Integrated task and motion planning in belief space

By Leslie Pack Kaelbling, Tomas Lozano-Perez. 2013

441 citations recorded by the source corpus.

We describe an integrated strategy for planning, perception, state estimation and action in complex mobile manipulation domains based on planning in the belief space of probability distributions over states using hierarchical goal regression (pre-image back-chaining). We develop a vocabulary of logical expressions that describe sets of belief states, which are goals and subgoals in the planning process. We show that a relatively small set of symbolic operators can give rise to task-oriented perception in support of the manipulation goals. An implementation of this method is demonstrated in simulation and on a real PR2 robot, showing robust, flexible solution of mobile manipulation problems with multiple objects and substantial uncertainty.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Control and Systems Engineering, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Robotics & Control

Citations in the corpus

Inner Monologue: Embodied Reasoning through Planning with Language Models (2022, neutral): “, TAMP [1]) or hierarchical learning (e.”
Integrated Task and Motion Planning (2020, unknown): “(102, 116, 117, 118)”
Metric learning for generalizing spatial relations to new objects (2017, unknown): “In the context of robotics, previous work has focused on leveraging predeﬁned relations in the form of symbolic predicates for solving tasks, as in the case of combined task and motion planning or in the context of relational reinforcement learning [4, 8, 12, 22].”
ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation (2024, methodology): “For sequential manipulation tasks, task and motion planning (TAMP) [1, 8, 13] is a widely used framework, often formulated as constraint satisfaction problems [11, 75–80] with continuous geometric problems as subroutines.”
Regression Planning Networks (2019, methodology): “In addition, more principled approaches [19] may require extending RPN to explicitly reason about uncertainty of the state.”
Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation (2022, background): “In the sub-field of Task and Motion Planning (TAMP) [80, 81], Konidaris et al.”
Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planning (2020, methodology): “These methods then plan over them, for example, via trees or optimization-based methods [11, 12, 13, 14, 15, 16, 17].”
Online Replanning in Belief Space for Partially Observable Task and Motion Problems (2019, methodology): “There are many approaches for representing and updating a belief such as joint, unscented Kalman filtering [23], [7], factoring the belief into independent distributions per object [15], [25], and maintaining a particle filter, which represents the belief as a set of weighted samples [17],”
ALLEGRO: Belief-Based Programming in Stochastic Dynamical Domains (2015, background): “…planning [Petrick and Bacchus, 2004; Van Ditmarsch et al., 2007], decision-theoretic proposals [Puterman, 1994; Kaelbling et al., 1998], corresponding relational abstractions [Sanner and Kersting, 2010; Zamani et al., 2012], and belief-based planning [Kaelbling and Lozano-Pérez, 2013].”
The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark Towards Physically Realistic Embodied AI (2021, unknown): “Our work falls in the domain of task and motion planning (TAMP) [22, 23, 18, 42], recently reviewed in [17].”
Effective robot teammate behaviors for supporting sequential manipulation tasks (2015, background): “more powerful abstractions and heuristics for the purpose of reducing search complexity [4], [5] or broadening the types of constraints that can be handled [6], [7], [8], [9].”