Many robotics tasks require an ability to determine quickly the nature of the terrain surrounding the robot. In cross country navigation in particular, the robot needs to know where the vegetation is and where the hard obstacles are. I have developed a general system which has successfully allowed real-time terrain typing in the NavLab II autonomous vehicle. This system and training paradigm are based on standard neural network technology and allow the robot to learn arbitrary non-linear mappings from color and texture space to terrain space.
Neural Networks for Real-Time Terrain Typing
1995
16 pages
Report
No indication
English
Terrain Typing for Real Robots
British Library Conference Proceedings | 1995
|Terrain typing for real robots
IEEE | 1995
|Modeling Terrestrial Mobile Networks in Real Terrain
British Library Conference Proceedings | 1999
|Terrain contour matching with recurrent neural networks
IEEE | 2018
|