Achieving the right balance between planning quality, safety and efficiency is a major challenge for autonomous driving. Optimisation-based motion planners are capable of producing safe, smooth and comfortable plans, but often at the cost of runtime efficiency. On the other hand, naively deploying trajectories produced by efficient-to-run deep imitation learning approaches might risk compromising safety. In this paper, we present PILOT -- a planning framework that comprises an imitation neural network followed by an efficient optimiser that actively rectifies the network's plan, guaranteeing fulfilment of safety and comfort requirements. The objective of the efficient optimiser is the same as the objective of an expensive-to-run optimisation-based planning system that the neural network is trained offline to imitate. This efficient optimiser provides a key layer of online protection from learning failures or deficiency on out-of-distribution situations that might compromise safety or comfort. Using a state-of-the-art, runtime-intensive optimisation-based method as the expert, we demonstrate in simulated autonomous driving experiments in CARLA that PILOT achieves a significant reduction in runtime when compared to the expert it imitates without sacrificing planning quality.
翻译:实现规划质量、安全和效率之间的适当平衡是自主驾驶的一大挑战。优化型运动规划者能够制定安全、顺畅和舒适的计划,但往往以运行效率为代价。另一方面,天真地部署高效到运行深度模仿学习方法产生的轨迹可能会危及安全。在本文中,我们介绍PILOT -- -- 一个规划框架,包括一个模仿神经神经网络,然后有一个高效的优化器,积极修正网络的计划,保证满足安全和舒适要求。高效的优化仪的目标与一个昂贵到运行的优化型规划系统的目标相同,即对神经网络进行离线培训以模仿。这一高效的优化仪提供了关键的在线保护,防止在可能损害安全或舒适的传播情形中学习失败或缺陷。我们以专家的身份使用一种最先进的、运行时间密集的优化方法,在CARLA的模拟自动驾驶实验中展示,PILOT在不做专家的模拟性规划时,在不进行质量模拟时,在不作牺牲的情况下,在不作牺牲的情况下,大幅降低质量。