A Review of Motion Planning Techniques for Automated Vehicles

综述和分类

0

Motion Planning for Autonomous Driving with a Conformal Spatiotemporal Lattice

从unstructured环境向structured环境的拓展，同时还从state lattice拓展到了spatiotemporal lattice从而解决path+speed=trajectory的motion planning问题

conformed? 顺从结构化道路，比如终点sample的朝向，曲率

k(s) path set， 不需要frenet

v(s) speed set

问题： 这种路径和spiral， clothoid 有什么区别

https://zhuanlan.zhihu.com/p/495193848

1

A Real-Time Motion Planner with Trajectory Optimization for Autonomous Vehicles

spatiotemporal lattice

横向采样用了第一篇的思维， cost 感觉和Apollodp 里面静态动态障碍物差不多

后面优化项没看懂

2

DL-IAPS and PJSO: A Path/Speed Decoupled Trajectory Optimization and its Application in Autonomous Driving

优化算法SCP sequential convex programming

弹性带理论CES

平滑模型 cost-theta smooth 不是fem

PJSO: 粗解cubic polynomial, 细解： pwj

3

Reactive nonholonomic trajectory generation via parametric optimal control

基础理论，待读

最优控制 ocp

PolyTraj

Apollo 2017 cubic spiral / quintic spiral

https://zhuanlan.zhihu.com/p/495193848

4

Optimal Trajectory Generation for Dynamic Street Scenarios in a Frenet Frame

BMW werling frenet_lattice_planner / apollo lattice

5

FISS: A Trajectory Planning Framework Using Fast Iterative Search and Sampling Strategy for Auto Driving

对比werlling vanila vs apollo lattice 效率，提出一种迭代最优搜索求解， 主要创新点是快速找出最优解

A Reasoning Framework for Autonomous Urban Driving

DARPA 挑战赛 boss 论文， 分成三个场景， lanedriving, intersection, unstructured, lane driving 主要是 spiral lattice planner， intersection 主要是路口 划区域的择机问题， unstructured 主要是用D* lattice graph search