Real-Time Adaptive Motion Planning via Point Cloud-Guided, Energy-Based Diffusion and Potential Fields

TL;DR

This paper introduces a real-time motion planning framework that combines energy-based diffusion models with potential fields, using point cloud data for efficient obstacle avoidance in dynamic pursuit-evasion scenarios.

Contribution

It presents a novel integration of diffusion models with potential fields for real-time trajectory planning directly from point cloud data, enabling robust navigation without full environment maps.

Findings

Effective obstacle avoidance in complex environments

Real-time trajectory refinement in dynamic scenarios

Successful application to pursuit-evasion tasks

Abstract

Motivated by the problem of pursuit-evasion, we present a motion planning framework that combines energy-based diffusion models with artificial potential fields for robust real time trajectory generation in complex environments. Our approach processes obstacle information directly from point clouds, enabling efficient planning without requiring complete geometric representations. The framework employs classifier-free guidance training and integrates local potential fields during sampling to enhance obstacle avoidance. In dynamic scenarios, the system generates initial trajectories using the diffusion model and continuously refines them through potential field-based adaptation, demonstrating effective performance in pursuit-evasion scenarios with partial pursuer observability.