Generating diverse and comprehensive interacting agents to evaluate the decision-making modules is essential for the safe and robust planning of autonomous vehicles~(AV). Due to efficiency and safety concerns, most researchers choose to train interactive adversary~(competitive or weakly competitive) agents in simulators and generate test cases to interact with evaluated AVs. However, most existing methods fail to provide both natural and critical interaction behaviors in various traffic scenarios. To tackle this problem, we propose a styled generative model RouteGAN that generates diverse interactions by controlling the vehicles separately with desired styles. By altering its style coefficients, the model can generate trajectories with different safety levels serve as an online planner. Experiments show that our model can generate diverse interactions in various scenarios. We evaluate different planners with our model by testing their collision rate in interaction with RouteGAN planners of multiple critical levels.
翻译:产生多种和全面的互动代理来评价决策模块,对于安全、稳健地规划自治车辆(AV)至关重要。由于效率和安全考虑,大多数研究人员选择在模拟器中培训互动敌(有竞争力或竞争力弱的)代理,并生成测试案例,以便与经评估的AV互动。然而,大多数现有方法未能在各种交通情景中提供自然和关键的互动行为。为解决这一问题,我们提议了典型的基因模型RUBGAN,通过以理想的风格分别控制车辆,产生多种互动。通过改变其风格系数,该模型可以产生具有不同安全等级的轨迹,作为在线规划者。实验表明,我们的模型可以在不同情景中产生不同互动。我们通过与多关键级别的RUPGAN规划者互动测试不同模型的碰撞率,从而评估不同模型与模型的碰撞率。