MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving

2025-12-03

AI Summary

To address the weak social interaction capability and difficulty in generating human-like behaviors for autonomous driving in dynamic traffic scenarios, this paper proposes an interpretable, socially aware method that integrates physical priors with data-driven learning. We explicitly model multi-vehicle social interaction dynamics for the first time, embedding traffic physics constraints into a discrete state space and employing a Transformer encoder-decoder to learn interaction dynamical coefficients. Furthermore, we incorporate Model Predictive Control (MPC) to enable safe and efficient closed-loop planning. On the NGSIM dataset, our method achieves a 5-second trajectory prediction error of only 0.86 m; in closed-loop evaluation, planning success rate reaches 94.67%, collision rate drops significantly from 21.25% to 0.5%, and traffic throughput improves by 15.75%. The core contribution lies in a physics-guided, interpretable interaction modeling framework, rigorously validated for human-like decision-making in complex traffic environments.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• 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
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Autonomous Driving (AD) vehicles still struggle to exhibit human-like behavior in highly dynamic and interactive traffic scenarios. The key challenge lies in AD's limited ability to interact with surrounding vehicles, largely due to a lack of understanding the underlying mechanisms of social interaction. To address this issue, we introduce MPCFormer, an explainable socially-aware autonomous driving approach with physics-informed and data-driven coupled social interaction dynamics. In this model, the dynamics are formulated into a discrete space-state representation, which embeds physics priors to enhance modeling explainability. The dynamics coefficients are learned from naturalistic driving data via a Transformer-based encoder-decoder architecture. To the best of our knowledge, MPCFormer is the first approach to explicitly model the dynamics of multi-vehicle social interactions. The learned social interaction dynamics enable the planner to generate manifold, human-like behaviors when interacting with surrounding traffic. By leveraging the MPC framework, the approach mitigates the potential safety risks typically associated with purely learning-based methods. Open-looped evaluation on NGSIM dataset demonstrates that MPCFormer achieves superior social interaction awareness, yielding the lowest trajectory prediction errors compared with other state-of-the-art approach. The prediction achieves an ADE as low as 0.86 m over a long prediction horizon of 5 seconds. Close-looped experiments in highly intense interaction scenarios, where consecutive lane changes are required to exit an off-ramp, further validate the effectiveness of MPCFormer. Results show that MPCFormer achieves the highest planning success rate of 94.67%, improves driving efficiency by 15.75%, and reduces the collision rate from 21.25% to 0.5%, outperforming a frontier Reinforcement Learning (RL) based planner.

Problem

• Modeling multi-vehicle social interaction dynamics for autonomous driving
• Enhancing explainability and safety in socially-aware driving systems
• Improving trajectory prediction and planning in interactive traffic scenarios

Innovation

• Physics-informed data-driven model for social interaction dynamics
• Transformer-based encoder-decoder learns dynamics from driving data
• MPC framework ensures safety and human-like behavior generation