JediBot is an autonomous robot designed to duel with humans in simulated sword fights. It was created by a group of four students in Stanford University's Experimental Robotics class, who combined a KUKA Light-Weight Robot arm for manipulation and a Microsoft Kinect for 3D sensing, along with custom software that leverages several open source libraries, including the Point Cloud Library (PCL) for 3D perception, the Reflexxes Motion Library for motion planning, and the Fast Research Interface Library for low-level control.
When facing off against a human combatant, the JediBot's software starts by analyzing the point cloud data acquired from its Microsoft Kinect 3D-camera. The Point Cloud Library is used to robustly find the pose of an opponent's sword in real time. The JediBot then quickly plans its response. Depending on the current strategy (attack or defense) an appropriate pose of the robot's sword is calculated. This pose is then sent to the Reflexxes Motion Library, which continuously plans a smooth sequence of arm motions. The resulting robot motions are directly sent to the Fast Research Interface Library, which provides low-level access to the motion controllers of the KUKA Light-Weight Robot.
Examples of PCL's stick segmentation algorithms are shown in the two videos below. The stick segmentation model was developed precisely for JediBot by the PCL development team. More information about it is available on our tutorials page.
By leveraging the power of these existing libraries, JediBot's developers were able to create a highly capable integrated system in a very short time. And because these libraries contain highly optimized algorithms, JediBot is also incredibly responsive. The Point Cloud Library is able to recognize an opponent's sword in real time, and the subsequent motion plans can be computed in under a millisecond, which allows the robot to react immediately to its opponent's movements, and when the two swords make contact, the robot can instantly recoil and respond.
JediBot is a great demonstration of what talented developers can do with open source tools. And although it began as a class project, it has become surprisingly popular. A video about JediBot is currently Stanford University's most-viewed research video, and because of its unexpected success and international media attention, the JediBot was recently presented to the international research community at the International Conference on Intelligent Robots and Systems (IROS) 2011. The video below presents the demonstration that took place at the KUKA booth at IROS:
If you'd like to learn more about JediBot or get in touch with its developers, you can contact Torsten Kroeger at firstname.lastname@example.org.