无人驾驶汽车的不断普及导致了自主赛车领域的研究和发展，而自主赛车中的超车是一项具有挑战性的任务。车辆必须在动态操控的极限下进行检测和操作，车内的决策必须在高速和高加速度下做出。自主竞赛中最关键的部分之一是路径规划和决策，以便与动态对手车辆进行超车操作。在本文中，我们介绍了对基于赛道的自主赛车离线策略学习方法的评估。我们定义了特定的赛道部分，并进行了离线实验，以评估基于自我车辆的速度和位置的超车演习的概率。基于这些实验，我们可以为每个赛道部分定义超车的概率分布。此外，我们提出了一个切换式MPCC控制器设置，以纳入所学到的政策，实现更高的超车机动率。通过详尽的模拟，我们表明，我们提出的算法能够增加不同轨道部分的超车数量。
A. 自主赛车
近几年来，自动驾驶赛车已经变得很流行，像Roborace[1]或Indy Autonomous Challenge这样的比赛，以及像F1Tenth[2]这样的小型赛车，为评估自动驾驶软件提供平台。所有这些比赛的总体目标是，研究人员和工程师可以开发在车辆边缘运行的算法。高速、高加速、高计算能力、对抗性环境。与一级方程式赛车等正常的赛车系列类似，自主赛车的算法开发在自主驾驶领域产生了信任，并使先进的自主驾驶算法得到发展。到目前为止，在自主赛车领域开发的算法大多只关注单车，试图实现类似人类的单圈时间。到目前为止，与动态对手的高动态超车动作领域的展示较少。此外，实现类似人类的行为（例如，像一级方程式赛车手），对超车动作作出决定，并在高速下执行安全可靠的动作，仍然是一个未解决的问题。
原文标题：Track based Offline Policy Learning for Overtaking Maneuvers with Autonomous Racecars
原文：
The rising popularity of driver-less cars has led to the research and development in the field of autonomous racing, and overtaking in autonomous racing is a challenging task. Vehicles have to detect and operate at the limits of dynamic handling and decisions in the car have to be made at high speeds and high acceleration. One of the most crucial parts in autonomous racing is path planning and decision making for an overtaking maneuver with a dynamic opponent vehicle. In this paper we present the evaluation of a track based offline policy learning approach for autonomous racing. We define specific track portions and conduct offline experiments to evaluate the probability of an overtaking maneuver based on speed and position of the ego vehicle. Based on these experiments we can define overtaking probability distributions for each of the track portions. Further, we propose a switching MPCC controller setup for incorporating the learnt policies to achieve a higher rate of overtaking maneuvers. By exhaustive simulations, we show that our proposed algorithm is able to increase the number of overtakes at different track portions.
- Autonomous Racing
Autonomous racing has become popular over the recent years and competitions like Roborace [1] or the Indy Autonomous Challenge as well as with small-scale racecars like F1Tenth [2] provide platforms for evaluating autonomous driving software. The overall goal of all these competitions is that researchers and engineers can develop algorithms that operate at the vehicles edge: High speeds, high accelerations, high computation power, adversarial environments. Similar to normal racing series like Formula 1 the development of algorithms for autonomous racing generate trust in the field of autonomous driving and enables the development of advanced autonomous driving algorithms. The algorithms that were developed in the field of autonomous racing so far are mostly focusing on single vehicle only that try to achieve a human-like lap time. The field of high dynamic overtaking maneuver with dynamic opponents was less displayed so far. In addition, achieving a human-like behavior (e.g. like a Formula 1 race driver) that makes the decision about an overtaking maneuver and executes a secure and reliable maneuver at high speeds is still an unsolved question.
Track based Offline Policy Learning for Overtaking Maneuvers with Autonomous Racecars.pdf