A Shared Control Framework for Mobile Robots with Planning-Level Intention Prediction

2025-11-12

AI Summary

To address the challenges of inferring human motion intent and achieving seamless human–robot collaboration in shared control of mobile robots, this paper proposes a planning-layer intent-prediction-based shared control framework. Methodologically, it (1) explicitly models human motion intent via an “intent domain”; (2) jointly formulates intent modeling and path re-planning as a Markov decision process (MDP), enabling end-to-end reinforcement learning; and (3) eliminates reliance on real human demonstration data by training entirely in simulation—including a Voronoi-based synthetic human trajectory model. Experimental results demonstrate that the proposed approach significantly reduces operator cognitive load while improving task safety and execution efficiency. It outperforms state-of-the-art assisted teleoperation methods in both simulated and real-user evaluations.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: The sharing economy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

In mobile robot shared control, effectively understanding human motion intention is critical for seamless human-robot collaboration. This paper presents a novel shared control framework featuring planning-level intention prediction. A path replanning algorithm is designed to adjust the robot's desired trajectory according to inferred human intentions. To represent future motion intentions, we introduce the concept of an intention domain, which serves as a constraint for path replanning. The intention-domain prediction and path replanning problems are jointly formulated as a Markov Decision Process and solved through deep reinforcement learning. In addition, a Voronoi-based human trajectory generation algorithm is developed, allowing the model to be trained entirely in simulation without human participation or demonstration data. Extensive simulations and real-world user studies demonstrate that the proposed method significantly reduces operator workload and enhances safety, without compromising task efficiency compared with existing assistive teleoperation approaches.

Problem

• Predicting human motion intentions at planning level for robot control
• Developing path replanning algorithms based on intention prediction
• Enabling safe human-robot collaboration without human demonstration data

Innovation

• Planning-level intention prediction for robot control
• Intention domain concept guides path replanning
• Deep reinforcement learning solves joint prediction and planning