Allowing untrained scientists to safely pilot ROV's: Early collision detection and avoidance using omnidirectional vision
The study of underwater environments involves multiple hazards that can compromise the safety of robots. Underwater missions require a high level of attention from Remotely Operated Vehicle (ROV) operators to avoid damage to the robot. For this reason, there is a growing trend in research to develop systems with new capabilities, such as advanced assisted mapping, spatial awareness and safety, and user immersion. The aim of this work is to devise a system that provides the vehicle with proximity awareness capabilities for navigation in complex environments. By using the advantages of omnidirectional multi-camera systems a much higher level of spatial awareness can be achieved. This paper presents a visual-based multi-camera system which is able to detect the presence of nearby objects in the environment, to create a local map of points, and to assign collision risk values to this map. The system exploits this information to generate warnings when approaching potentially dangerous obstacles and at the same time creates a collision risk map that provides a proximity awareness representation of the environment.
Extrinsic visual-inertial calibration for motion distortion correction of underwater 3D scans
Underwater 3D laser scanners are an essential type of sensor used by unmanned underwater vehicles (UUVs) for operations such as navigation, inspection, and object recognition and manipulation. Scanners that acquire 3D data by sweeping a laser plane across the scene can provide very high lateral resolution. However, their data may suffer from rolling shutter effect if the change of pose of the robot with respect to the scanned target during the sweep is not negligible. In order to compensate for motion-related distortions without the need for point cloud postprocessing, the 6-DoF pose at which the scanner acquires each line needs to be accurately known. In the underwater domain, autonomous vehicles are often equipped with a high-end inertial navigation system (INS) that provides reliable navigation data. Nonetheless, the relative pose of the 3D scanner with respect to the inertial reference frame of the robot is not usually known a priori. Therefore, our work uses an ego-motion-based calibration algorithm to calibrate the extrinsic parameters of the visual-inertial sensor pair. The method was evaluated experimentally in laboratory conditions.