Online, interactive user guidance for high-dimensional, constrained motion planning
This addresses the challenge of efficient motion planning for complex robots in constrained environments, offering a novel interactive approach that reduces reliance on domain expertise, though it is incremental in combining user guidance with existing algorithms.
The paper tackles the problem of planning collision-free paths for high-dimensional robots by introducing an interactive framework where a motion planner requests user guidance only when progress stalls, using an intermediate configuration to bias the search. They demonstrate this approach with a 34-DOF humanoid robot, showing it can compute highly-constrained paths with minimal domain knowledge, whereas traditional methods require carefully crafted heuristics.
We consider the problem of planning a collision-free path for a high-dimensional robot. Specifically, we suggest a planning framework where a motion-planning algorithm can obtain guidance from a user. In contrast to existing approaches that try to speed up planning by incorporating experiences or demonstrations ahead of planning, we suggest to seek user guidance only when the planner identifies that it ceases to make significant progress towards the goal. Guidance is provided in the form of an intermediate configuration $\hat{q}$, which is used to bias the planner to go through $\hat{q}$. We demonstrate our approach for the case where the planning algorithm is Multi-Heuristic A* (MHA*) and the robot is a 34-DOF humanoid. We show that our approach allows to compute highly-constrained paths with little domain knowledge. Without our approach, solving such problems requires carefully-crafting domain-dependent heuristics.