ROBOTIC GUIDANCE Joe Stawicki PROJECT DESCRIPTION Teach a robot to guide a person to a predefined destination. The robot must use a cam and a vision algorithm(s) as the main guidance. Sensors such as bump, infra-red and ultra-sound could provide direction and safety for the robot. The solution should be easily modified for alternative routes. Check out Alexander Popov’s 2011 senior project for techniques about driving the robot. MY SOLUTION Turtlebot Kinect Sensor/Gyroscope ROS (Robot Operating System) Moves the robot Gathers data Kinect Sensor Gyroscope Calculates the next position User Interface SLAM (Simultaneous Localization and Mapping) KINECT SENSOR Variety of Sensors 3D depth sensors Laser RGB camera Array of Microphones SLAM Simultaneous Localization and Mapping Build map of unknown environment Uses Sensors Keeps track of current location Based on what it sees/has seen Navigate to a particular spot on the map PROBLEMS Network Issues (SNC Firewall) Using ROS (Open Source) Weight Balance Issues MORE WORK… Calibration of the gyroscope METHODOLOGY Moving the Robot using Sasha’s project Assembling the Turtlebot ROS Installation ROS Tutorials Teleop/Navigation Adaptation to new environments Documentation DEMO RESOURCES Sasha Popov Professors Dr. Pankratz and Dr. McVey Classmates ROS.org Many tutorials/how-to’s/answers Other online resources Trial and Error KNOWLEDGE Programming Languages (CS 322) Turtlebot software written in Python Analysis of Algorithms (CS 321) Navigation Operating Systems (CS 370) Linux and ROS All Classes EXTENSIONS Voice Activation Other Turtlebot Applications Object Avoidance Mobile Device Operation Turtlebot Arm ADVICE FOR UPCOMING SENIORS Start early Do little bits Weekly meetings are very helpful Document as you go When stuck, ask for help Enjoy it!! QUESTIONS???