Path evaluation for a mobile robot based on a risk of collision
Mari Irie, Keiji Nagatani, Akio Gofuku
- Year
- 2004
- Citations
- 5
Abstract
An odometry system that mobile robot uses for positioning has cumulative error because of wheels' slippage and uneven ground. It causes a risk of collision of obstacles. Therefore, we propose a path evaluation method for a mobile robot based on a risk of collision. To evaluate a robot's path, we define an evaluation value as an integral of a risk of collision along the path. To evaluate the risk of collision at each point, we use an estimated positioning error generated in the odometry system. Using the evaluation method, the robot can plan a path based on a risk of collision, not the shortest path. We also consider sensing points planning for position adjustment of the mobile robot, based on the same approach. Some examples of path evaluation results support a validity of the proposed method.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Fractional Differential Equations
Igor Podlubný
2025
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991