner are geometrically evaluated. This geometric evaluation is a search problem per se, which we refer to as geometric backtrack search. In kinematically constrained problems, a significant computational effort is spent on geometric backtrack search, which impairs search at the task level. At the basis of our approach to address this problem, is the introduction of an intermediate layer between task planning and geometric reasoning. A set of constraints is automatically generated from the symbolic action sequences to evaluate, and combined with a set of constraints derived from the kinematic model of the robot. The resulting constraint network is then used to prune the search space during geometric backtrack search. We present experimental evidence that our approach significantly reduces the complexity of geometric backtrack search on various types of problem.

Combining task and motion planning requires tointerleave causal and geometric reasoning, in order to guaranteethe plan to be executable in the real world. The resulting searchspace, which is the cross product of the symbolic search spaceand the geometric search space, is huge. Systematically calling ageometric reasoner while evaluating symbolic actions is costly. Onthe other hand, geometric reasoning can prune out large parts ofthis search space if geometrically infeasible actions are detectedearly. Hence, we hypothesized the existence of a search depthlevel, until which geometric reasoning can be interleaved withsymbolic reasoning with tractable combinatorial explosion, whilekeeping the benefits of this pruning. In this paper, we propose asimple model that proves the existence of such search depth level,and validate it empirically through experiments in simulation

In this chapter, we describe how Artificial Intelligence planning techniques are used in The Adapted and TRusted Ambient eCOlogies (ATRACO) in order to provide Sphere Adaptation. We introduce the Planning Agent (PA) which plays a central role in the realization and the structural adaptation of activity spheres. Based on particular information included in the ontology of the execution environment, the PA delivers workflows that consist of the basic activities to be executed in order to achieve a user's goals. The PA encapsulates a search engine for hybrid planning--the combination of hierarchical task network planning and partial-order causal-link planning. In this chapter, we describe a formal framework and a development platform for hybrid planning, PANDA. This platform allows for the implementation of many search strategies, and we explain how we realize the search engine of the PA by adapting and configuring PANDA specifically for addressing planning problems that are part of the ATRACO service composition. We describe how the PA interacts with the Sphere Manager and the Ontology Manager in order to create planning problems dynamically and generate workflows in the ATRACO-BPEL language. In addition, an excerpt of a planning domain for ATRACO is provided.

In this article, we describe how real world planning problems can be solved by employing Artificial Intelligence planning techniques. We introduce the paradigm of hybrid planning, which is particularly suited for applications where plans are not intended to be automatically executed by systems, but are made for humans. Hybrid planning combines hierarchical planning – the stepwise refinement of complex tasks – with explicit reasoning about causal dependencies between actions, thereby reflecting exactly the kinds of reasoning humans perform when developing plans. We show how plans are generated and how failed plans are repaired in a way that guarantees stability. Our illustrating examples are taken from a domain model for disaster relief missions enforced upon extensive floods. Finally, we present a tool to support the challenging task of constructing planning domain models.

The article ends with an overview of a wide varity of actual planning applications and outlines further such in the area of cognitive technical systems.

In this paper, we present an approach to aggregating and using devices that support the everyday life of human users in ambient intelligence environments. These execution environments are complex and changing over time, since the devices of the environments are numerous and heterogeneous, and they may appear or disappear at any time. In order to appropriately adapt the ambient system to a user's needs, we adopt a service-oriented approach; i.e., devices provide services that reflect their capabilities. The orchestration of the devices is actually realized with the help of Artificial Intelligence planning techniques and dynamic service binding. At design time, (i) a planning problem is created that consists of the user's goal to be achieved and the services currently offered by the intelligent environment, (ii) the planning problem is then solved using Hierarchical Task Network and Partial-Order Causal-Link planning techniques, (iii) and from the planning decisions taken to find solution plans, abstract service workflows are automatically generated. At run time, the abstract services are dynamically bound to devices that are actually present in the environment. Adaptation of the workflow instantiation is possible due to the late binding mechanism employed. The paper depicts the architecture of our system. It also describes the modeling and the life cycle of the workflows. We discuss the advantages and the limit of our approach with respect to related work and give specific details about implementation. We present some experimental results that validate our system in a real-world application scenario.

Hybrid planning provides a powerful mechanism to solve real-world planning problems. We present a domain-independent, mixed-initiative approach to plan generation that is based on a formal concept of hybrid planning. It allows any interaction modalities and models of initiative while preserving the soundness of the planning process. Adequately involving the decision competences of end-users in this way will improve the application potential as well as the acceptance of the technology.