Iterative Imitation Policy Improvement for Interactive Autonomous Driving
On the map: End-to-end autonomous driving → Imitation-learning end-to-end planners
Abstract (arXiv)
We propose an imitation learning system for autonomous driving in urban traffic with interactions. We train a Behavioral Cloning~(BC) policy to imitate driving behavior collected from the real urban traffic, and apply the data aggregation algorithm to improve its performance iteratively. Applying data aggregation in this setting comes with two challenges. The first challenge is that it is expensive and dangerous to collect online rollout data in the real urban traffic. Creating similar traffic scenarios in simulator like CARLA for online rollout collection can also be difficult. Instead, we propose to create a weak simulator from the training dataset, in which all the surrounding vehicles follow the data trajectory provided by the dataset. We find that the collected online data in such a simulator can still be used to improve BC policy's performance. The second challenge is the tedious and time-consuming process of human labelling process during online rollout. To solve this problem, we use an A^* planner as a pseudo-expert to provide expert-like demonstration. We validate our proposed imitation learning system in the real urban traffic scenarios. The experimental results show that our system can significantly improve the performance of baseline BC policy.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving. Builds on 16 of its 29 references that are in the map. First posted on arXiv 3 Sep 2021.
Builds on
16 of 29 references.
References · 16
- 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
- 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
- 2016Generative Adversarial Imitation Learningcited by 1,576
- 2016End to End Learning for Self-Driving Carscited by 1,000
- 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
- 2017End-to-end Driving via Conditional Imitation Learningcited by 479
- 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 417
- 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 391
- 2019INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Mapscited by 231
- 2015DeepDriving: Learning Affordance for Direct Perception in Autonomous Drivingcited by 229
- 2020Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Netcited by 228
- 2017Deep Reinforcement Learning framework for Autonomous Drivingcited by 224
4 more
- 2017DART: Noise Injection for Robust Imitation Learningcited by 187
- 2021IntentNet: Learning to Predict Intention from Raw Sensor Datacited by 158
- 2016Query-Efficient Imitation Learning for End-to-End Autonomous Drivingcited by 83
- 2018Generative Modeling of Multimodal Multi-Human Behaviorcited by 24
Built on by
Citing papers per year: 2023: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2022Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios
- 2022Exploring the trade off between human driving imitation and safety for traffic simulation
- 2025Learning to Drive by Imitating Surrounding Vehicles
- 2021Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients
- 2023Learning Realistic Traffic Agents in Closed-loop
- 2021Improved Deep Reinforcement Learning with Expert Demonstrations for Urban Autonomous Driving
- 2019Exploring the Limitations of Behavior Cloning for Autonomous Driving
- 2023Human-Like Autonomous Driving on Dense Traffic