Deep Reinforcement Learning for Autonomous Driving

Abstract

Reinforcement learning has steadily improved and outperform human in lots of traditional games since the resurgence of deep neural network. However, these success is not easy to be copied to autonomous driving because the state spaces in real world are extreme complex and action spaces are continuous and fine control is required. Moreover, the autonomous driving vehicles must also keep functional safety under the complex environments. To deal with these challenges, we first adopt the deep deterministic policy gradient (DDPG) algorithm, which has the capacity to handle complex state and action spaces in continuous domain. We then choose The Open Racing Car Simulator (TORCS) as our environment to avoid physical damage. Meanwhile, we select a set of appropriate sensor information from TORCS and design our own rewarder. In order to fit DDPG algorithm to TORCS, we design our network architecture for both actor and critic inside DDPG paradigm. To demonstrate the effectiveness of our model, We evaluate on different modes in TORCS and show both quantitative and qualitative results.

arXiv commentno time for further improvement

References in corpus (6)

• Continuous control with deep reinforcement learning
• Playing Atari with Deep Reinforcement Learning
• An Empirical Evaluation of Deep Learning on Highway Driving
• Virtual to Real Reinforcement Learning for Autonomous Driving
• Learning to Drive using Inverse Reinforcement Learning and Deep Q-Networks
• Learning from Maps: Visual Common Sense for Autonomous Driving

Cited by in corpus (23)

• Constrained Policy Optimization
• Verification for Machine Learning, Autonomy, and Neural Networks Survey
• AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metrics
• 3D Multi-Object Tracking: A Baseline and New Evaluation Metrics
• Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety
• Deep Reinforcement Learning and Transportation Research: A Comprehensive Review
• PTP: Parallelized Tracking and Prediction with Graph Neural Networks and Diversity Sampling
• GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning
• Implicit Multiagent Coordination at Unsignalized Intersections via Multimodal Inference Enabled by Topological Braids
• The PlayStation Reinforcement Learning Environment (PSXLE)
• Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimization
• Learning hierarchical behavior and motion planning for autonomous driving
• Graph Neural Networks for 3D Multi-Object Tracking
• Game Theory and Machine Learning in UAVs-Assisted Wireless Communication Networks: A Survey
• When We First Met: Visual-Inertial Person Localization for Co-Robot Rendezvous
• Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction
• Objective-aware Traffic Simulation via Inverse Reinforcement Learning
• Integrating Imitation Learning with Human Driving Data into Reinforcement Learning to Improve Training Efficiency for Autonomous Driving
• Controlling an Inverted Pendulum with Policy Gradient Methods-A Tutorial
• AutoSelect: Automatic and Dynamic Detection Selection for 3D Multi-Object Tracking
• GroundNet: Monocular Ground Plane Normal Estimation with Geometric Consistency
• Learning Negotiating Behavior Between Cars in Intersections using Deep Q-Learning
• Risk Analysis and Policy Enforcement of Function Interactions in Robot Apps