aiqbench analysis
This research advances autonomous driving safety by framing mutual communication between human and machine drivers as an information-theoretic problem. By integrating Bayesian persuasion games with inverse reinforcement learning, the study demonstrates a 20% reduction in prediction errors for lane changes while validating subjective driver perceptions of intent signaling. The work establishes that explicit modeling of inquiry and listening affordances is critical for resolving epistemic uncertainty in mixed-autonomy environments.
Pride and Prejudice: Toward an Information-Theoretic Framework for Mutually Communicative Driver Behavior Modeling
arXiv:2606.16735v1 Announce Type: new Abstract: Mixed autonomy driving becomes unsafe and inefficient when autonomous vehicles (AVs) and human-driven vehicles (HVs) misread each other's intentions. We study this problem as implicit mutual communication in lane changes. The proposed framework models how the ego vehicle both expresses its intent and probes the other driver's preference under epistemic uncertainty. It combines a level-k Bayesian persuasion game with virtual features for proactive signaling, information-theoretic rewards for mutual communication, and adaptive weights of communication affordances. We further introduce the Pride-Inquiry (P-I) and Pride-Prejudice (P-P) planes to analyze communication intensity and tendency. The model is calibrated with a Communication-Based Multi-Agent Inverse Reinforcement Learning algorithm (C-MIRL) on the naturalistic NGSIM dataset. Compared with the non-communicative baseline, the proposed model reduces the prediction error of mandatory lane changes by up to 20% while maintaining strong generalization. Driver-In-the-Loop questionnaire scores are positively correlated with the calibrated communication variables, supporting the subjective validity of the model. The learned rewards further show that inquiry and listening affordances contribute more than pride and expression alone, and that inquiry preference varies more strongly across drivers. These results support explicit modeling of mutual communication and epistemic uncertainty in interactive driving.
Abstract:Mixed autonomy driving becomes unsafe and inefficient when autonomous vehicles (AVs) and human-driven vehicles (HVs) misread each other's intentions. We study this problem as implicit mutual communication in lane changes. The proposed framework models how the ego vehicle both expresses its intent and probes the other driver's preference under epistemic uncertainty. It combines a level-k Bayesian persuasion game with virtual features for proactive signaling, information-theoretic rewards for mutual communication, and adaptive weights of communication affordances. We further introduce the Pride-Inquiry (P-I) and Pride-Prejudice (P-P) planes to analyze communication intensity and tendency. The model is calibrated with a Communication-Based Multi-Agent Inverse Reinforcement Learning algorithm (C-MIRL) on the naturalistic NGSIM dataset. Compared with the non-communicative baseline, the proposed model reduces the prediction error of mandatory lane changes by up to 20% while maintaining strong generalization. Driver-In-the-Loop questionnaire scores are positively correlated with the calibrated communication variables, supporting the subjective validity of the model. The learned rewards further show that inquiry and listening affordances contribute more than pride and expression alone, and that inquiry preference varies more strongly across drivers. These results support explicit modeling of mutual communication and epistemic uncertainty in interactive driving.
16 pages, 10 figures. Accepted for the IEEE Transactions on Intelligent Transportation Systems (T-ITS), June 2026
Robotics (cs.RO)
arXiv:2606.16735 [cs.RO]
(or arXiv:2606.16735v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.16735 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 300 words
Related coverage
BRICS Draws a New Global Line: Full Text of New Delhi Declaration
slguardian.org · Sep 12, 2026
Problems of Proliferation
LessWrong · Sep 29, 2026
Dependency, Compression, and Synergy: A Unified Information-Theoretic View of Multimodal Learning
arXiv · Oct 15, 2026
One if by Land, Two if by Sea, Three if by Four Seas, and More to Come -- Values of Perception, Prediction, Communication, and Common Sense in Decision Making
arXiv · Jun 9, 2026