A Reactive Framework for Whole-Body Motion Planning of Mobile Manipulators Combining Reinforcement Learning and SDF-Constrained Quadratic Programmi

2025-03-31

AI Summary

To address the low efficiency and poor safety of real-time whole-body motion planning for mobile manipulators in complex environments, this paper proposes a reactive hierarchical motion planning framework integrating reinforcement learning (RL) and optimization-based control. The method introduces two key innovations: (1) a novel Bayesian Distributed Soft Actor-Critic (Bayes-DSAC) algorithm that enhances value estimation accuracy and accelerates policy convergence via probabilistic uncertainty modeling; and (2) a Signed Distance Field (SDF)-based geometric representation coupled with an SDF-constrained quadratic programming (QP) obstacle avoidance module, enabling precise, safe, and computationally efficient real-time collision avoidance. Experimental results demonstrate that the proposed approach significantly reduces planning latency and improves task success rates. On standard benchmarks, it achieves faster learning convergence, superior environmental adaptability, and enhanced robustness and safety compared to state-of-the-art methods.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Multiagent Systems: Multiagent Planning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

As an important branch of embodied artificial intelligence, mobile manipulators are increasingly applied in intelligent services, but their redundant degrees of freedom also limit efficient motion planning in cluttered environments. To address this issue, this paper proposes a hybrid learning and optimization framework for reactive whole-body motion planning of mobile manipulators. We develop the Bayesian distributional soft actor-critic (Bayes-DSAC) algorithm to improve the quality of value estimation and the convergence performance of the learning. Additionally, we introduce a quadratic programming method constrained by the signed distance field to enhance the safety of the obstacle avoidance motion. We conduct experiments and make comparison with standard benchmark. The experimental results verify that our proposed framework significantly improves the efficiency of reactive whole-body motion planning, reduces the planning time, and improves the success rate of motion planning. Additionally, the proposed reinforcement learning method ensures a rapid learning process in the whole-body planning task. The novel framework allows mobile manipulators to adapt to complex environments more safely and efficiently.

Problem

• Improving motion planning for mobile manipulators in cluttered environments
• Enhancing safety in obstacle avoidance using SDF-constrained quadratic programming
• Accelerating learning process in whole-body planning with Bayes-DSAC algorithm

Innovation

• Hybrid learning and optimization framework
• Bayes-DSAC algorithm for better learning
• SDF-constrained quadratic programming for safety