# Modeling driver's evasive behavior during safety-critical lane changes:Two-dimensional time-to-collision and deep reinforcement learning

arXiv: https://arxiv.org/abs/2209.15133 · HTML: https://mlsanity.com/paper/2209.15133/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 111 references that are in the map.
- First posted on arXiv 29 Sep 2022.

## Builds on (most cited first, 10 of 10)

- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Deep Reinforcement Learning: An Overview](https://mlsanity.com/paper/1701.07274/) (2017)
- [Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey](https://mlsanity.com/paper/2005.00935/) (2020)
- [Safe, Efficient, and Comfortable Velocity Control based on Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/1902.00089/) (2019)
- [Human-Like Autonomous Car-Following Model with Deep Reinforcement Learning](https://mlsanity.com/paper/1901.00569/) (2019)
- [Autonomous Braking System via Deep Reinforcement Learning](https://mlsanity.com/paper/1702.02302/) (2017)
- [Automated vehicle's behavior decision making using deep reinforcement learning and high-fidelity simulation environment](https://mlsanity.com/paper/1804.06264/) (2018)
- [Spatiotemporal Learning of Multivehicle Interaction Patterns in Lane-Change Scenarios](https://mlsanity.com/paper/2003.00759/) (2020)
- [TrafficNet: An Open Naturalistic Driving Scenario Library](https://mlsanity.com/paper/1708.01872/) (2017)
- [Empirical Study of DSRC Performance Based on Safety Pilot Model Deployment Data](https://mlsanity.com/paper/1606.08365/) (2016)

## Built on by (most cited first, 7 of 7)

- [BridgeSim: Unveiling the OL-CL Gap in End-to-End Autonomous Driving](https://mlsanity.com/paper/2604.10856/) (2026)
- [RIFT: Group-Relative RL Fine-Tuning for Realistic and Controllable Traffic Simulation](https://mlsanity.com/paper/2505.03344/) (2025)
- [Learning collision risk proactively from naturalistic driving data at scale](https://mlsanity.com/paper/2505.13556/) (2025)
- [A Driving Regime-Embedded Deep Learning Framework for Modeling Intra-Driver Heterogeneity in Multi-Scale Car-Following Dynamics](https://mlsanity.com/paper/2506.05902/) (2025)
- [Invariant-based Mapping of Space During General Motion of an Observer](https://mlsanity.com/paper/2311.11130/) (2023)
- [Training Adversarial yet Safe Agent to Characterize Safety Performance of Highly Automated Vehicles](https://mlsanity.com/paper/2402.01576/) (2024)
- [Human Behavior-Informed Crash Scenario Generation with Real-World Crash Priors for Autonomous Vehicle Safety Evaluation](https://mlsanity.com/paper/2610.04366/) (2026)

## Abstract (arXiv)

Lane changes are complex driving behaviors and frequently involve safety-critical situations. This study aims to develop a lane-change-related evasive behavior model, which can facilitate the development of safety-aware traffic simulations and predictive collision avoidance systems. Large-scale connected vehicle data from the Safety Pilot Model Deployment (SPMD) program were used for this study. A new surrogate safety measure, two-dimensional time-to-collision (2D-TTC), was proposed to identify the safety-critical situations during lane changes. The validity of 2D-TTC was confirmed by showing a high correlation between the detected conflict risks and the archived crashes. A deep deterministic policy gradient (DDPG) algorithm, which could learn the sequential decision-making process over continuous action spaces, was used to model the evasive behaviors in the identified safety-critical situations. The results showed the superiority of the proposed model in replicating both the longitudinal and lateral evasive behaviors.