Potential Based Diffusion Motion Planning

TL;DR

This paper introduces a neural network-based approach to potential-based motion planning that learns easily optimizable potentials, outperforming classical methods and avoiding local minima issues, while maintaining composability for various constraints.

Contribution

The paper presents a novel neural network method for learning potential functions in motion planning, enhancing optimization and generalization capabilities.

Findings

Significantly outperforms classical and learned motion planning methods.

Avoids local minima issues common in potential-based planning.

Demonstrates effective composability for different motion constraints.

Abstract

Effective motion planning in high dimensional spaces is a long-standing open problem in robotics. One class of traditional motion planning algorithms corresponds to potential-based motion planning. An advantage of potential based motion planning is composability -- different motion constraints can be easily combined by adding corresponding potentials. However, constructing motion paths from potentials requires solving a global optimization across configuration space potential landscape, which is often prone to local minima. We propose a new approach towards learning potential based motion planning, where we train a neural network to capture and learn an easily optimizable potentials over motion planning trajectories. We illustrate the effectiveness of such approach, significantly outperforming both classical and recent learned motion planning approaches and avoiding issues with local minima. We further illustrate its inherent composability, enabling us to generalize to a multitude of different motion constraints.