The Use of Gaze-Derived Confidence of Inferred Operator Intent in Adjusting Safety-Conscious Haptic Assistance

2025-04-04

AI Summary

In remote robotic teleoperation, operators face challenges in intent perception and control alignment due to the absence of visual depth cues and haptic feedback. To address this, this paper proposes an eye-tracking–based, intent-driven haptic assistance framework. It quantifies gaze behavior to model operator intent confidence, enabling— for the first time—the real-time coupling of assistance intensity with human intent certainty. Combined with dynamic safety-boundary–constrained potential-field force feedback, the system adaptively modulates haptic guidance within the human–robot closed loop. Experimental results demonstrate significant improvements: 28.6% higher task accuracy, 22.3% faster completion time, and a 37.1% reduction in errors. Moreover, the approach enhances the naturalness and safety of teleoperation.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Motion & Tracking

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Humans directly completing tasks in dangerous or hazardous conditions is not always possible where these tasks are increasingly be performed remotely by teleoperated robots. However, teleoperation is difficult since the operator feels a disconnect with the robot caused by missing feedback from several senses, including touch, and the lack of depth in the video feedback presented to the operator. To overcome this problem, the proposed system actively infers the operator's intent and provides assistance based on the predicted intent. Furthermore, a novel method of calculating confidence in the inferred intent modifies the human-in-the-loop control. The operator's gaze is employed to intuitively indicate the target before the manipulation with the robot begins. A potential field method is used to provide a guiding force towards the intended target, and a safety boundary reduces risk of damage. Modifying these assistances based on the confidence level in the operator's intent makes the control more natural, and gives the robot an intuitive understanding of its human master. Initial validation results show the ability of the system to improve accuracy, execution time, and reduce operator error.

Problem

• Improving teleoperation accuracy using inferred operator intent
• Enhancing safety with gaze-derived confidence in intent prediction
• Reducing operator error via adaptive haptic assistance

Innovation

• Uses gaze to infer operator intent
• Applies potential field for guiding force
• Adjusts assistance based on confidence level