XFlowMP: Task-Conditioned Motion Fields for Generative Robot Planning with Schrodinger Bridges

TL;DR

XFlowMP introduces a novel task-conditioned generative motion planning approach using Schrödinger bridges, enabling smooth, collision-free, and dynamically feasible robot trajectories across diverse tasks.

Contribution

The paper proposes XFlowMP, a new method that models robot motion as entropic flows conditioned on tasks, integrating high-order dynamics and real-world feasibility.

Findings

Achieves up to 53.79% lower maximum mean discrepancy

Produces 36.36% smoother motions and 39.88% lower energy consumption

Reduces short-horizon planning time by 11.72%

Abstract

Generative robotic motion planning requires not only the synthesis of smooth and collision-free trajectories but also feasibility across diverse tasks and dynamic constraints. Prior planning methods, both traditional and generative, often struggle to incorporate high-level semantics with low-level constraints, especially the nexus between task configurations and motion controllability. In this work, we present XFlowMP, a task-conditioned generative motion planner that models robot trajectory evolution as entropic flows bridging stochastic noises and expert demonstrations via Schrodinger bridges given the inquiry task configuration. Specifically, our method leverages Schrodinger bridges as a conditional flow matching coupled with a score function to learn motion fields with high-order dynamics while encoding start-goal configurations, enabling the generation of collision-free and dynamically-feasible motions. Through evaluations, XFlowMP achieves up to 53.79% lower maximum mean discrepancy, 36.36% smoother motions, and 39.88% lower energy consumption while comparing to the next-best baseline on the RobotPointMass benchmark, and also reducing short-horizon planning time by 11.72%. On long-horizon motions in the LASA Handwriting dataset, our method maintains the trajectories with 1.26% lower maximum mean discrepancy, 3.96% smoother, and 31.97% lower energy. We further demonstrate the practicality of our method on the Kinova Gen3 manipulator, executing planning motions and confirming its robustness in real-world settings.