English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose a Visual Teach and Repeat (VTR) algorithm using semantic landmarksextracted from environmental objects for ground robots with fixed mountmonocular cameras. The proposed algorithm is robust to changes in the startingpose of the camera/robot, where a pose is defined as the planar position plusthe orientation around the vertical axis. VTR consists of a teach phase inwhich a robot moves in a prescribed path, and a repeat phase in which the robottries to repeat the same path starting from the same or a different pose. Mostavailable VTR algorithms are pose dependent and cannot perform well in therepeat phase when starting from an initial pose far from that of the teachphase. To achieve more robust pose independency, the key is to generate a 3Dsemantic map of the environment containing the camera trajectory and thepositions of surrounding objects during the teach phase. For specificimplementation, we use ORB-SLAM to collect the camera poses and the 3D pointclouds of the environment, and YOLOv3 to detect objects in the environment. Wethen combine the two outputs to build the semantic map. In the repeat phase, werelocalize the robot based on the detected objects and the stored semantic map.The robot is then able to move toward the teach path, and repeat it in bothforward and backward directions. We have tested the proposed algorithm indifferent scenarios and compared it with two most relevant recent studies.Also, we compared our algorithm with two image-based relocalization methods.One is purely based on ORB-SLAM and the other combines Superglue and RANSAC.The results show that our algorithm is much more robust with respect to posevariations as well as environmental alterations. Our code and data areavailable at the following Github page:https://github.com/mmahdavian/semantic_visual_teach_repeat.

Robust Visual Teach and Repeat for UGVs Using 3D Semantic Maps