Affordance-based Reinforcement Learning for Urban Driving

Abstract

Traditional autonomous vehicle pipelines that follow a modular approach have been very successful in the past both in academia and industry, which has led to autonomy deployed on road. Though this approach provides ease of interpretation, its generalizability to unseen environments is limited and hand-engineering of numerous parameters is required, especially in the prediction and planning systems. Recently, deep reinforcement learning has been shown to learn complex strategic games and perform challenging robotic tasks, which provides an appealing framework for learning to drive. In this work, we propose a deep reinforcement learning framework to learn optimal control policy using waypoints and low-dimensional visual representations, also known as affordances. We demonstrate that our agents when trained from scratch learn the tasks of lane-following, driving around inter-sections as well as stopping in front of other actors or traffic lights even in the dense traffic setting. We note that our method achieves comparable or better performance than the baseline methods on the original and NoCrash benchmarks on the CARLA simulator.

References in corpus (18)

• Continuous control with deep reinforcement learning
• Playing Atari with Deep Reinforcement Learning
• End to End Learning for Self-Driving Cars
• A Survey of Autonomous Driving: Common Practices and Emerging Technologies
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Deep Learning-based Vehicle Behaviour Prediction For Autonomous Driving Applications: A Review
• Solving Rubik's Cube with a Robot Hand
• Distributed Prioritized Experience Replay
• Rainbow: Combining Improvements in Deep Reinforcement Learning
• Implicit Quantile Networks for Distributional Reinforcement Learning
• Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car
• Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control
• Query-Efficient Imitation Learning for End-to-End Autonomous Driving
• Deep Steering: Learning End-to-End Driving Model from Spatial and Temporal Visual Cues
• Deep Imitative Models for Flexible Inference, Planning, and Control
• End-to-end Multi-Modal Multi-Task Vehicle Control for Self-Driving Cars with Visual Perception
• Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving
• Latent Space Reinforcement Learning for Steering Angle Prediction