Science Daily  July 11, 2023 Autonomous lander missions on extraterrestrial bodies will need to sample granular material while coping with domain shift, no matter how well a sampling strategy is tuned on Earth. Researchers at the University of Illinois proposed an adaptive scooping strategy that uses deep Gaussian process method trained with meta-learning to learn on-line from very limited experience on the target terrains. Deep Meta-Learning with Controlled Deployment Gaps (CoDeGa) explicitly trained the deep kernel to predict scooping volume robustly under large domain shifts. Employed in a Bayesian Optimization sequential decision-making framework, the proposed method allowed the robot to […]