engleski

Radar-IMU-camera system data fusion for ego-motion estimation

Knowledge of ego-motion is a key task for all autonomous mobile robots. For that purpose, one usually uses sensors like cameras, inertial measurement units (IMU), and lidars. Given recent developments, novel research is also targeting radars for ego-motion estimation due to their robustness to environmental conditions. Different sensors measure different physical properties of the environment or inner system states. Thus their limitations and the extent of operating conditions can differ substantially. By fusing different sensors, we can increase the system's robustness and extend operating conditions. The goal of this thesis is to estimate the ego-motion of a sensor platform by fusing radar, camera, and IMU data. To that end, novel dataset collection will be required through which fusion can be carried out and accuracy analyzed.

Radar ; Camera ; Inertial measurement unit ; Sensor fusion ; Kalman filtar ; State estimation

nije evidentirano