Scientists at Defence R&D Canada Suffield have been investigating autonomous operation of Unmanned Ground Vehicles (UGVs). In order to navigate unknown terrain effectively, UGVs must be able to create an accurate representation of the operational environment. This is typically done by constructing a geometric representation of the environment, called a Terrain Map, from exteroceptive and proprioceptive data streams. This Terrain Map can further be analyzed to provide a measure of the traversability of the terrain. The resulting Traversability Map can be utilized by path planning and obstacle avoidance algorithms to determine the best path to follow. This paper discusses DRDC s Traversability Map as a method of world representation. The Traversability Map interprets geometric data by calculating statistics about the environment to determine whether an area is traversable or not. In doing so, the Traversability Map interprets geometry from a vehicle specific context, allowing for the unique mobility characteristics of platforms to dictate map parameters.
Traversability Analysis for Unmanned Ground Vehicles: Interpreting the Environment
2006
36 pages
Report
Keine Angabe
Englisch
Algebra, Analysis, Geometry, & Mathematical Logic , Computers, Control & Information Theory , Transportation , Navigation Systems , Autonomous navigation , Ground vehicles , Unmanned , Robotics , Statistics , Terrain , Algorithms , Collision avoidance , Mapping , Paths , Perception , Planning , Traversability analysis , Ugv(Unmanned ground vehicles) , Obstacle avoidance , Path planning , Terrain mapping , Traversability mapping
Learning traversability models for autonomous mobile vehicles
British Library Online Contents | 2008
|Semantic scene understanding and traversability estimation for off-road vehicles
BASE | 2021
|Learning multiobjective rough terrain traversability
Elsevier | 2022
|