b-it-bots: Our Approach for Autonomous Robotics in Industrial Environments

This paper presents the approach of our team, b-it-bots, in the RoboCup@Work competition which resulted in us winning the World Championship in Sydney in 2019. We describe our current hardware, including modifications made to the KUKA youBot, the underlying software framework and components developed for navigation, manipulation, perception and task planning for scenarios in industrial environments. Our combined 2D and 3D approach for object recognition has improved robustness and performance compared to previous years, and our task planning framework has moved us away from large state machines for high-level control. Future work includes closing the perception-manipulation loop for more robust grasping. Our open-source repository is available at https://github.com/b-it-bots/mas_industrial_robotics.