自杀式行人：自动驾驶车辆安全关键场景的生成
Suicidal Pedestrian: Generation of Safety-Critical Scenarios for Autonomous Vehicles
AI总结：
本文提出在CARLA模拟器中设计自杀式行人强化学习智能体，自动生成安全关键场景，以测试自动驾驶算法并识别其决策错误。
摘要：
开发可靠的自动驾驶算法在测试方面面临挑战，尤其是在涉及行人的安全关键交通场景中。一个悬而未决的问题是，如何模拟那些不一定出现在自动驾驶数据集或脚本化仿真中、但可能在测试中出现并最终导致严重行人相关事故的罕见事件。本文提出了一种在CARLA模拟器中设计自杀式行人智能体的方法，能够自动生成用于在危险情况下测试自动驾驶车辆（AV）安全性的交通场景。该行人被建模为强化学习（RL）智能体，具有两个自定义奖励函数，使得智能体能够任意地或以高速度与自动驾驶车辆碰撞。我们不对初始位置和行人行为进行严格限制，而是允许行人和自动驾驶汽车放置在环境中的任何位置，并允许行人自由漫游以生成多样化的场景。为了评估测试期间自杀式行人和目标车辆的性能，我们提出了三个面向碰撞的评估指标。实验涉及两个最先进的自动驾驶算法，这些算法通过从传感器数据进行端到端模仿学习训练，实验结果证明了自杀式行人在识别由这些算法控制的自动驾驶车辆所做出的决策错误方面的有效性。
英文摘要：
Developing reliable autonomous driving algorithms poses challenges in testing, particularly when it comes to safety-critical traffic scenarios involving pedestrians. An open question is how to simulate rare events, not necessarily found in autonomous driving datasets or scripted simulations, but which can occur in testing, and, in the end may lead to severe pedestrian related accidents. This paper presents a method for designing a suicidal pedestrian agent within the CARLA simulator, enabling the automatic generation of traffic scenarios for testing safety of autonomous vehicles (AVs) in dangerous situations with pedestrians. The pedestrian is modeled as a reinforcement learning (RL) agent with two custom reward functions that allow the agent to either arbitrarily or with high velocity to collide with the AV. Instead of significantly constraining the initial locations and the pedestrian behavior, we allow the pedestrian and autonomous car to be placed anywhere in the environment and the pedestrian to roam freely to generate diverse scenarios. To assess the performance of the suicidal pedestrian and the target vehicle during testing, we propose three collision-oriented evaluation metrics. Experimental results involving two state-of-the-art autonomous driving algorithms trained end-to-end with imitation learning from sensor data demonstrate the effectiveness of the suicidal pedestrian in identifying decision errors made by autonomous vehicles controlled by the algorithms.
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。
