# Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving

arXiv: https://arxiv.org/abs/2508.14926 · HTML: https://mlsanity.com/paper/2508.14926/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 15 of its 45 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Placed in

- End-to-end autonomous driving / [Reinforcement learning for driving](https://mlsanity.com/driving/reinforcement-learning-for-driving/)
- Deep reinforcement learning methods / [RL for autonomous driving and traffic](https://mlsanity.com/deeprl/rl-for-autonomous-driving-and-traffic/)

## Builds on (most cited first, 15 of 15)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [A Distributional Perspective on Reinforcement Learning](https://mlsanity.com/paper/1707.06887/) (2017)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [Risk-Constrained Reinforcement Learning with Percentile Risk Criteria](https://mlsanity.com/paper/1512.01629/) (2015)
- [MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning](https://mlsanity.com/paper/2109.12674/) (2021)
- [Policy Gradient for Coherent Risk Measures](https://mlsanity.com/paper/1502.03919/) (2015)
- [Algorithms for Fairness in Sequential Decision Making](https://mlsanity.com/paper/1901.08568/) (2019)
- [The social dilemma of autonomous vehicles](https://mlsanity.com/paper/1510.03346/) (2015)
- [An Ethical Trajectory Planning Algorithm for Autonomous Vehicles](https://mlsanity.com/paper/2212.08577/) (2022)
- [Modified DDPG car-following model with a real-world human driving experience with CARLA simulator](https://mlsanity.com/paper/2112.14602/) (2021)
- [Autonomous Driving Small-Scale Cars: A Survey of Recent Development](https://mlsanity.com/paper/2404.06229/) (2024)

## Built on by (most cited first, 1 of 1)

- [MTA-RL: Robust Urban Driving via Multi-modal Transformer-based 3D Affordances and Reinforcement Learning](https://mlsanity.com/paper/2605.10177/) (2026)

## Abstract (arXiv)

Autonomous vehicles hold great promise for reducing traffic fatalities and improving transportation efficiency, yet their widespread adoption hinges on embedding credible and transparent ethical reasoning into routine and emergency maneuvers, particularly to protect vulnerable road users (VRUs) such as pedestrians and cyclists. Here, we present a hierarchical Safe Reinforcement Learning (Safe RL) framework that augments standard driving objectives with ethics-aware cost signals. At the decision level, a Safe RL agent is trained using a composite ethical risk cost, combining collision probability and harm severity, to generate high-level motion targets. A dynamic, risk-sensitive Prioritized Experience Replay mechanism amplifies learning from rare but critical, high-risk events. At the execution level, polynomial path planning coupled with Proportional-Integral-Derivative (PID) and Stanley controllers translates these targets into smooth, feasible trajectories, ensuring both accuracy and comfort. We train and validate our approach on closed-loop simulation environments derived from large-scale, real-world traffic datasets encompassing diverse vehicles, cyclists, and pedestrians, and demonstrate that it outperforms baseline methods in reducing risk to others while maintaining ego performance and comfort. This work provides a reproducible benchmark for Safe RL with explicitly ethics-aware objectives in human-mixed traffic scenarios. Our results highlight the potential of combining formal control theory and data-driven learning to advance ethically accountable autonomy that explicitly protects those most at risk in urban traffic environments. Across two interactive benchmarks and five random seeds, our policy decreases conflict frequency by 25-45% compared to matched task successes while maintaining comfort metrics within 5%.