This repo collects interesting papers related to Autonomous Vehicle Planning. It is worth noting that these papers are broadly related to the topic in my point of view: papers not directly study about vehicle motion planning (e.g. pure RL, IL) may also be collected in the list. You can also refer to more details of these papers in Notes.md, which records my summarization for the papers. Welcome pull requests for interesting papers!
| Subcategory | Paper | Conference | Links |
|---|---|---|---|
| RL Related | Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning | arXiv'22 | Paper |
| Driving by Dreaming: Offline Model-Based Reinforcement Learning for Autonomous Vehicles | Master's Thesis'22 | Paper | |
| Rethinking Closed-loop Training for Autonomous Driving | ECCV'22 | Paper | |
| Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning | ICML'22 | Paper | Code | |
| UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning | NeurIPS'21 Workshop (Best paper) | Paper | |
| Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement | NeurIPS'21 Workshop | Paper | |
| Motion Planning for Autonomous Vehicles in the Presence of Uncertainty Using Reinforcement Learning | IROS'21 | Paper | |
| Marrying Motion Forecasting and Offline Model-Based Reinforcement Learning for Self-Driving Cars | Github'20 | Paper | |
| Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning | arXiv'20 | Paper | Code | |
| Model-free Deep Reinforcement Learning for Urban Autonomous Driving | arXiv'19 | Paper | Code | |
| Learning to Drive in a Day | arXiv'18 | Paper | |
| IL Related | Guided Conditional Diffsuion for Controllable Traffic Simulation | arXiv'22 | Paper |
| Model-Based Imitation Learning for Urban Driving | NeurIPS'22 | Paper | Code | |
| Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving | arXiv'22 | Paper | |
| ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning | ECCV'22 | Paper | Code | |
| PlanT: Explainable Planning Transformers via Object-Level Representations | CoRL'22 | Paper | Code | |
| End-to-End Urban Driving by Imitating a Reinforcement Learning Coach | CVPR'21 | Paper | Code | |
| Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations | ECCV'20 | Paper | |
| DSDNet: Deep Structured self-Driving Network | ECCV'20 | Paper | |
| Jointly Learnable Behavior and Trajectory Planning for Self-Driving Vehicles | IROS'19 | Paper | |
| End-to-end Interpretable Neural Motion Planner | CVPR'19 (Oral) | Paper | |
| ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst | RSS'19 | Paper | |
| End-to-end Driving via Conditional Imitation Learning | ICRA'18 | Paper | |
| Tree Search Related | LEADER: Learning Attention over Driving Behaviors for Planning under Uncertainty | CoRL'22 (Oral) | Paper |
| Closing the Planning-Learning Loop with Application to Autonomous Driving | T-RP'22 | Paper | Code | |
| KB-Tree: Learnable and Continuous Monte-Carlo Tree Search for Autonomous Driving Planning | IROS'21 | Paper | |
| Driving Maneuvers Prediction Based Autonomous Driving Control by Deep Monte Carlo Tree | T-VT'20 | Paper | Code | |
| Interaction Modeling | M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction | CVPR'22 | Paper | Code |
| InterSim: Interactive Traffic Simulation via Explicit Relation Modeling | IROS'22 | Paper | Code | |
| Optimization Related | Comprehensive Reactive Safety: No Need for a Trajectory if You Have a Strategy | IROS'22 | Paper |
| Autonomous Driving Motion Planning With Constrained Iterative LQR | T-IT'19 | Paper | |
| Tunable and Stable Real-Time Trajectory Planning for Urban Autonomous Driving | IROS'15 | Paper | |
| Traditional Planning Algorithms | Path Planning using Neural A* Search | ICML'21 | Paper | Code |
| Sampling-based Algorithms for Optimal Motion Planning | IJRR'10 | Paper | |
| Practical Search Techniques in Path Planning for Autonomous Driving | AAAI'08 | Paper |
| Subcategory | Paper | Conference | Link |
|---|---|---|---|
| Model-based RL | Mismatched No More: Joint Model-Policy Optimization for Model-Based RL | NeurIPS'22 | Paper |
| Planning with Diffusion for Flexible Behavior Synthesis | ICML'22 | Paper | |
| Offline RL | Hierarchical Decision Transformer | arXiv'22 | Paper |
| The In-Sample Softmax for Offline Reinforcement Learning | ICLR'23 (submitted) | Paper | |
| Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning | arXiv'22 | Paper | |
| Know Your Boundaries: The Necessity of Explicit Behavioral Cloning in Offline RL | arXiv'22 | Paper | |
| Mildly Conservative Q-Learning for Offline Reinforcement Learning | NeurIPS'22 | Paper | Code | |
| Bootstrapped Transformer for Offline Reinforcement Learning | NeurIPS'22 | Paper | Code | |
| A Unified Framework for Alternating Offline Model Training and Policy Learning | NeurIPS'22 | Paper |Code | |
| A Policy-Guided Imitation Approach for Offline Reinforcement Learning | NeurIPS'22 | Paper | Code | |
| MOReL: Model-Based Offline Reinforcement Learning | arXiv'21 | Paper | Code | |
| Offline Reinforcement Learning with Implicit Q-Learning | arXiv'21 | Paper | Code | |
| Offline Reinforcement Learning from Images with Latent Space Models | PRML'21 | Paper | Code | |
| Online and Offline Reinforcement Learning by Planning with a Learned Model | NeurIPS'21 (Spotlight) | Paper | |
| Offline Reinforcement Learning as One Big Sequence Modeling Problem | NeurIPS'21 | Paper | Code | |
| Decision Transformer: Reinforcement Learning via Sequence Modeling | NeurIPS'21 | Paper | Code | |
| Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble | NeurIPS'21 | Paper | Code | |
| Conservative Q-Learning for Offline Reinforcement Learning | NeurIPS'20 | Paper | Code | |
| Model-Based Offline Planning | ICLR'21 | Paper | |
| Off-Policy Deep Reinforcement Learning without Exploration | ICML'19 | Paper | Code |
| Paper | Conference | Link |
|---|---|---|
| Planning for Sample Efficient Imitation Learning | NeurIPS'22 | Paper | Code |
| Generative Adversarial Imitation Learning | arXiv'16 | Paper |