Learning Symbolic Operators for Task and Motion Planning
This work addresses the need for efficient planning in robotics by automating operator learning, though it is incremental as it builds on existing TAMP frameworks.
The paper tackles the problem of learning symbolic operators for task and motion planning (TAMP) to improve efficiency in robotic planning, and it shows that their bottom-up relational learning method substantially outperforms baselines, including graph neural network approaches, in three domains.
Robotic planning problems in hybrid state and action spaces can be solved by integrated task and motion planners (TAMP) that handle the complex interaction between motion-level decisions and task-level plan feasibility. TAMP approaches rely on domain-specific symbolic operators to guide the task-level search, making planning efficient. In this work, we formalize and study the problem of operator learning for TAMP. Central to this study is the view that operators define a lossy abstraction of the transition model of a domain. We then propose a bottom-up relational learning method for operator learning and show how the learned operators can be used for planning in a TAMP system. Experimentally, we provide results in three domains, including long-horizon robotic planning tasks. We find our approach to substantially outperform several baselines, including three graph neural network-based model-free approaches from the recent literature. Video: https://youtu.be/iVfpX9BpBRo Code: https://git.io/JCT0g