Friday, October 5, 2012

Self Navigating Robots


Robots could navigate through constantly changing surroundings with no inputs from humans with a system being developed by researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL).
PR2 Robot

The approach is based on Simultaneously Localisation And Mapping(SLAM). As the robot travels through an unexplored area, the kinect sensor's visible light video camera and infra red depth sensor scan the surroundings, building up a 3D model of the walls of the rooms and the objects within it. Then, when the robot passes through the same area again, the system compares the features of the new image it has created - including details such as edges of the wall for example with all the previous images it has taken until it finds a match.

At the same time the system constantly estimates the robot's motion using on-board sensors that measures the distance its wheels has rotated. By comparing the visual information with this data, it can be determined where within the building the robot is positioned. Comparing the two sources of information it allows the system to eliminate errors that might creep in it if relied on robot's on-board sensors alone.

No comments:

Post a Comment