Embedded Vision for Self-Driving on Forest Roads

25th June, 2021

Authors Sorin Grigorescu, Mihai Zaha, Bogdan Trasnea and Cosmin Ginerica

Abstract: Forest roads in Romania are unique natural wildlife sites used for recreation by countless tourists. In order to protect and maintain these roads, we propose RovisLab AMTU (Autonomous Mobile Test Unit), which is a robotic system designed to autonomously navigate off-road terrain and inspect if any deforestation or damage occurred along tracked route. AMTU’s core component is its embedded vision module, optimized for real-time environment perception. For achieving a high computation speed, we use a learning system to train a multi-task Deep Neural Network (DNN) for scene and instance segmentation of objects, while the keypoints required for simultaneous localization and mapping are calculated using a handcrafted FAST feature detector and the Lucas-Kanade tracking algorithm. Both the DNN and the handcrafted backbone are run in parallel on the GPU of an NVIDIA AGX Xavier board. We show experimental results on the test track of our research facility.

Color map of what the robot sees

Embedded vision results using the four cameras of the robot. The perception system is trained to segment the scene, as well as to track relevant feature points used for simultaneous localization and mapping. The color of the points encodes each feature point’s ID

Multimedia material is available at:


The paper can be found at the following link: https://arxiv.org/abs/2105.13754

, , ,