Ken Goldberg at CoRL
BCNM professor Ken Goldberg's research was recently featured at the 2020 Conference on Robot Learning (CoRL). Two of Golberg's papers were presented: "Untangling Dense Knots by Learning Task-Relevant Keypoints" and "Exploratory Grasping: Asymptotically Optimal Algorithms for Grasping Challenging Polyhedral Objects".
From the "Untangling Dense Knots by Learning Task-Relevant Keypoints" abstract:
Untangling ropes, wires, and cables is a challenging task for robots due to the high-dimensional configuration space, visual homogeneity, self-occlusions, and complex dynamics. We consider dense (tight) knots that lack space between self-intersections and present an iterative approach that uses learned geometric structure in configurations. We instantiate this into an algorithm, HULK: Hierarchical Untangling from Learned Keypoints, which combines learning-based perception with a geometric planner into a policy that guides a bilateral robot to untangle knots.
Read the rest of the abstract and more about the paper here! Check out this video for more information as well:
From the "Exploratory Grasping: Asymptotically Optimal Algorithms for Grasping Challenging Polyhedral Objects" abstract:
There has been significant recent work on data-driven algorithms for learning general-purpose grasping policies. However, these policies can consistently fail to grasp challenging objects which are significantly out of the distribution of objects in the training data or which have very few high quality grasps. Motivated by such objects, we propose a novel problem setting, Exploratory Grasping, for efficiently discovering reliable grasps on an unknown polyhedral object via sequential grasping, releasing, and toppling.
Read the rest of the abstract and more about this paper here! You can also check out the video for this paper as well: