2002 · 145 citations · 14 references
EngineeringAutonomous SystemsRobotics EngineeringMobile RoboticsRobot VisionRoboticsAutonomous NavigationMobile Robot ControlObstacle AvoidanceObstacle DetectionRobot NavigationRobotic VisionComputer Vision For AvoidanceMobile Robot NavigationMonocular Obstacle DetectionNavigation In Unstructured EnvironmentsObstacle Detection SystemsSmall Obstacle DetectionVision-based GuidanceVision-based Navigation
The study introduces an autonomous vision‑based obstacle avoidance system. The system uses three lightweight vision modules—brightness gradients, RGB, and HSV—whose outputs independently select the control commands on a small monocular mobile robot with low‑resolution images. The system was evaluated for over 200 hours across diverse environments, demonstrating robust performance.
This paper presents an autonomous vision-based obstacle avoidance system. The system consists of three independent vision modules for obstacle detection, each of which is computationally simple and uses a different criterion for detection purposes. These criteria are based on brightness gradients, RGB (red, green, blue) color, and HSV (hue, saturation, value) color, respectively. Selection of which modules are used to command the robot proceeds exclusively from the outputs of the modules themselves. The system is implemented on a small monocular mobile robot and uses very lour resolution images. It has been tested for over 200 hours in diverse environments.
14