Interactive Navigation for Legged Manipulators with Learned Arm-Pushing Controller

2025-03-03

AI Summary

This work addresses the challenge of legged robots navigating narrow environments where their body size impedes active obstacle removal, thereby degrading navigation efficiency. We propose an arm-assisted active interaction navigation method. Methodologically, we introduce a novel two-stage reinforcement learning reward mechanism that jointly optimizes contact configuration feasibility and pushing motion stability; further, we integrate an end-to-end arm control policy into the legged robot navigation framework—incorporating kinematic constraint modeling, dynamic contact point tracking, and sim-to-real co-training. Experiments demonstrate: 40% faster policy convergence in simulation; 22% shorter path length and 18% reduction in average traversal time on hardware; and robust multi-step obstacle-pushing navigation in cluttered, complex environments. This work breaks from conventional passive obstacle avoidance paradigms, establishing a new framework for autonomous navigation in confined spaces.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Multiagent Systems: Adversarial Agents
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Interactive navigation is crucial in scenarios where proactively interacting with objects can yield shorter paths, thus significantly improving traversal efficiency. Existing methods primarily focus on using the robot body to relocate large obstacles (which could be comparable to the size of a robot). However, they prove ineffective in narrow or constrained spaces where the robot's dimensions restrict its manipulation capabilities. This paper introduces a novel interactive navigation framework for legged manipulators, featuring an active arm-pushing mechanism that enables the robot to reposition movable obstacles in space-constrained environments. To this end, we develop a reinforcement learning-based arm-pushing controller with a two-stage reward strategy for large-object manipulation. Specifically, this strategy first directs the manipulator to a designated pushing zone to achieve a kinematically feasible contact configuration. Then, the end effector is guided to maintain its position at appropriate contact points for stable object displacement while preventing toppling. The simulations validate the robustness of the arm-pushing controller, showing that the two-stage reward strategy improves policy convergence and long-term performance. Real-world experiments further demonstrate the effectiveness of the proposed navigation framework, which achieves shorter paths and reduced traversal time. The open-source project can be found at https://github.com/Zhihaibi/Interactive-Navigation-for-legged-manipulator.git.

Problem

• Enables legged manipulators to navigate in constrained spaces
• Develops reinforcement learning-based arm-pushing controller
• Improves traversal efficiency by repositioning obstacles

Innovation

• Reinforcement learning-based arm-pushing controller
• Two-stage reward strategy for object manipulation
• Active arm-pushing in constrained environments