2020 · 22 citations · 31 references
ComputingAutonomous SystemsComputer ScienceAutonomous VehiclesComputer VisionMachine LearningPolicy LearningReinforcement LearningSim-to-real TransferSimulation-based LearningVehicle ControlVehicle PerceptionReal-world Performance EvaluationReinforcement Learning For VisionReinforcement Learning Transfer
We use reinforcement learning in simulation to obtain a driving system controlling a full-size real-world vehicle. The driving policy takes RGB images from a single camera and their semantic segmentation as input. We use mostly synthetic data, with labelled real-world data appearing only in the training of the segmentation network.Using reinforcement learning in simulation and synthetic data is motivated by lowering costs and engineering effort.In real-world experiments we confirm that we achieved successful sim-to-real policy transfer. Based on the extensive evaluation, we analyze how design decisions about perception, control, and training impact the real-world performance.
31
MuJoCo: A physics engine for model-based control
Emanuel Todorov, Tom Erez, Yuval Tassa · 2012 · 4.4K citations
Engineering, Mechanical Engineering, Robotics Engineering +17
The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
Gerhard Neuhold, Tobias Ollmann, Samuel Rota Bulò et al. · 2017 · 1.4K citations