Navigation System for Mobile Robot using RGBD Sensor based on Probabilistic Roadmaps

The research of autonomous mobile has always been a popular field and navigation system is one of the key topic. To achieve autonomous capability, a well-behave navigation system is required. Currently, there are many different kinds of path planning methods, each with its own advantages and disadvantages. This paper presents an indoor navigation system for mobile robot using a RBGD sensor base on probabilistic roadmaps(PRM). In this approach, the indoor environment is identified with the use of RGBD SLAM algorithm and a cloud point map is generated. Then the point cloud map is converted to Octo-map that can be used to create occupancy grid map. In the end, a collision-free path is produced for mobile robot based on modified PRM algorithm. The experiments are conducted with robot operating system (ROS), mobile robot and Kinect v2. The result shows that the navigation system has good performance on mobile robot within an indoor environment.