Multilayer occupancy grid for obstacle avoidance in an autonomous ground vehicle using RGB-D camera

TL;DR

This work describes the process of integrating a depth camera into the navigation system of a self-driving ground vehicle and the implementation of a multilayer costmap that enhances the vehicle's obstacle identification process by expanding its two-dimensional field of view to a three-dimensional perception system using an RGB-D camera.

Abstract

This work describes the process of integrating a depth camera into the navigation system of a self-driving ground vehicle (SDV) and the implementation of a multilayer costmap that enhances the vehicle's obstacle identification process by expanding its two-dimensional field of view, based on 2D LIDAR, to a three-dimensional perception system using an RGB-D camera. This approach lays the foundation for a robust vision-based navigation and obstacle detection system. A theoretical review is presented and implementation results are discussed for future work.

Figures (16)

• Figure 1: Vertical field of view concept for LiDAR 2D.
• Figure 2: SDV II vehicle from the LabFabEx sdvII_unimedios_report.
• Figure 3: Skid-steering architecture skid_steering_diagram.
• Figure 4: Costmap under the navigation system architecture of the SDV move_base_ros_node.
• Figure 5: The Multilayer Costmap concept costmap_multilayer.