Learning Human Perception Dynamics for Informative Robot Communication

2025-02-03

AI Summary

This paper addresses the high cognitive load and low communication efficiency in human-robot collaborative navigation caused by information asymmetry. We propose an information-gain-driven visual sharing mechanism. A novel simulation environment, CoNav-Maze, is introduced, enabling robots to navigate autonomously under local sensing while selectively sharing camera views to enhance human environmental understanding. We present the first computational model of human perception dynamics in robot visual communication and propose IG-MCTS—an online algorithm jointly optimizing communication efficiency and task performance. Our approach integrates a fully convolutional neural model of human perception (with data augmentation), eye-tracking evaluation, and a crowdsourced map annotation dataset. User studies demonstrate that, compared to teleoperation and instruction-following baselines, our method achieves comparable task success rates while reducing communication volume by 42% and significantly lowering human cognitive load (p < 0.01, validated via eye-tracking metrics).

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Economics, Online Markets and Human Computation: The sharing economy
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Human-robot cooperative navigation is challenging in environments with incomplete information. We introduce CoNav-Maze, a simulated robotics environment where a robot navigates using local perception while a human operator provides guidance based on an inaccurate map. The robot can share its camera views to improve the operator's understanding of the environment. To enable efficient human-robot cooperation, we propose Information Gain Monte Carlo Tree Search (IG-MCTS), an online planning algorithm that balances autonomous movement and informative communication. Central to IG-MCTS is a neural human perception dynamics model that estimates how humans distill information from robot communications. We collect a dataset through a crowdsourced mapping task in CoNav-Maze and train this model using a fully convolutional architecture with data augmentation. User studies show that IG-MCTS outperforms teleoperation and instruction-following baselines, achieving comparable task performance with significantly less communication and lower human cognitive load, as evidenced by eye-tracking metrics.

Problem

• Develops robot navigation with human guidance.
• Introduces IG-MCTS for efficient human-robot communication.
• Trains neural model on human perception dynamics.

Innovation

• CoNav-Maze simulation for navigation
• IG-MCTS algorithm for planning
• Neural human perception dynamics model