Efficient Hierarchical Robot Motion Planning Under Uncertainty and Hybrid Dynamics
This work addresses motion planning challenges for robots in noisy, nonlinear environments, but it is incremental as it builds on existing hybrid dynamics and hierarchical methods.
The paper tackles robot motion planning under uncertainty and nonlinear dynamics by proposing a hierarchical POMDP planner that decomposes the problem into smaller parts, resulting in significantly lower computational costs while effectively handling high observation noise and nonlinear dynamics in simulated navigation and robotic assembly tasks.
Noisy observations coupled with nonlinear dynamics pose one of the biggest challenges in robot motion planning. By decomposing nonlinear dynamics into a discrete set of local dynamics models, hybrid dynamics provide a natural way to model nonlinear dynamics, especially in systems with sudden discontinuities in dynamics due to factors such as contacts. We propose a hierarchical POMDP planner that develops cost-optimized motion plans for hybrid dynamics models. The hierarchical planner first develops a high-level motion plan to sequence the local dynamics models to be visited and then converts it into a detailed continuous state plan. This hierarchical planning approach results in a decomposition of the POMDP planning problem into smaller sub-parts that can be solved with significantly lower computational costs. The ability to sequence the visitation of local dynamics models also provides a powerful way to leverage the hybrid dynamics to reduce state uncertainty. We evaluate the proposed planner on a navigation task in the simulated domain and on an assembly task with a robotic manipulator, showing that our approach can solve tasks having high observation noise and nonlinear dynamics effectively with significantly lower computational costs compared to direct planning approaches.