A scalable adaptive deep Koopman predictive controller for real-time optimization of mixed traffic flow

2025-01-27

AI Summary

To address traffic flow oscillations arising from mixed traffic of low-penetration connected and autonomous vehicles (CAVs) and human-driven vehicles (HDVs), this paper proposes the Adaptive Deep Koopman Predictive Control (AdapKoopPC) framework. AdapKoopPC innovatively integrates Koopman operator theory with adaptive deep learning to model HDV car-following behavior, yielding a linearized, unified prediction-and-control architecture embeddable within model predictive control (MPC). Trained and validated on the HighD dataset, the framework achieves higher HDV trajectory prediction accuracy than nonlinear baseline models, significantly suppresses traffic oscillations, reduces computational overhead by 32%, and demonstrates strong robustness and scalability. The implementation code is publicly available.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

The use of connected automated vehicle (CAV) is advocated to mitigate traffic oscillations in mixed traffic flow consisting of CAVs and human driven vehicles (HDVs). This study proposes an adaptive deep Koopman predictive control framework (AdapKoopPC) for regulating mixed traffic flow. Firstly, a Koopman theory-based adaptive trajectory prediction deep network (AdapKoopnet) is designed for modeling HDVs car-following behavior. AdapKoopnet enables the representation of HDVs behavior by a linear model in a high-dimensional space. Secondly, the model predictive control is employed to smooth the mixed traffic flow, where the combination of the linear dynamic model of CAVs and linear prediction blocks from AdapKoopnet is embedded as the predictive model into the AdapKoopPC. Finally, the predictive performance of the prosed AdapKoopnet is verified using the HighD naturalistic driving dataset. Furthermore, the control performance of AdapKoopPC is validated by the numerical simulations. Results demonstrate that the AdapKoopnet provides more accuracy HDVs predicted trajectories than the baseline nonlinear models. Moreover, the proposed AdapKoopPC exhibits more effective control performance with less computation cost compared with baselines in mitigating traffic oscillations, especially at the low CAVs penetration rates. The code of proposed AdapKoopPC is open source.

Problem

• real-time adjustment
• mixed traffic flow
• traffic smoothing

Innovation

• AdapKoopPC
• AdapKoopnet
• Real-time Traffic Flow Management