A Learning-Based Framework for Collision-Free Motion Planning

TL;DR

This paper introduces a learning-based motion planning framework that uses deep neural networks to infer optimal parameters from depth images, enabling real-time, collision-free trajectory planning in cluttered environments without manual tuning.

Contribution

It presents a novel deep learning extension to a CF-based planner that improves efficiency and generalization, overcoming limitations of traditional hand-tuned methods.

Findings

Successful real-time planning in cluttered scenes

Improved task completion rates over classical planners

Effective generalization demonstrated in robot experiments

Abstract

This paper presents a learning-based extension to a Circular Field (CF)-based motion planner for efficient, collision-free trajectory generation in cluttered environments. The proposed approach overcomes the limitations of hand-tuned force field parameters by employing a deep neural network trained to infer optimal planner gains from a single depth image of the scene. The pipeline incorporates a CUDA-accelerated perception module, a predictive agent-based planning strategy, and a dataset generated through Bayesian optimization in simulation. The resulting framework enables real-time planning without manual parameter tuning and is validated both in simulation and on a Franka Emika Panda robot. Experimental results demonstrate successful task completion and improved generalization compared to classical planners.