Using VLM Reasoning to Constrain Task and Motion Planning
This addresses inefficiencies in robotics planning for long-horizon tasks, though it is incremental as it builds on prior constraint-based methods.
The paper tackles the problem of infeasible task-level plans in task and motion planning due to poor downward refinability, proposing VIZ-COAST to use Vision-Language Models for a priori constraint identification, which drastically reduces planning times and sometimes eliminates refinement failures in experiments on three domains.
In task and motion planning, high-level task planning is done over an abstraction of the world to enable efficient search in long-horizon robotics problems. However, the feasibility of these task-level plans relies on the downward refinability of the abstraction into continuous motion. When a domain's refinability is poor, task-level plans that appear valid may ultimately fail during motion planning, requiring replanning and resulting in slower overall performance. Prior works mitigate this by encoding refinement issues as constraints to prune infeasible task plans. However, these approaches only add constraints upon refinement failure, expending significant search effort on infeasible branches. We propose VIZ-COAST, a method of leveraging the common-sense spatial reasoning of large pretrained Vision-Language Models to identify issues with downward refinement a priori, bypassing the need to fix these failures during planning. Experiments on three challenging TAMP domains show that our approach is able to extract plausible constraints from images and domain descriptions, drastically reducing planning times and, in some cases, eliminating downward refinement failures altogether, generalizing to a diverse range of instances from the broader domain.