Active Learning of Robot Vision Using Adaptive Path Planning

Robots need robust and flexible vision systems to perceive and reason about their environments beyond geometry. As autonomous robots are commonly deployed in initially unknown environments, pre-training on static datasets cannot always capture the variety of domains and limits the robot’s vision performance during missions. To address these issues, we present an adaptive planning framework for efficient training data collection to substantially reduce human labelling requirements in semantic terrain monitoring missions. We combine high-quality human labels with automatically generated pseudo labels. Experimental results show that the framework reaches segmentation performance close to fully supervised approaches with drastically reduced human labelling effort while outperforming purely self-supervised approaches.