# Imitation Learning for Autonomous Driving in CARLA

arXiv: https://arxiv.org/abs/2609.17757 · HTML: https://mlsanity.com/paper/2609.17757/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving.
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Placed in

- End-to-end autonomous driving / [Imitation-learning end-to-end planners](https://mlsanity.com/driving/imitation-learning-end-to-end-planners/)
- Offline RL and imitation learning from data / [Imitation and offline RL for driving](https://mlsanity.com/offlinerl/imitation-and-offline-rl-for-driving/)

## Builds on (most cited first, 6 of 6)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [End-to-end Driving via Conditional Imitation Learning](https://mlsanity.com/paper/1710.02410/) (2017)
- [Learning by Cheating](https://mlsanity.com/paper/1912.12294/) (2019)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)

## Abstract (arXiv)

Behavioral cloning trains a policy offline on expert demonstrations, but deployment is closed loop: each action affects the observations the policy receives next. We study how much closed-loop driving competence a compact multimodal policy can acquire from offline demonstrations in the CARLA simulator. The policy uses five-frame histories of RGB images, LiDAR, vehicle telemetry, and lane waypoints to predict throttle, brake, and steering at 20 Hz. Demonstrations were collected in three stages, ending with a systematic route-generation procedure that enumerates spawn points and feasible maneuvers and verifies completed autopilot routes. The released 1.36 million parameter policy was trained on 236,882 windows, representing about 3.3 hours of driving from 448 captures. The resulting policy drives autonomously for hours on training and held-out routes. In our runs, it did so without collisions and also transferred qualitatively to an unseen CARLA town with different road geometry. We also observed recovery from large trajectory deviations, although we do not claim systematic recovery without controlled evaluation. We report offline metrics and distinguish measured results from qualitative closed-loop observations. We release the code, trained checkpoint, ONNX model, data sample, and an evidence audit for the reported claims.