Deep Reinforcement Learning framework for Autonomous Driving

Abstract

Reinforcement learning is considered to be a strong AI paradigm which can be used to teach machines through interaction with the environment and learning from their mistakes. Despite its perceived utility, it has not yet been successfully applied in automotive applications. Motivated by the successful demonstrations of learning of Atari games and Go by Google DeepMind, we propose a framework for autonomous driving using deep reinforcement learning. This is of particular relevance as it is difficult to pose autonomous driving as a supervised learning problem due to strong interactions with the environment including other vehicles, pedestrians and roadworks. As it is a relatively new area of research for autonomous driving, we provide a short overview of deep reinforcement learning and then describe our proposed framework. It incorporates Recurrent Neural Networks for information integration, enabling the car to handle partially observable scenarios. It also integrates the recent work on attention models to focus on relevant information, thereby reducing the computational complexity for deployment on embedded hardware. The framework was tested in an open source 3D car racing simulator called TORCS. Our simulation results demonstrate learning of autonomous maneuvering in a scenario of complex road curvatures and simple interaction of other vehicles.

Reprinted with permission of IS&T: The Society for Imaging Science and Technology, sole copyright owners of Electronic Imaging, Autonomous Vehicles and Machines 2017

Cited by in corpus (44)

• A Survey of Autonomous Driving: Common Practices and Emerging Technologies
• A Survey of Deep Learning Techniques for Autonomous Driving
• Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges
• A Survey of End-to-End Driving: Architectures and Training Methods
• Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and The Way Forward
• Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning
• Hybrid Reinforcement Learning-Based Eco-Driving Strategy for Connected and Automated Vehicles at Signalized Intersections
• Black-Box Testing of Deep Neural Networks Through Test Case Diversity
• Controlling an Autonomous Vehicle with Deep Reinforcement Learning
• Interaction-aware Decision-making for Automated Vehicles using Social Value Orientation
• Feature engineering and symbolic regression methods for detecting hidden physics from sparse sensors
• Weak Form Theory-guided Neural Network (TgNN-wf) for Deep Learning of Subsurface Single and Two-phase Flow
• Stop-and-Go: Exploring Backdoor Attacks on Deep Reinforcement Learning-based Traffic Congestion Control Systems
• Adaptive Behavior Generation for Autonomous Driving using Deep Reinforcement Learning with Compact Semantic States
• Hierarchical Program-Triggered Reinforcement Learning Agents For Automated Driving
• Quantum Machine Learning for Finance
• Gym-ANM: Reinforcement Learning Environments for Active Network Management Tasks in Electricity Distribution Systems
• Optimization of Pressure Management Strategies for Geological CO2 Sequestration Using Surrogate Model-based Reinforcement Learning
• Energy-based error bound of physics-informed neural network solutions in elasticity
• Safeguarding connected autonomous vehicle communication: Protocols, intra- and inter-vehicular attacks and defenses
• Redirection Controller Using Reinforcement Learning
• COMET: Coverage-guided Model Generation For Deep Learning Library Testing
• Geo-Context Aware Study of Vision-Based Autonomous Driving Models and Spatial Video Data
• An Exploratory Study on the Introduction and Removal of Different Types of Technical Debt
• ARtonomous: Introducing Middle School Students to Reinforcement Learning Through Virtual Robotics
• Robust Reinforcement Learning-based Autonomous Driving Agent for Simulation and Real World
• Uncovering Interpretable Internal States of Merging Tasks at Highway On-Ramps for Autonomous Driving Decision-Making
• VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability
• GIN: Graph-based Interaction-aware Constraint Policy Optimization for Autonomous Driving
• Reliable Off-policy Evaluation for Reinforcement Learning
• Towards Safer Self-Driving Through Great PAIN (Physically Adversarial Intelligent Networks)
• Gym-ANM: Open-source software to leverage reinforcement learning for power system management in research and education
• Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking
• Deep Reinforcement Learning for Multi-Agent Coordination
• Optimal Feature Manipulation Attacks Against Linear Regression
• Learning to Race through Coordinate Descent Bayesian Optimisation
• Autonomous vehicle decision and control through reinforcement learning with traffic flow randomization
• T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler
• A Comparative Tutorial of Bayesian Sequential Design and Reinforcement Learning
• Multi-task Reinforcement Learning in Reproducing Kernel Hilbert Spaces via Cross-learning
• Group-Agent Reinforcement Learning
• Development of A Stochastic Traffic Environment with Generative Time-Series Models for Improving Generalization Capabilities of Autonomous Driving Agents
• Tactical Decision Making for Autonomous Trucks by Deep Reinforcement Learning with Total Cost of Operation Based Reward
• Investigation of Factorized Optical Flows as Mid-Level Representations