SaFeR：通过可行性约束的令牌重采样实现自动驾驶测试的安全关键场景生成
SaFeR: Safety-Critical Scenario Generation for Autonomous Driving Test via Feasibility-Constrained Token Resampling
AI总结：
SaFeR通过可行性约束的令牌重采样生成安全关键场景，提升自动驾驶测试的对抗性和现实性
摘要：
安全关键场景生成对于评估自动驾驶系统至关重要。然而，现有方法往往难以平衡三个相互冲突的目标：对抗性关键性、物理可行性以及行为现实性。为解决这一问题，我们提出了SaFeR：通过可行性约束的令牌重采样实现自动驾驶测试的安全关键场景生成。我们首先将交通生成建模为一个离散的下一个令牌预测问题，采用基于Transformer的模型作为现实性先验，以捕捉自然驾驶分布。为了捕捉复杂相互作用并有效减轻注意力噪声，我们提出了一种新的微分注意力机制，用于现实性先验中。在此先验基础上，SaFeR实现了新的重采样策略，该策略在高概率信任区域内诱导对抗性行为以维持自然性，同时施加源自最大可行区域（LFR）的可行性约束。通过离线强化学习近似LFR，SaFeR有效防止了理论上不可避免的碰撞生成。在Waymo Open Motion Dataset和nuPlan上的闭环实验表明，SaFeR显著优于现有最先进基线，实现了更高的解决方案率和更优越的运动学现实性，同时保持了强大的对抗有效性。
英文摘要：
Safety-critical scenario generation is crucial for evaluating autonomous driving systems. However, existing approaches often struggle to balance three conflicting objectives: adversarial criticality, physical feasibility, and behavioral realism. To bridge this gap, we propose SaFeR: safety-critical scenario generation for autonomous driving test via feasibility-constrained token resampling. We first formulate traffic generation as a discrete next token prediction problem, employing a Transformer-based model as a realism prior to capture naturalistic driving distributions. To capture complex interactions while effectively mitigating attention noise, we propose a novel differential attention mechanism within the realism prior. Building on this prior, SaFeR implements a novel resampling strategy that induces adversarial behaviors within a high-probability trust region to maintain naturalism, while enforcing a feasibility constraint derived from the Largest Feasible Region (LFR). By approximating the LFR via offline reinforcement learning, SaFeR effectively prevents the generation of theoretically inevitable collisions. Closed-loop experiments on the Waymo Open Motion Dataset and nuPlan demonstrate that SaFeR significantly outperforms state-of-the-art baselines, achieving a higher solution rate and superior kinematic realism while maintaining strong adversarial effectiveness.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
