Global-Local Interface for On-Demand Teleoperation

2025-02-14

AI Summary

Existing teleoperation methods struggle to simultaneously achieve large-scale navigation, high-precision dexterous manipulation, and user-friendliness. This paper proposes a Global–Local (G–L) teleoperation interface that, for the first time, decouples and coordinates navigation-level (global) and micro-manipulation-level (local) behaviors. The interface achieves this through motion-scale separation modeling, hierarchical human–robot intent mapping, and real-time behavior switching—enabling unified support for pick-and-place, fine assembly, and large-range positioning tasks on both single- and dual-arm multimodal platforms. Experiments demonstrate significant improvements in operational intuitiveness and task generalizability: the interface achieves ±0.8 mm positioning accuracy in fine assembly tasks, validating its cross-platform compatibility and effectiveness in real-world applications.

Technology Category

• Intelligent Robots: Manipulation
• 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: Practical large-scale studies of user experience

Abstract

Teleoperation is a critical method for human-robot interface, holds significant potential for enabling robotic applications in industrial and unstructured environments. Existing teleoperation methods have distinct strengths and limitations in flexibility, range of workspace and precision. To fuse these advantages, we introduce the Global-Local (G-L) Teleoperation Interface. This interface decouples robotic teleoperation into global behavior, which ensures the robot motion range and intuitiveness, and local behavior, which enhances human operator's dexterity and capability for performing fine tasks. The G-L interface enables efficient teleoperation not only for conventional tasks like pick-and-place, but also for challenging fine manipulation and large-scale movements. Based on the G-L interface, we constructed a single-arm and a dual-arm teleoperation system with different remote control devices, then demonstrated tasks requiring large motion range, precise manipulation or dexterous end-effector control. Extensive experiments validated the user-friendliness, accuracy, and generalizability of the proposed interface.

Problem

• Enhances teleoperation flexibility and precision
• Decouples global and local robotic behaviors
• Supports large-scale and fine manipulation tasks

Innovation

• Global-Local Teleoperation Interface
• Decouples global and local behaviors
• Enhances precision and dexterity