A Unified Sampling-Based Approach to Integrated Task and Motion Planning

Thomason, Wil; Knepper, Ross A.

doi:10.1007/978-3-030-95459-8_47

Cited by 17 publications

(23 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We assume that Q is bounded in all dimensions. This state space construction is similar to those of Thomason and Knepper [34] and Vega-Brown and Roy [37].…”

Section: Dpsqmentioning

confidence: 74%

“…Though the majority of planners use STRIPSlike action descriptions (i.e. precondition and effect formulae over discrete predicate symbols), the symbolic-geometric abstractions used include bespoke abstraction and refinement function pairs [15], symbolic pose references with actionspecific pose samplers [32], several variations on samplers for predicate-satisfying values [16,20,22,34], and others [2,7,10,19,26]. These approaches require manual specification of the symbolic models of their actions.…”

Section: Related Work a Tmp And Action Abstractionsmentioning

confidence: 99%

“…These planning problems, including many real-world mobile manipulation, assembly, and surveillance tasks, are core to practical robot utility. Existing work in TMP has primarily focused on efficiency and has produced planners which can solve reasonably complex problems [15,20,32,34,35]. However, TMP needs more than efficiency to be practically useful.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Counterexample-Guided Repair for Symbolic-Geometric Action Abstractions

Thomason,

Kress-Gazit

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Integrated Task and Motion Planning (TMP) provides a promising class of approaches for solving robot planning problems with intricate symbolic and geometric constraints. However, the practical usefulness of TMP planners is limited by their need for symbolic abstractions of robot actions, which are difficult to construct even for experts. We propose an approach to automatically construct and continuously improve a symbolic abstraction of a robot action via observations of the robot performing the action. This approach, called automatic abstraction repair, allows symbolic abstractions to be initially incorrect or incomplete and converge toward a correct model over time. Abstraction repair uses constrained polynomial zonotopes (CPZs), an efficient non-convex set representation, to model predicates over joint symbolic and geometric state, and performs an optimizing search over symbolic edit operations to predicate formulae to improve the correspondence of a symbolic abstraction to the behavior of a physical robot controller. In this work, we describe the aforementioned predicate model, introduce the symbolic-geometric abstraction repair problem, and present an anytime algorithm for automatic abstraction repair. We then demonstrate that abstraction repair can improve realistic action abstractions for common mobile manipulation actions from a handful of observations.

show abstract

“…We assume that Q is bounded in all dimensions. This state space construction is similar to those of Thomason and Knepper [34] and Vega-Brown and Roy [37].…”

Section: Dpsqmentioning

confidence: 74%

Section: Related Work a Tmp And Action Abstractionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Counterexample-Guided Repair for Symbolic-Geometric Action Abstractions

Thomason,

Kress-Gazit

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Second, symbolic assembly approaches explicitly introduce symbolic states to find task-level decisions and to factorize the problem [20,52,53]. Once symbolic decision sequences (skeletons) are found, lower level planners are used to execute a skeleton, using sampling-based [6,50] or optimizationbased [52] methods. This approach can be tailored towards many different applications, for example by including force constraints [53], dealing with re-planning [32,44] or handling partial observability [39].…”

Section: B Assembly Planningmentioning

confidence: 99%

Long-Horizon Multi-Robot Rearrangement Planning for Construction Assembly

Hartmann¹,

Orthey²,

Driess³

et al. 2021

Preprint

View full text Add to dashboard Cite

Robotic assembly planning has the potential to profoundly change how buildings can be designed and created. It enables architects to explicitly account for the assembly process already during the design phase, and enables efficient building methods that profit from the robots' different capabilities. Previous work has addressed planning of robot assembly sequences and identifying the feasibility of architectural designs. This paper extends previous work by enabling assembly planning with large, heterogeneous teams of robots. We present a scalable planning system which enables parallelization of complex task and motion planning problems by iteratively solving smaller sub-problems. Combining optimization methods to solve for manipulation constraints with a sampling-based bi-directional space-time path planner enables us to plan cooperative multirobot manipulation with unknown arrival-times. Thus, our solver allows for completing sub-problems and tasks with differing timescales and synchronizes them effectively. We demonstrate the approach on multiple case-studies and on two long-horizon building assembly scenarios to show the robustness and scalability of our algorithm.

show abstract

“…TMIT* interleaves asymmetric forward and reverse searches [6] to identify geometrically infeasible plans and avoid computationally expensive action-parameter sampling and motion-planning operations. When combined with novel SMTbased (Satisfiability Modulo Theories [7]) symbolic planning and a differentiable distance-based predicate representation [8], this allows TMIT* to quickly find initial solutions to high-level problems and almost-surely converge asymptotically to the optimum with additional computational time. We demonstrate the benefits of this approach on robotic-manipulation benchmark problems (Figs.…”

Section: Introductionmentioning

confidence: 99%

Task and Motion Informed Trees (TMIT*): Almost-Surely Asymptotically Optimal Integrated Task and Motion Planning

Thomason

Strub

Gammell

2022

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

High-level autonomy requires discrete and continuous reasoning to decide both what actions to take and how to execute them. Integrated Task and Motion Planning (TMP) algorithms solve these hybrid problems jointly to consider constraints between the discrete symbolic actions (i.e., the task plan) and their continuous geometric realization (i.e., motion plans). This joint approach solves more difficult problems than approaches that address the task and motion subproblems independently.TMP algorithms combine and extend results from both task and motion planning. TMP has mainly focused on computational performance and completeness and less on solution optimality. Optimal TMP is difficult because the independent optima of the subproblems may not be the optimal integrated solution, which can only be found by jointly optimizing both plans.This paper presents Task and Motion Informed Trees (TMIT*), an optimal TMP algorithm that combines results from makespanoptimal task planning and almost-surely asymptotically optimal motion planning. TMIT* interleaves asymmetric forward and reverse searches to delay computationally expensive operations until necessary and perform an efficient informed search directly in the problem's hybrid state space. This allows it to solve problems quickly and then converge towards the optimal solution with additional computational time, as demonstrated on the evaluated robotic-manipulation benchmark problems.

show abstract

A Unified Sampling-Based Approach to Integrated Task and Motion Planning

Cited by 17 publications

References 26 publications

Counterexample-Guided Repair for Symbolic-Geometric Action Abstractions

Counterexample-Guided Repair for Symbolic-Geometric Action Abstractions

Long-Horizon Multi-Robot Rearrangement Planning for Construction Assembly

Task and Motion Informed Trees (TMIT*): Almost-Surely Asymptotically Optimal Integrated Task and Motion Planning

Contact Info

Product

Resources

About