Precise motion estimation is vital for any mobile robot to correctly control its actuators and thus to navigate through terrain. Bar sic approaches of motion estimation (e.g. wheel odometry) that can be considered reliable in laboratory conditions tend to fail in real-world search and rescue scenarios because of uneven and slippery surface the robot has to cross. In this article, we pick some of the current localization and motion estimation techniques and discuss their prerequisites in contrast with experience gathered during end-user evaluations and a real-world deployment of our robotic platform in a town struck by an earthquake (Mirandola, Italy). The robotic platform is equipped with a set of sensors allowing us to combine various approaches to robot localization and motion estimation in order to increase the redundancy in the system and thus the overall reliability. We present our approach to fuse selected sensor modalities that was developed with emphasis on possible sensor failures, which have been subsequently experimentally tested.
展开▼