🤖 AI Summary
Implicit communication in human–robot interaction remains challenging due to its reliance on explicit intent modeling and domain-specific prior knowledge. Method: This paper proposes a transfer entropy (TE)-based influence modeling framework within a partially observable Markov decision process (POMDP), dynamically quantifying interactive influence and directly embedding it into the reinforcement learning reward function—enabling adaptive implicit communication without intent recognition or handcrafted domain knowledge. Contribution/Results: To our knowledge, this is the first work to employ TE-driven influence measurement for reward shaping. It uncovers a novel mechanism: influence enhancement fosters cooperation, whereas resistance to influence degrades performance—validated in both cooperative and competitive settings. Simulations and real-world social navigation experiments demonstrate significant improvements: 32% higher task success rate in collaborative scenarios, 27% reduction in response latency, and markedly enhanced accuracy in inferring human nonverbal intent.
📝 Abstract
Communication is essential for successful interaction. In human-robot interaction, implicit communication holds the potential to enhance robots' understanding of human needs, emotions, and intentions. This paper introduces a method to foster implicit communication in HRI without explicitly modelling human intentions or relying on pre-existing knowledge. Leveraging Transfer Entropy, we modulate influence between agents in social interactions in scenarios involving either collaboration or competition. By integrating influence into agents' rewards within a partially observable Markov decision process, we demonstrate that boosting influence enhances collaboration, while resisting influence diminishes performance. Our findings are validated through simulations and real-world experiments with human participants in social navigation settings.