Abstract
In this paper, we present a reactive, vision based obstacle avoidance technique for Unmanned Ground Vehicles (UGVs) navigating in an indoor environment without Global Positioning System (GPS) signals. The proposed technique enables UGVs to maneuver using only visual electro-optic sensors. The proposed work is unique in that, to the best of our knowledge, there was no other bearing angle only obstacle avoidance technique for ground vehicles reported in the literature. A Lyapunov-based sliding mode controller is used to maintain the bearing angle of the UGV from obstacles, using a real-time image processing method. The proposed technique is implemented and tested with a Pioneer robot in an indoor environment, and the results demonstrate its effectiveness.
Highlights
Over the past decade, an increasing number of unmanned systems have been used in both military and civilian applications such as surveillance, survey, and search and rescue missions
While global path planning approaches are used to guide a Unmanned Ground Vehicles (UGVs) to a destination, a local path planning is necessary for a UGV to reactively avoid unexpected obstacles while following an overall trajectory generated by a global path planner
Extracting Obstacle Information we describe the image processing algorithms used to compute the bearing angle between an obstacle and a UGV
Summary
An increasing number of unmanned systems have been used in both military and civilian applications such as surveillance, survey, and search and rescue missions. Bandyophadyay et al (2010) used a short range 2-D laser sensor to allow Autonomous Surface Craft (ASC) to reactively avoid obstacles They used simple linear prediction based on the current history of obstacles and ASC dynamics to determine the best path for USV to take. Lensar and Veloso (2003) presented an obstacle avoidance strategy using images from a single camera to estimate the range and angle to an obstacle with a known color. Conventional image processing methods were employed to obtain the bearing angle between a UGV and obstacles. 2. Extracting Obstacle Information we describe the image processing algorithms used to compute the bearing angle between an obstacle and a UGV. The second sub-controller, the focus of this paper, is constructed based on a Lyapunov-based sliding mode control algorithm
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
