Testing of Automotive CPS

Game Theoretic Traffic Simulator (GTTS) for Autonomous Vehicle Control System Verification and Validation

The Game Theoretic Traffic Simulator (GTTS) models and simulates heterogeneous and interactive traffic, where interactions among human-driven and/or autonomous vehicles in multi-vehicle traffic scenarios are represented based on a game-theoretic framework. The GTTS supports the verification and validation of autonomous vehicle control systems, discovering faults, identifying corner cases, and informing test trajectory generation.

Game-theoretic highway traffic model

A highway traffic model based on a level-k game formulation.

Integration with high-fidelity simulator

Our game-theoretic highway traffic model has been integrated with The Open Racing Car Simulator (TORCS) [link]. Our model simulates the interactive decision-making processes of the drivers and TORCS simulates the vehicle dynamics.

Autonomous vehicle control systems can be implemented and tested in simulated multi-vehicle traffic scenarios. The performance in terms of user-defined metrics can be evaluated based on simulation results. Critical scenarios can be extracted and recorded for post-analysis.

Program packages

We welcome download and usage of our model and simulator for autonomous driving research activities.

Game-theoretic driver/vehicle decision-making model (Java): Policy training, Heterogeneous and interactive traffic simulation, Testing of control algorithm examples (Decision-tree based controller, Stackelberg-game based controller, Finite-state-machine based controller, Human operation). [download]
Plot traffic simulation trajectories (Matlab). [download]
Integration with TORCS (C++): Decision making + Vehicle dynamics and control. [download]

If you find these packages useful, please acknowledge us. Thank you very much!

Game-theoretic urban traffic model

Our game-theoretic framework has been extended and recently applied to modeling vehicle interactions in urban traffic , with focus on uncontrolled intersections.

Program

Game-theoretic intersection model (Matlab). [download]

An intersection traffic model based on a leader-follower game formulation.

The model is capable of reproducing real-world traffic scenarios extracted from traffic data.

List of publications

Highway traffic modeling:

Li, N., Oyler, D. W., Zhang, M., Yildiz, Y., Kolmanovsky, I., & Girard, A. R. (2018). Game theoretic modeling of driver and vehicle interactions for verification and validation of autonomous vehicle control systems. IEEE Transactions on control systems technology, 26(5), 1782-1797. [link]
Li, N., Zhang, M., Yildiz, Y., Kolmanovsky, I., & Girard, A. (2018). Game theory-based traffic modeling for calibration of automated driving algorithms. In Control Strategies for Advanced Driver Assistance Systems and Autonomous Driving Functions (pp. 89-106). Springer, Cham. [link]
Su, G., Li, N., Yildiz, Y., Girard, A., & Kolmanovsky, I. (2018, December). A traffic simulation model with interactive drivers and high-fidelity car dynamics. In Cyber-Physical & Human Systems (CPHS), 2nd IFAC Conference on. IFAC-PapersOnLine, 51(34), 384-389. [link]
Li, N., Oyler, D., Zhang, M., Yildiz, Y., Girard, A., & Kolmanovsky, I. (2016, December). Hierarchical reasoning game theory based approach for evaluation and testing of autonomous vehicle control systems. In Decision and Control (CDC), 2016 IEEE 55th Conference on (pp. 727-733). IEEE. [link]
Oyler, D. W., Yildiz, Y., Girard, A. R., Li, N. I., & Kolmanovsky, I. V. (2016, July). A game theoretical model of traffic with multiple interacting drivers for use in autonomous vehicle development. In American Control Conference (ACC), 2016 (pp. 1705-1710). IEEE. [link]

Urban traffic modeling:

Li, N., Yao, Y., Kolmanovsky, I., Atkins, E., & Girard, A. (2019). Game-theoretic modeling of multi-vehicle interactions at uncontrolled intersections. IEEE Transactions on Intelligent Transportation Systems, under review.
Tian, R., Li, S., Li, N., Kolmanovsky, I., Girard, A., & Yildiz, Y. (2018, December). Adaptive game theoretic decision making for autonomous vehicle control at roundabouts. In Decision and Control (CDC), 2018 IEEE 57th Conference on (pp. 321-326). IEEE. [link]
Li, N., Kolmanovsky, I., Girard, A., & Yildiz, Y. (2018, June). Game theoretic modeling of vehicle interactions at unsignalized intersections and application to autonomous vehicle control. In American Control Conference (ACC), 2018 (pp. 3215-3220). IEEE. [link]

Other relevant publications:

Li, N., Girard, A., & Kolmanovsky, I. (2019). Stochastic predictive control for partially observable Markov decision processes with time-joint chance constraints and application to autonomous vehicle control. ASME Journal of Dynamic Systems, Measurement, and Control, 141(7), 071007. [link]
Li, S., Li, N., Girard, A., & Kolmanovsky, I. (2019). Decision making in dynamic and interactive environment based on cognitive hierarchy theory: formulation, solution, and application to autonomous driving. In Decision and Control (CDC), 2019 IEEE 58th Conference on, accepted. IEEE.
Li, N., Kolmanovsky, I., & Girard, A. (2018). Tractable stochastic predictive control for partially observable Markov decision processes with time-joint chance constraints. In Decision and Control (CDC), 2018 IEEE 57th Conference on (pp. 3276-3282). IEEE. [link]
Li, N., Chen, H., Kolmanovsky, I., & Girard, A. (2017, October). An explicit decision tree approach for automated driving. In Dynamic Systems and Control Conference (DSCC), 2017 (pp. V001T45A003-V001T45A003). ASME. [link]
Zhang, M., Li, N., Girard, A., & Kolmanovsky, I. (2017, October). A finite state machine based automated driving controller and its stochastic optimization. In Dynamic Systems and Control Conference (DSCC), 2017 (pp. V002T07A002-V002T07A002). ASME. [link]

Report abuse