Modeling Environmental Uncertainty in Ground Robot Navigation
Abstract
The Missouri University of Science and Technology (formerly University of Missouri-Rolla) Robotics Competition Team has developed an innovative solution to the challenge presented by the Intelligent Ground Vehicle Competition. the challenge calls for a ground robot to navigate an obstacle course consisting of boundary lines and upright obstacles. the obstacle course, arranged on a grass field bounded by painted lines, includes construction barrels, heavy-duty netting, cones, trees and simulated potholes. This competition expects students to focus on advanced path planning, control, and vision algorithms. the base system can be extended with higher-level learning algorithms for any ground vehicle platform. the team's solution is to have the robot develop two models of its environment. the first is simply a map of the obstacles detected by the robot's sensors. the second records the uncertainty of each region in the obstacle model. These models are populated by a vision system and accessed by an intelligent control system to drive the robot. This allows the team's omni-directional robot to look in areas of low certainty while driving in areas of low cost, thus making the robot seem curious and intelligent in its environment.
Recommended Citation
R. Meuth et al., "Modeling Environmental Uncertainty in Ground Robot Navigation," AUVSI Unmanned Systems North America Conference 2008, vol. 1, pp. 132 - 141, Association for Unmanned Vehicle Systems International, Dec 2008.
Department(s)
Electrical and Computer Engineering
Second Department
Computer Science
International Standard Book Number (ISBN)
978-161567194-6
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2024 Association for Unmanned Vehicle Systems International, All rights reserved.
Publication Date
01 Dec 2008