DK-RRT: Deep Koopman RRT for Collision-Aware Motion Planning of Space Manipulators in Dynamic Debris Environments

TL;DR

DK-RRT is a novel motion planning framework that combines deep learning, Koopman operator theory, and RRT to enable collision-aware, real-time space manipulator navigation in dynamic debris environments.

Contribution

It introduces a deep Koopman-based RRT approach that improves prediction accuracy and planning efficiency in complex, dynamic orbital debris scenarios.

Findings

Outperforms traditional RRT in dynamic environments

Enhances debris motion prediction with deep Koopman embeddings

Demonstrates real-time adaptability and robustness in simulations

Abstract

Trajectory planning for robotic manipulators operating in dynamic orbital debris environments poses significant challenges due to complex obstacle movements and uncertainties. This paper presents Deep Koopman RRT (DK-RRT), an advanced collision-aware motion planning framework integrating deep learning with Koopman operator theory and Rapidly-exploring Random Trees (RRT). DK-RRT leverages deep neural networks to identify efficient nonlinear embeddings of debris dynamics, enhancing Koopman-based predictions and enabling accurate, proactive planning in real-time. By continuously refining predictive models through online sensor feedback, DK-RRT effectively navigates the manipulator through evolving obstacle fields. Simulation studies demonstrate DK-RRT's superior performance in terms of adaptability, robustness, and computational efficiency compared to traditional RRT and conventional Koopman-based planning, highlighting its potential for autonomous space manipulation tasks.