Robot Obstacle Avoidance using the Kinect.

Abstract

Kinect for Xbox 360 is a low-cost controller-free device originally designed for gaming and entertainment experience by Microsoft Corporation. This device is equipped with one IR camera, one color camera and one IR projector to produce images with voxels (depth pixels). This additional dimension to the image, makes it a tempting device to be used as an invaluable sensor in robotics applications which is the motivation for this master thesis. This work presents a solution using the Kinect sensor to cope with one important aspect of autonomous mobile robotics, Obstacle Avoidance. Modeling the environment based on the point cloud extracted from the depth image data as well as an obstacle avoidance method using the straight line segments and circle arcs, were the main focus of the thesis. The environment is represented by a set of polygons and the obstacle avoidance algorithm attempts to find a collision-free path from the current position of the robot to the target pose subject to the shortest possible path considering a safeguard. The whole algorithm was implemented and simulated in Matlab successfully. However, it is partially implemented in C++ to be able to integrate into the current software architecture of the project CogX running at CVAP/CAS department, KTH. A mobile robotic platform based on Pioneer P3-DX which was equipped with a LIDAR module that the obstacle avoidance algorithm relied on its perception only. The shortcoming of not being able to detect all types of obstacles was the motivation to use the Kinect sensor to extend the ability of detecting obstacles and hence to improve the local path planner and obstacle avoidance components in the software.