DeepCollision: Learning Configurations of Operating Environment of Autonomous Vehicles to Maximize their Collisions

With the aim to test autonomous driving systems, we propose a novel reinforcement learning (RL)-based approach named <strong>DeepCollision </strong>to learn operating environment configurations of autonomous vehicles, including formalizing environment configuration learning as an MDP and adopting DQN algorithm as the RL solution; <strong>DeepCollision</strong> learns environment configurations to maximize collisions of an Autonomous Vehicle Under Test (AVUT). This dataset contains: <strong>algorithms</strong> - The algorithm of DeepCollision, which includes the network architecture and the DQN hyperparameter settings; <strong>pilot-study</strong> - All the raw data and plots for the pilot study; <strong>formal-experiment</strong> - A dataset contains all the raw data for analysis and the scenarios with detailed demand values; <strong>rest-api</strong> - The REST API endpoints for environment configuration and one <strong>example </strong>to show the usage of the APIs.