Keywords: Skill Learning, Neuro-Symbolic, Task and Motion Planning
TL;DR: We learn neuro-symbolic skills from demonstrations and plan with them using search-then-sample TAMP techniques.
Abstract: Decision-making is challenging in robotics environments with continuous object-centric states, continuous actions, long horizons, and sparse feedback. Hierarchical approaches, such as task and motion planning (TAMP), address these challenges by decomposing decision-making into two or more levels of abstraction. In a setting where demonstrations and symbolic predicates are given, prior work has shown how to learn symbolic operators and neural samplers for TAMP with manually designed parameterized policies. Our main contribution is a method for learning parameterized polices in combination with operators and samplers. These components are packaged into modular neuro-symbolic skills and sequenced together with search-then-sample TAMP to solve new tasks. In experiments in four robotics domains, we show that our approach --- bilevel planning with neuro-symbolic skills --- can solve a wide range of tasks with varying initial states, goals, and objects, outperforming six baselines and ablations.
Student First Author: yes
Supplementary Material: zip