Learning Negotiating Behavior Between Cars in Intersections using Deep\n Q-Learning

2018/10/24 by Tommy Tram, Tram, Tommy, Anton Jansson +8 · 1 citation
Computer Science · Engineering · #Adversarial Robustness in Machine Learning #Autonomous Vehicle Technology and Safety #Computer Science and Game Theory (cs.GT) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Traffic Prediction and Management Techniques #Traffic control and management

paper · pdf · doi:10.48550/arxiv.1810.10469

openalex publication_date 2018/10/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper concerns automated vehicles negotiating with other vehicles,\ntypically human driven, in crossings with the goal to find a decision algorithm\nby learning typical behaviors of other vehicles. The vehicle observes distance\nand speed of vehicles on the intersecting road and use a policy that adapts its\nspeed along its pre-defined trajectory to pass the crossing efficiently. Deep\nQ-learning is used on simulated traffic with different predefined driver\nbehaviors and intentions. The results show a policy that is able to cross the\nintersection avoiding collision with other vehicles 98% of the time, while at\nthe same time not being too passive. Moreover, inferring information over time\nis important to distinguish between different intentions and is shown by\ncomparing the collision rate between a Deep Recurrent Q-Network at 0.85% and a\nDeep Q-learning at 1.75%.\n

Citations

• Improving neural networks by preventing co-adaptation of feature detectors
• A Markovian Decision Process
• End to End Learning for Self-Driving Cars
• Deep Reinforcement Learning for Autonomous Driving

Cited by

• Goal-conditioned Hierarchical Reinforcement Learning for Sample-efficient and Safe Autonomous Driving at Intersections

Related

• Mix Q-learning for Lane Changing: A Collaborative Decision-Making Method in Multi-Agent Deep Reinforcement Learning
• Dueling Deep Q Network for Highway Decision Making in Autonomous Vehicles: A Case Study
• Learning When to Drive in Intersections by Combining Reinforcement\n Learning and Model Predictive Control
• Exploring the impact of traffic signal control and connected and automated vehicles on intersections safety: A deep reinforcement learning approach
• Pedestrian Collision Avoidance for Autonomous Vehicles at Unsignalized Intersection Using Deep Q-Network