Belief-Aware Influence and Trust (BAIT): Shaping Human Belief During Repeated Human-Robot Interaction

2026-07-28

AI Summary

This work addresses the challenge of belief dynamics in repeated human–robot interaction, where existing approaches either neglect the evolving nature of human beliefs—leading to degraded performance—or rely on unpredictable behaviors that erode trust and hinder scalability. To overcome these limitations, the authors propose the Belief-Aware Interactive Trajectory (BAIT) controller, which explicitly distinguishes between rapid human policy adaptation and slower belief updating. BAIT integrates hierarchical particle filtering with a belief-aware Model Predictive Path Integral (MPPI) planner to jointly optimize long-term influence, user trust, and immediate task performance while satisfying task constraints. Experimental results across simulation, user studies, and real-world lane-changing scenarios with a GEM vehicle demonstrate that BAIT significantly enhances user trust compared to baselines, without compromising task performance, thereby enabling scalable and trustworthy interactive strategies.

Abstract

Repeated human-robot interaction (HRI) requires proactively accounting for humans who continually adapt to evolving beliefs about the robot. Prior frameworks often treat encounters as isolated events, suffering cumulative task performance decay as human perception drifts, or maintain long-term influence through erratic, unpredictable behavior that erodes perceived human trust and relies on computationally unscalable formulations. To address these gaps, we introduce the Belief- Aware Influence and Trust (BAIT) controller. BAIT integrates a hierarchical particle filter, which infers both fast human strategic shifts and slow perceptual belief updates, with a belief-aware Model Predictive Path Integral planner. BAIT explicitly optimizes the trade-off between long-horizon influence and human trust, while enforcing immediate task performance as a strict constraint. Across simulations, a human-subject study, and a real-world GEM vehicle deployments in repeated lane-merging scenarios, BAIT achieves task performance comparable to baselines that optimize long-term influence through unpredictability while yielding significantly higher user trust. The video demonstrating our experiments is available at https://youtu.be/GsPfHRujzVs.

Problem

• human-robot interaction
• belief adaptation
• trust
• task performance
• perception drift

Innovation

• Belief-Aware Control
• Human-Robot Interaction
• Trust Optimization
• Hierarchical Particle Filter
• Model Predictive Path Integral