Online Replanning in Belief Space for Partially Observable Task and Motion Problems
By Caelan Reed Garrett, Chris Paxton, Tomas Lozano-Perez, Leslie Pack Kaelbling, Dieter Fox. 2019
145 citations recorded by the source corpus.
To solve multi-step manipulation tasks in the real world, an autonomous robot must take actions to observe its environment and react to unexpected observations. This may require opening a drawer to observe its contents or moving an object out of the way to examine the space behind it. Upon receiving a new observation, the robot must update its belief about the world and compute a new plan of action. In this work, we present an online planning and execution system for robots faced with these challenges. We perform deterministic cost-sensitive planning in the space of hybrid belief states to select likely-to-succeed observation actions and continuous control actions. After execution and observation, we replan using our new state estimate. We initially enforce that planner reuses the structure of the unexecuted tail of the last plan. This both improves planning efficiency and ensures that the overall policy does not undo its progress towards achieving the goal. Our approach is able to efficiently solve partially observable problems both in simulation and in a real-world kitchen.
Subfields: Reinforcement Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Reinforcement Learning
- Sergey Levine
- Chelsea Finn
- Pieter Abbeel
- Karol Hausman
- Pierre Sermanet
- Ted Xiao
- Josh Tenenbaum
- Jitendra Malik
Citations in the corpus
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (2022, methodology): “Machine learning has recently been applied to enable abstract task specification, allow general primitives, or relax constraints [67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78].”
- Habitat 2.0: Training Home Assistants to Rearrange their Habitat (2021, background): “[56] study replanning in the presence of partial observability but do not consider mobile manipulation.”
- Integrated Task and Motion Planning (2020, unknown): “(102, 116, 117, 118)”
- Inventing Relational State and Action Abstractions for Effective and Efficient Bilevel Planning (2022, background): “Finally, for (4) we would like to draw insights from recent advances in task and motion planning, in both the stochastic setting [92] and the partially observed setting [93].”