Using Reachable Sets for Trajectory Planning of Automated Vehicles
Using Reachable Sets for Trajectory Planning of Automated Vehicles
复制标题
DOI：
10.1109/tiv.2020.3017342
复制
发表时间：
2021-06
影响因子：
8.2
通讯作者：
Stefanie Manzinger;Christian Pek;M. Althoff
中科院分区：
文献类型：
--
作者：
Stefanie Manzinger;Christian Pek;M. Althoff
自动驾驶车辆的轨迹规划的计算工作量往往随着交通状况的复杂性而增加。这在车辆必须及时做出反应的安全关键情况下尤其成问题。我们提出了一种新的自动驾驶汽车的运动规划方法，它结合了基于集合的可达性分析与凸优化来解决这个问题。这种组合使得即使在小而复杂的解空间中也可以找到驾驶机动。与现有的工作相比，我们的方法的计算时间通常会减少，更复杂的情况变得。我们展示了我们的运动规划的好处，从CommonRoad基准套件的情况下，并验证了一个真实的测试车辆的方法。
The computational effort of trajectory planning for automated vehicles often increases with the complexity of the traffic situation. This is particularly problematic in safety-critical situations, in which the vehicle must react in a timely manner. We present a novel motion planning approach for automated vehicles, which combines set-based reachability analysis with convex optimization to address this issue. This combination makes it possible to find driving maneuvers even in small and convoluted solution spaces. In contrast to existing work, the computation time of our approach typically decreases, the more complex situations become. We demonstrate the benefits of our motion planner in scenarios from the CommonRoad benchmark suite and validate the approach on a real test vehicle.