When should the chicken cross the road? Game theory for autonomous vehicle - human interactions

TY - GEN

T1 - When should the chicken cross the road? Game theory for autonomous vehicle - human interactions

AU - Fox, C. W.

AU - Camara, F.

AU - Markkula, G.

AU - Romano, R. A.

AU - Madigan, R.

AU - Merat, N.

N1 - Funding Information: This project has received funding from the European Union’s Horizon 2020 Research and Innovation programme under grant agreement InterACT No 723395. Publisher Copyright: Copyright © 2018 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved

PY - 2018

Y1 - 2018

N2 - Autonomous vehicle localization, mapping and planning in un-reactive environments are well-understood, but the human factors of complex interactions with other road users are not yet developed. This study presents an initial model for negotiation between an autonomous vehicle and another vehicle at an unsigned intersections or (equivalently) with a pedestrian at an unsigned road-crossing (jaywalking), using discrete sequential game theory. The model is intended as a basic framework for more realistic and data-driven future extensions. The model shows that when only vehicle position is used to signal intent, the optimal behaviors for both agents must include a non-zero probability of allowing a collision to occur. This suggests extensions to reduce this probability in future, such as other forms of signaling and control. Unlike most Game Theory applications in Economics, active vehicle control requires real-time selection from multiple equilibria with no history, and we present and argue for a novel solution concept, meta-strategy convergence, suited to this task.

AB - Autonomous vehicle localization, mapping and planning in un-reactive environments are well-understood, but the human factors of complex interactions with other road users are not yet developed. This study presents an initial model for negotiation between an autonomous vehicle and another vehicle at an unsigned intersections or (equivalently) with a pedestrian at an unsigned road-crossing (jaywalking), using discrete sequential game theory. The model is intended as a basic framework for more realistic and data-driven future extensions. The model shows that when only vehicle position is used to signal intent, the optimal behaviors for both agents must include a non-zero probability of allowing a collision to occur. This suggests extensions to reduce this probability in future, such as other forms of signaling and control. Unlike most Game Theory applications in Economics, active vehicle control requires real-time selection from multiple equilibria with no history, and we present and argue for a novel solution concept, meta-strategy convergence, suited to this task.

KW - Autonomous Vehicles

KW - Game Theory

KW - Human Factors

UR - http://www.scopus.com/inward/record.url?scp=85051944334&partnerID=8YFLogxK

U2 - 10.5220/0006765404310439

DO - 10.5220/0006765404310439

M3 - Conference contribution

AN - SCOPUS:85051944334

T3 - VEHITS 2018 - Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems

SP - 429

EP - 431

BT - VEHITS 2018 - Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems

A2 - Helfert, Markus

A2 - Gusikhin, Oleg

PB - SciTePress

T2 - 4th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2018

Y2 - 16 March 2018 through 18 March 2018

ER -