【Review]Planning and Decision-Making for Autonomous Vehicles

自动驾驶汽车的运动规划-Motion Planning for Autonomous Vehicles

3类传统方法：[1]

1. The first is input space discretization with collision checking, such as lattice planners or road-aligned primitives, whose main advantage is their simplicity and effectiveness, especially in highway scenarios.
2. The second is randomized planning, such as rapidly exploring random trees (RRT), whose main advantage is the probabilistic exploration of large state spaces, albeit at a high computational cost.
3. The third is constrained optimization and receding-horizon control, which have been applied mostly to path following but now can also compute collision-free trajectories to avoid other traffic participants.

5类运动规划的搜索空间[2]