Calculon: An Autonomous Ground Vehicle for the 13th Annual Intelligent Ground Vehicle Competition

This paper presents the design of a totally autonomous vehicle built to compete in the 13th Intelligent Ground Vehicle Competition, IGVC. The vehicle, Calculon, is based on a powered wheelchair and uses a variety of sensors for its navigation and obstacle avoidance including a 3CCD Sony color camera, an outdoor laser range finder, a DGPS, 2 wheel encoders and a solid state compass. Obstacle avoidance is primarily done using its 2 main sensors; the laser range finder detects physical objects while its camera detects painted obstacles such as painted lines and pot holes. The color cameras 3CCD optical system is better suited for outdoor and poor lighting conditions. This along with a laser range finder the vehicle can detect obstacles and road features at a greater distance than in previous designs. Detecting obstacles at a greater distance makes higher speeds and less processing time possible. The sensor data is used to build a local area map containing the location of obstacles and waypoints. Accurate steering is accomplished by fusing its dead reckoning and DGPS positional data. An onboard laptop computer uses color and line finding algorithms such as Hough Transformation for machine vision. A modified road map / rapidly exploring random trees / potential field's method are used for path planning.