运动规划
地形
任意角度路径规划
路径(计算)
计算机科学
曲率
机器人学
曲面(拓扑)
图形
人工智能
运动学
路径长度
计算机视觉
算法
机器人
数学
地理
理论计算机科学
几何学
物理
程序设计语言
计算机网络
经典力学
地图学
作者
Riku Usami,Yuji Kobashi,Taiki Onuma,Takashi Maekawa
标识
DOI:10.1109/tiv.2019.2955904
摘要
We present a two-lane path planning of autonomous vehicles in two-and-a-half-dimensional (2.5D) environments. Our method builds on collision-free two-dimensional (2D) path-planning techniques from our previous work, and extends these techniques to 2.5D by mapping a 2D path in the parameter space onto a terrain graph surface, as a curve on the surface in the object space. Based on this path on the terrain surface, we propose a novel method of designing cross slopes in high curvature regions of the path, such that vehicles need not slow down in these regions. Furthermore, we apply time-optimal control techniques developed in robotics to compute the minimal-time speed control along the specified path. Examples are provided to demonstrate the effectiveness of the proposed algorithm.
科研通智能强力驱动
Strongly Powered by AbleSci AI