Deep Reinforcement Learning for Autonomous Driving: A Survey
2020/02/02 by B Ravi Kiran, Kiran, B Ravi, Ibrahim Sobh +11 · 2 voices · 136 citations
Computer Science · #cs.AI #cs.LG #cs.RO
paper · pdf · doi:10.48550/arxiv.2002.00444
Accepted for publication at IEEE Transactions on Intelligent Transportation Systems
arxiv created 2021/01/23 · arxiv updated 2021/01/26
Abstract
With the development of deep representation learning, the domain of reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in high dimensional environments. This review summarises deep reinforcement learning (DRL) algorithms and provides a taxonomy of automated driving tasks where (D)RL methods have been employed, while addressing key computational challenges in real world deployment of autonomous driving agents. It also delineates adjacent domains such as behavior cloning, imitation learning, inverse reinforcement learning that are related but are not classical RL algorithms. The role of simulators in training agents, methods to validate, test and robustify existing solutions in RL are discussed.
Cited by
- Spatiotemporal Feature Alignment and Weighted Fusion in Collaborative Perception Enabled by Network Synchronization and Age of Information
- Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations
- Learning Safe Autonomous Driving Policies Using Predictive Safety Representations
- Online Robust Reinforcement Learning with General Function Approximation
- Learning to Plan, Planning to Learn: Adaptive Hierarchical RL-MPC for Sample-Efficient Decision Making
- Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future
- Tiny, On-Device Decision Makers with the MiniConv Library
- High Order Control Lyapunov Function - Control Barrier Function - Quadratic Programming Based Autonomous Driving Controller for Bicyclist Safety
- Goal Reaching with Eikonal-Constrained Hierarchical Quasimetric Reinforcement Learning
- A Review of Learning-Based Motion Planning: Toward a Data-Driven Optimal Control Approach
- How to Brake? Ethical Emergency Braking with Deep Reinforcement Learning
- Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning
- Entropy-Controlled Intrinsic Motivation Reinforcement Learning for Quadruped Robot Locomotion in Complex Terrains
- A Fast Anti-Jamming Cognitive Radar Deployment Algorithm Based on Reinforcement Learning
- Semore: VLM-guided Enhanced Semantic Motion Representations for Visual Reinforcement Learning
- Aligning with Human Values to Enhance Interaction: An eHMI-Mediated Lane-Changing Negotiation Strategy Using Bayesian Inference
- FOVA: Offline Federated Reinforcement Learning with Mixed-Quality Data
- RoaD: Rollouts as Demonstrations for Closed-Loop Supervised Fine-Tuning of Autonomous Driving Policies
- On the Tension Between Optimality and Adversarial Robustness in Policy Optimization
- Fault-Tolerant MARL for CAVs under Observation Perturbations for Highway On-Ramp Merging
- OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability
- Think How Your Teammates Think: Active Inference Can Benefit Decentralized Execution
- Are LLMs The Way Forward? A Case Study on LLM-Guided Reinforcement Learning for Decentralized Autonomous Driving
- Diffusion Policies with Value-Conditional Optimization for Offline Reinforcement Learning
- SafeMIL: Learning Offline Safe Imitation Policy from Non-Preferred Trajectories
- Diffusion Guided Adversarial State Perturbations in Reinforcement Learning
- CoFineLLM: Conformal Finetuning of LLMs for Language-Instructed Robot Planning
- MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios
- Exchange Policy Optimization Algorithm for Semi-Infinite Safe Reinforcement Learning
- Reinforcement learning based data assimilation for unknown state model
- Foundation Models for Trajectory Planning in Autonomous Driving: A Review of Progress and Open Challenges
- Real-DRL: Teach and Learn in Reality
- Learning to Drive Safely with Hybrid Options
- Modeling Electric Vehicle Car-Following Behavior: Classical vs Machine Learning Approach
- Confounding Robust Deep Reinforcement Learning: A Causal Approach
- Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses
- Soft Switching Expert Policies for Controlling Systems with Uncertain Parameters
- OffSim: Offline Simulator for Model-based Offline Inverse Reinforcement Learning
- Towards Robust Zero-Shot Reinforcement Learning
- A Diffusion-Refined Planner with Reinforcement Learning Priors for Confined-Space Parking
- Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling
- Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs
- HyPlan: Hybrid Learning-Assisted Planning Under Uncertainty for Safe Autonomous Driving
- From Learning to Mastery: Achieving Safe and Efficient Real-World Autonomous Driving with Human-In-The-Loop Reinforcement Learning
- Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI
- Rounding-Guided Backdoor Injection in Deep Learning Model Quantization
- Global Convergence of Policy Gradient for Entropy Regularized Linear-Quadratic Control with Multiplicative Noise
- Learning Distinguishable Representations in Deep Q-Networks for Linear Transfer
- SavviDriver: model-based framework for game-based testing of autonomous vehicles in diverse multi-agent traffic scenarios
- Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving
- RDAR: Reward-Driven Agent Relevance Estimation for Autonomous Driving
- SEG-Parking: Towards Safe, Efficient, and Generalizable Autonomous Parking via End-to-End Offline Reinforcement Learning
- TreeIRL: Safe Urban Driving with Tree Search and Inverse Reinforcement Learning
- An Uncertainty-Weighted Decision Transformer for Navigation in Dense, Complex Driving Scenarios
- Deep Learning-based Techniques for Integrated Sensing and Communication Systems: State-of-the-Art, Challenges, and Opportunities
- Deep Reinforcement Learning-Assisted Component Auto-Configuration of Differential Evolution Algorithm for Constrained Optimization: A Foundation Model
- Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning
- Continuous-Time Value Iteration for Multi-Agent Reinforcement Learning
- TrajAware: Graph Cross-Attention and Trajectory-Aware for Generalisable VANETs under Partial Observations
