Designing traffic-smoothing cruise controllers that can be deployed onto autonomous vehicles is a key step towards improving traffic flow, reducing congestion, and enhancing fuel efficiency in mixed autonomy traffic. We bypass the common issue of having to carefully fine-tune a large traffic microsimulator by leveraging real-world trajectory data from the I-24 highway in Tennessee, replayed in a one-lane simulation. Using standard deep reinforcement learning methods, we train energy-reducing wave-smoothing policies. As an input to the agent, we observe the speed and distance of only the vehicle in front, which are local states readily available on most recent vehicles, as well as non-local observations about the downstream state of the traffic. We show that at a low 4% autonomous vehicle penetration rate, we achieve significant fuel savings of over 15% on trajectories exhibiting many stop-and-go waves. Finally, we analyze the smoothing effect of the controllers and demonstrate robustness to adding lane-changing into the simulation as well as the removal of downstream information.

翻译：设计可部署于自动驾驶车辆上的交通流平滑巡航控制器，是改善混合交通环境下交通流运行、缓解拥堵并提升燃油经济性的关键步骤。我们通过利用田纳西州I-24高速公路的真实轨迹数据，在单车道仿真中进行回放，绕过了通常需要精细调校大规模交通微观模拟器的常见难题。采用标准深度强化学习方法，我们训练了能够减少能量的波动平滑策略。智能体可观测前车的速度与距离（该局部状态信息已为多数新型车辆所具备），以及下游交通状态的全局观测数据。研究表明，在仅4%的自动驾驶车辆渗透率下，对于呈现频繁启停波的轨迹，燃油消耗可显著降低超过15%。最后，我们分析了控制器的平滑效应，并验证了其在仿真中增加换道行为及移除下游信息时的鲁棒性。