5 papers · 1 filter
Self-supervised Learning Of Visual Pose Estimation Without Pose Labels By Classifying LED States
Nicholas Carlotti, Mirko Nava, Alessandro Giusti
We introduce a model for monocular RGB relative pose estimation of a ground robot that trains from scratch without pose labels nor prior knowledge about the robot's shape or appear…
Multi-LED Classification as Pretext For Robot Heading Estimation
Nicholas Carlotti, Mirko Nava, Alessandro Giusti
We propose a self-supervised approach for visual robot detection and heading estimation by learning to estimate the states (OFF or ON) of four independent robot-mounted LEDs. Exper…
Visual Servoing with Geometrically Interpretable Neural Perception
Antonio Paolillo, Mirko Nava, Dario Piga +1
An increasing number of nonspecialist robotic users demand easy-to-use machines. In the context of visual servoing, the removal of explicit image processing is becoming a trend, al…
Uncertainty-Aware Self-Supervised Learning of Spatial Perception Tasks
Mirko Nava, Antonio Paolillo, Jérôme Guzzi +2
We propose a general self-supervised learning approach for spatial perception tasks, such as estimating the pose of an object relative to the robot, from onboard sensor readings. T…
Learning Long-Range Perception Using Self-Supervision from Short-Range Sensors and Odometry
Mirko Nava, Jerome Guzzi, R. Omar Chavez-Garcia +2
We introduce a general self-supervised approach to predict the future outputs of a short-range sensor (such as a proximity sensor) given the current outputs of a long-range sensor…