Behavior Metrics is an open-sourced autonomous driving network comparison tool that allows the user to load and test their autonomous driving models in different scenarios and compare the performance metrics against other models. Previously, Behavior Metrics only supported the follow-the-line task, where the vehicle must drive along a circuit while maintaining proximity to the center of the lane, and provided multiple trained models for benchmarking. This project aims to expand the current stack by adding support for an route-following task in CARLA simulator, where the agent needs to follow a sequence of high-level turning instructions to reach a target while avoiding obstacles, and providing an end-to-end learning solution for the task.
Codebase: github.com/TheRoboticsClub/gs...
Behavior Metrics Website: jderobot.github.io/BehaviorMe...
Behavior Metrics Github: github.com/JdeRobot/BehaviorM...
8 окт 2023