- PolicyEvolve: Evolving Programmatic Policies by LLMs for multi-player games via Population-Based Training
- Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks
- Safe and Efficient Lane-Changing for Autonomous Vehicles: An Improved Double Quintic Polynomial Approach with Time-to-Collision Evaluation
- Learning Game-Playing Agents with Generative Code Optimization
- Search-Based Credit Assignment for Offline Preference-Based Reinforcement Learning
- A Dynamical Systems Framework for Reinforcement Learning Safety and Robustness Verification
- Reinforcement learning entangling operations on spin qubits
- Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving
- One-Step Flow Q-Learning: Addressing the Diffusion Policy Bottleneck in Offline Reinforcement Learning
- Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data
- Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments
- Fusing Rewards and Preferences in Reinforcement Learning
- Reinforcement-Learning-Designed Field-Free Sub-Nanosecond Spin-Orbit-Torque Switching
- How Safe Will I Be Given What I Saw? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy
- MORE-CLEAR: Multimodal Offline Reinforcement learning for Clinical notes Leveraged Enhanced State Representation
- Stackelberg Coupling of Online Representation Learning and Reinforcement Learning
- ME3-BEV: Mamba-Enhanced Deep Reinforcement Learning for End-to-End Autonomous Driving with BEV-Perception
- Hierarchical Deep Deterministic Policy Gradient for Autonomous Maze Navigation of Mobile Robots
- CSRAP: Enhanced Canvas Attention Scheduling for Real-Time Mission Critical Perception
- EvaDrive: Evolutionary Adversarial Policy Optimization for End-to-End Autonomous Driving
- ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning
- Deep Learning Framework Testing via Heuristic Guidance Based on Multiple Model Measurements
- Revisiting Bisimulation Metric for Robust Representations in Reinforcement Learning
- From Novelty to Imitation: Self-Distilled Rewards for Offline Reinforcement Learning
- MOORL: A Framework for Integrating Offline-Online Reinforcement Learning
- Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving
- Time-Aware World Model for Adaptive Prediction and Control
- MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning
- Policy-Based Trajectory Clustering in Offline Reinforcement Learning
- Federated Learning-based MARL for Strengthening Physical-Layer Security in B5G Networks
- Optimizing Cognitive Networks: Reinforcement Learning Meets Energy Harvesting Over Cascaded Channels
- VisioPath: Vision-Language Enhanced Model Predictive Control for Safe Autonomous Navigation in Mixed Traffic
- From General Relation Patterns to Task-Specific Decision-Making in Continual Multi-Agent Coordination
- Assuring the Safety of Reinforcement Learning Components: AMLAS-RL
- Action Space Reduction Strategies for Reinforcement Learning in Autonomous Driving
- 2048: Reinforcement Learning in a Delayed Reward Environment
- WebSynthesis: World-Model-Guided MCTS for Efficient WebUI-Trajectory Synthesis
- Are Learning-Based Approaches Ready for Real-World Indoor Navigation? A Case for Imitation Learning
- Unraveling the Black Box of Neural Networks: A Dynamic Extremum Mapper
- Harnessing the Power of Reinforcement Learning for Adaptive MCMC
- FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning
- Ego-centric Learning of Communicative World Models for Autonomous Driving
- Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation
- BIDA: A Bi-level Interaction Decision-making Algorithm for Autonomous Vehicles in Dynamic Traffic Scenarios
- SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning
- Wasserstein Barycenter Soft Actor-Critic
- Statistical Guarantees for Offline Domain Randomization
- Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving
- Accelerated Learning with Linear Temporal Logic using Differentiable Simulation
- Causal-aware Large Language Models: Enhancing Decision-Making Through Learning, Adapting and Acting
- Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control
- Learning to Search for Vehicle Routing with Multiple Time Windows
- Reinforcement Learning-based Sequential Route Recommendation for System-Optimal Traffic Assignment
- A Framework for Adversarial Analysis of Decision Support Systems Prior to Deployment
- Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects
- Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning
- URB -- Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles
- A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safety
- Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies
- SpineWave: Harnessing Fish Rigid-Flexible Spinal Kinematics for Enhancing Biomimetic Robotic Locomotion
- Learning-based Autonomous Oversteer Control and Collision Avoidance
- Performance Optimization of Energy-Harvesting Underlay Cognitive Radio Networks Using Reinforcement Learning
- Embedded Mean Field Reinforcement Learning for Perimeter-defense Game
- MA-ROESL: Motion-aware Rapid Reward Optimization for Efficient Robot Skill Learning from Single Videos
- Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning
- Automatic Curriculum Learning for Driving Scenarios: Towards Robust and Efficient Reinforcement Learning
- Learning Value of Information towards Joint Communication and Control in 6G V2X
- Towards Human-Centric Autonomous Driving: A Fast-Slow Architecture Integrating Large Language Model Guidance with Reinforcement Learning
- Balancing Progress and Safety: A Novel Risk-Aware Objective for RL in Autonomous Driving
- Multi-agent Embodied AI: Advances and Future Directions
- Modification-Considering Value Learning for Reward Hacking Mitigation in RL
- Scaling Self-Play for End-to-End Driving
- Learning Streaming Video Representation via Multitask Training
- Deep Reinforcement Learning for Optimum Order Execution: Mitigating Risk and Maximizing Returns
- Learning Isometric Embeddings of Road Networks using Multidimensional Scaling
- Human-Level Competitive Pokémon via Scalable Offline Reinforcement Learning with Transformers
- AI Agents and Hard Choices
- Moderate Actor-Critic Methods: Controlling Overestimation Bias via Expectile Loss
Discussions
Related