Implicit Communication in Human-Robot Collaborative Transport

2025-02-05

AI Summary

In human-robot collaborative object transport, achieving implicit coordination among heterogeneous agents without explicit communication remains a key challenge due to disparities in perception, actuation, and reasoning capabilities. This paper proposes an implicit communication mechanism wherein communicative signals are encoded in physical interaction actions—specifically, in the robot-induced state transitions of the shared object. We further introduce a joint policy inference model embedded within a Model Predictive Control (MPC) framework, incorporating a human strategy uncertainty cost to jointly optimize collaboration fluency and task efficiency. The method integrates probabilistic inference, latent-variable modeling, and human-robot behavioral modeling, and is implemented on the Stretch mobile manipulator platform. A user study with 24 participants demonstrates statistically significant improvements in team transport performance over a no-communication baseline; users also subjectively rated the robot as significantly more fluent and competent.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Multiagent Systems: Coordination and Collaboration

Application Category

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

Abstract

We focus on human-robot collaborative transport, in which a robot and a user collaboratively move an object to a goal pose. In the absence of explicit communication, this problem is challenging because it demands tight implicit coordination between two heterogeneous agents, who have very different sensing, actuation, and reasoning capabilities. Our key insight is that the two agents can coordinate fluently by encoding subtle, communicative signals into actions that affect the state of the transported object. To this end, we design an inference mechanism that probabilistically maps observations of joint actions executed by the two agents to a set of joint strategies of workspace traversal. Based on this mechanism, we define a cost representing the human's uncertainty over the unfolding traversal strategy and introduce it into a model predictive controller that balances between uncertainty minimization and efficiency maximization. We deploy our framework on a mobile manipulator (Hello Robot Stretch) and evaluate it in a within-subjects lab study (N=24). We show that our framework enables greater team performance and empowers the robot to be perceived as a significantly more fluent and competent partner compared to baselines lacking a communicative mechanism.

Problem

• implicit communication in human-robot transport
• coordination without explicit signals
• enhancing fluency and competence in collaboration

Innovation

• Implicit communication encoding
• Probabilistic inference mechanism
• Model predictive controller