Red-Team Multi-Agent Reinforcement Learning for Emergency Braking Scenario
Not on the map. Why?
Abstract (arXiv)
Current research on decision-making in safety-critical scenarios often relies on inefficient data-driven scenario generation or specific modeling approaches, which fail to capture corner cases in real-world contexts. To address this issue, we propose a Red-Team Multi-Agent Reinforcement Learning framework, where background vehicles with interference capabilities are treated as red-team agents. Through active interference and exploration, red-team vehicles can uncover corner cases outside the data distribution. The framework uses a Constraint Graph Representation Markov Decision Process, ensuring that red-team vehicles comply with safety rules while continuously disrupting the autonomous vehicles (AVs). A policy threat zone model is constructed to quantify the threat posed by red-team vehicles to AVs, inducing more extreme actions to increase the danger level of the scenario. Experimental results show that the proposed framework significantly impacts AVs decision-making safety and generates various corner cases. This method also offers a novel direction for research in safety-critical scenarios.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 33 references that are in the map. First posted on arXiv 21 Jul 2025.
Builds on
11 of 33 references.
References · 11
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
- 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
- 2022A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspectivecited by 105
- 2020Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Methodcited by 75
- 2020Adversarial Evaluation of Autonomous Vehicles in Lane-Change Scenarioscited by 43
- 2019CMTS: Conditional Multiple Trajectory Synthesizer for Generating Safety-critical Driving Scenarioscited by 19
- 2024Risk-Aware Vehicle Trajectory Prediction Under Safety-Critical Scenarioscited by 7
- 2024Multilevel Graph Reinforcement Learning for Consistent Cognitive Decision-making in Heterogeneous Mixed Autonomycited by 1
- 2025Dynamic Residual Safe Reinforcement Learning for Multi-Agent Safety-Critical Scenarios Decision-Makingcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2021Multi-Agent Vulnerability Discovery for Autonomous Driving with Hazard Arbitration Reward
- 2022Spatial-Temporal-Aware Safe Multi-Agent Reinforcement Learning of Connected Autonomous Vehicles in Challenging Scenarios
- 2025Safe Reinforcement Learning with a Predictive Safety Filter for Motion Planning and Control: A Drifting Vehicle Example
- 2022Automatically Learning Fallback Strategies with Model-Free Reinforcement Learning in Safety-Critical Driving Scenarios
- 2025MARL-OT: Multi-Agent Reinforcement Learning Guided Online Fuzzing to Detect Safety Violation in Autonomous Driving Systems
- 2025Uncertainty-Aware Safety-Critical Decision and Control for Autonomous Vehicles at Unsignalized Intersections
- 2021Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning
- 2024Cooperative Decision-Making for CAVs at Unsignalized Intersections: A MARL Approach with Attention and Hierarchical Game Priors