Digitalization and new robotic systems technologies offer opportunities to rethink the future of rail mobility in terms of real-time capacity optimization and complete on-board situational awareness. By shifting the focus from track-side infrastructure to on-board solutions, we can enhance system safety, efficiency and robustness. The overall aim of this project is to provide a localization solution capable of low-drift odometry that can globally re-localize in a known and iteratively refined map. The design of our sensor suite, as well as the proposed mapping and motion estimation methods will target the domain challenges of the train network, including operating in different environmental conditions, as well as fundamental algorithmic challenges of pose estimation for railway systems where some states are unobservable. The contributions of this project will enable a safer, more efficient and more reliable train network while reducing the deployment and maintenance costs of the system. Consequently, end customers will benefit from greater train availability and fewer disruptions.
Prof. Dr. Roland Siegwart
Autonomous Systems Lab
Prof. Dr. Margarita Chli
Vision for Robotics Lab
11.2018 (36 months)