# Learning from Demonstrations of Critical Driving Behaviours Using Driver's Risk Field

arXiv: https://arxiv.org/abs/2210.01747 · HTML: https://mlsanity.com/paper/2210.01747/

## Key facts

- Cited by 4 papers in the map (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 12 of its 29 references that are in the map.
- First posted on arXiv 4 Oct 2022.

## 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, 12 of 12)

- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst](https://mlsanity.com/paper/1812.03079/) (2018)
- [Causal Confusion in Imitation Learning](https://mlsanity.com/paper/1905.11979/) (2019)
- [TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors](https://mlsanity.com/paper/2101.06557/) (2021)
- [Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients](https://mlsanity.com/paper/2109.13333/) (2021)
- [Urban Driving with Conditional Imitation Learning](https://mlsanity.com/paper/1912.00177/) (2019)
- [SceneGen: Learning to Generate Realistic Traffic Scenes](https://mlsanity.com/paper/2101.06541/) (2021)
- [SimNet: Learning Reactive Self-driving Simulations from Real-world Observations](https://mlsanity.com/paper/2105.12332/) (2021)
- [SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policies](https://mlsanity.com/paper/2109.13602/) (2021)
- [Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation](https://mlsanity.com/paper/2205.03195/) (2022)
- [Autonomy 2.0: Why is self-driving always 5 years away?](https://mlsanity.com/paper/2107.08142/) (2021)
- [Safe Imitation Learning on Real-Life Highway Data for Human-like Autonomous Driving](https://mlsanity.com/paper/2110.04052/) (2021)

## Built on by (most cited first, 4 of 4)

- [Navigating the Edge with the State-of-the-Art Insights into Corner Case Identification and Generation for Enhanced Autonomous Vehicle Safety](https://mlsanity.com/paper/2503.00077/) (2025)
- [S4TP: Social-Suitable and Safety-Sensitive Trajectory Planning for Autonomous Vehicles](https://mlsanity.com/paper/2404.11946/) (2024)
- [CORTEX-AVD: A Framework for CORner Case Testing and EXploration in Autonomous Vehicle Development](https://mlsanity.com/paper/2504.03989/) (2025)
- [Constructing the Umwelt: Cognitive Planning through Belief-Intent Co-Evolution](https://mlsanity.com/paper/2511.05540/) (2025)

## Abstract (arXiv)

In recent years, imitation learning (IL) has been widely used in industry as the core of autonomous vehicle (AV) planning modules. However, previous IL works show sample inefficiency and low generalisation in safety-critical scenarios, on which they are rarely tested. As a result, IL planners can reach a performance plateau where adding more training data ceases to improve the learnt policy. First, our work presents an IL model using the spline coefficient parameterisation and offline expert queries to enhance safety and training efficiency. Then, we expose the weakness of the learnt IL policy by synthetically generating critical scenarios through optimisation of parameters of the driver's risk field (DRF), a parametric human driving behaviour model implemented in a multi-agent traffic simulator based on the Lyft Prediction Dataset. To continuously improve the learnt policy, we retrain the IL model with augmented data. Thanks to the expressivity and interpretability of the DRF, the desired driving behaviours can be encoded and aggregated to the original training data. Our work constitutes a full development cycle that can efficiently and continuously improve the learnt IL policies in closed-loop. Finally, we show that our IL planner developed with less training resource still has superior performance compared to the previous state-of-the-art.