Decoupled Sampling Based Planning Method for Multiple Autonomous Vehicles

This paper proposes a sampling based planning algorithm to control autonomous vehicles. We propose an improved Rapidly-exploring Random Tree which includes the definition of K- nearest points and propose a two-stage sampling strategy to adjust RRT in other to perform maneuver while avoiding collision. The simulation results show the success of the algorithm.

A sub-optimal sampling based method for path planning

In this paper a search algorithm is proposed to find a sub optimal path for a non-holonomic system. For this purpose the algorithm starts sampling the front part of the vehicle and moves towards the destination with a cost function. The bicycle model is used to define the non-holonomic system and a stability analysis with different integration methods is performed on the dynamics of the system. A proper integration method is chosen with a reasonably large step size in order to decrease the computation time. When the tree is close enough to destination the algorithm returns the path and in order to connect the tree to destination point an optimal control problem using single shooting method is defined. To test the algorithm different scenarios are tested and the simulation results show the success of the algorithm.