# Autonomous Vehicle Collision Avoidance With Racing Parameterized Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2604.16702 · HTML: https://mlsanity.com/paper/2604.16702/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 13 of its 29 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## 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, 13 of 13)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Control Barrier Function Based Quadratic Programs for Safety Critical Systems](https://mlsanity.com/paper/1609.06408/) (2016)
- [Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving](https://mlsanity.com/paper/1907.06826/) (2019)
- [Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey](https://mlsanity.com/paper/2112.08936/) (2021)
- [Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning](https://mlsanity.com/paper/1910.11689/) (2019)
- [Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing](https://mlsanity.com/paper/2103.04909/) (2021)
- [RACE: Reinforced Cooperative Autonomous Vehicle Collision AvoidancE](https://mlsanity.com/paper/2004.01286/) (2020)
- [XTENTH-CAR: A Proportionally Scaled Experimental Vehicle Platform for Connected Autonomy and All-Terrain Research](https://mlsanity.com/paper/2212.01691/) (2022)
- [Emergency Collision Avoidance and Mitigation Using Model Predictive Control and Artificial Potential Function](https://mlsanity.com/paper/2211.06574/) (2022)
- [Collision Avoidance Testing of the Waymo Automated Driving System](https://mlsanity.com/paper/2212.08148/) (2022)
- [AutoVRL: A High Fidelity Autonomous Ground Vehicle Simulator for Sim-to-Real Deep Reinforcement Learning](https://mlsanity.com/paper/2304.11496/) (2023)
- [Security and Privacy Issues for Connected Vehicles](https://mlsanity.com/paper/1812.04967/) (2018)
- [Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing](https://mlsanity.com/paper/2604.09499/) (2026)

## Abstract (arXiv)

Road traffic accidents are a leading cause of fatalities worldwide. In the US, human error causes 94% of crashes, resulting in excess of 7,000 pedestrian fatalities and 500 billion in costs annually. Autonomous Vehicles (AVs) with emergency collision avoidance systems that operate at the limits of vehicle dynamics at a high frequency, a dual constraint of nonlinear kinodynamic accuracy and computational efficiency, further enhance safety benefits during adverse weather and cybersecurity breaches, and to evade dangerous human driving when AVs and human drivers share roads. This paper parameterizes a Deep Reinforcement Learning (DRL) collision avoidance policy Out-Of-Distribution (OOD) utilizing race car overtaking, without explicit geometric mimicry reference trajectory guidance, in simulation, with a physics-informed, simulator exploit-aware reward to encode nonlinear vehicle kinodynamics. Two policies are evaluated, a default uni-direction and a reversed heading variant that navigates in the opposite direction to other cars, which both consistently outperform a Model Predictive Control and Artificial Potential Function (MPC-APF) baseline, with zero-shot transfer to proportionally scaled hardware, across three intersection collision scenarios, at 31x fewer Floating Point Operations (FLOPS) and 64x lower inference latency. The reversed heading policy outperforms the default racing overtaking policy in head-to-head collisions by 30% and the baseline by 50%, and matches the former in side collisions, where both DRL policies evade 10% greater than numerical optimal control.