The same way humans have eyes 👀, Ascento has on-board cameras 📷 (marked in red) to perceive its environment. Two global shutter cameras are used for localisation. A depth sensor is used to create a 3D reconstruction of our environment and parametrise objects. For example, when the robot is standing in front of a step it wishes to overcome, it can get all the parameters such as height and depth to make an “optimal” jump.
All cameras are compactly installed in a modular “vision block”. The information gathered from the vision block, together with wheel odometry, enables Ascento to operate completely autonomously while building a map and at the same time localizing itself in that map.