Abstract
Inspired by the human 3D visual perception system, we present an obstacle detection and classification method based on the use of Time-of-Flight (ToF) cameras for robotic navigation in unstructured environments. The ToF camera provides 3D sensing by capturing an image along with per-pixel 3D space information. Based on this valuable feature and human knowledge of navigation, the proposed method first removes irrelevant regions which do not affect robot's movement from the scene. In the second step, regions of interest are detected and clustered as possible obstacles using both 3D information and intensity image obtained by the ToF camera. Consequently, a multiple relevance vector machine (RVM) classifier is designed to classify obstacles into four possible classes based on the terrain traversability and geometrical features of the obstacles. Finally, experimental results in various unstructured environments are presented to verify the robustness and performance of the proposed approach. We have found that, compared with the existing obstacle recognition methods, the new approach is more accurate and efficient.
Highlights
Nowadays, mobile robots, such as the unmanned ground vehicle (UGV), rescue robots, and space robots, are being increasingly utilized in complex and unstructured environments extending from the traditional indoor or man-made environments
This paper proposes an obstacle detection and classification method based on the use of Time of Flight (TOF) Camera-SR3000 manufactured by Mesa Imaging AG (Zürich, Switzerland)
We select integration time based on the following facts: First, as we focus on obstacle detection and classification, the environment is simplified in our study
Summary
Mobile robots, such as the unmanned ground vehicle (UGV), rescue robots, and space robots, are being increasingly utilized in complex and unstructured environments extending from the traditional indoor or man-made environments. With the increasing environmental complexity, fast and robust 3D environment perception and recognition have become extremely important in autonomous robotic navigation. Compared with a structured environment, unstructured environments are usually more complex and have less static and obviously distinguishable features, such as planar surfaces, country roads and other recognizable field features. A more realistic case is shown, where there are two regions with large height differences. There are no obvious image features, such as color, texture, intensity etc., to distinguish the height differences from each other. There are more noises and environmental disturbance, such as dramatic light changes
Sign-in/Register to view highlights & summary 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.
