Behaviorally Diverse Traffic Simulation via Reinforcement Learning

11/11/2020

∙

Traffic simulators are important tools in autonomous driving development. While continuous progress has been made to provide developers more options for modeling various traffic participants, tuning these models to increase their behavioral diversity while maintaining quality is often very challenging. This paper introduces an easily-tunable policy generation algorithm for autonomous driving agents. The proposed algorithm balances diversity and driving skills by leveraging the representation and exploration abilities of deep reinforcement learning via a distinct policy set selector. Moreover, we present an algorithm utilizing intrinsic rewards to widen behavioral differences in the training. To provide quantitative assessments, we develop two trajectory-based evaluation metrics which measure the differences among policies and behavioral coverage. We experimentally show the effectiveness of our methods on several challenging intersection scenes.

READ FULL TEXT

Behaviorally Diverse Traffic Simulation via Reinforcement Learning

CARLA Real Traffic Scenarios – novel training ground and benchmark for autonomous driving

Efficient Learning of Urban Driving Policies Using Bird's-Eye-View State Representations

A Reinforcement Learning Benchmark for Autonomous Driving in Intersection Scenarios

Exploring the trade off between human driving imitation and safety for traffic simulation

Spatially and Seamlessly Hierarchical Reinforcement Learning for State Space and Policy space in Autonomous Driving

Improve Generalization of Driving Policy at Signalized Intersections with Adversarial Learning

Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction

Behaviorally Diverse Traffic Simulation via Reinforcement Learning

Related Research

CARLA Real Traffic Scenarios – novel training ground and benchmark for autonomous driving

Efficient Learning of Urban Driving Policies Using Bird's-Eye-View State Representations

A Reinforcement Learning Benchmark for Autonomous Driving in Intersection Scenarios

Exploring the trade off between human driving imitation and safety for traffic simulation

Spatially and Seamlessly Hierarchical Reinforcement Learning for State Space and Policy space in Autonomous Driving

Improve Generalization of Driving Policy at Signalized Intersections with Adversarial Learning

Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction