Terrain-aware motion planning for a walking robot
Szymon Bartoszyk, Patryk Kasprzak, Dominik Belter
- 发表年份
- 2017
- 引用次数
- 12
摘要
In this paper, we propose a new environment model for legged robots. The model stores information about the shape of the obstacles and terrain type. We also propose the motion planner which takes into account terrain types when planning the motion of the robot. The planner is based on A* graph search method that guides RRT-Connect method for precise motion planning. With the proposed navigation system the robot is capable of planning its motion on the terrain with various terrain types and avoid regions which are potentially risky. Finally, we provide results of the experiments which show the properties of the proposed perception system and motion planner.
关键词
相关论文
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002