Ken Goldberg at IROS 2021
Several papers co-written by Ken Goldberg were presented at the IEEE Int'l Conference on Robots and Systems (IROS) 2021.
Disentangling Dense Multiple-Cable Knots. Vainavi Viswanath, Jennifer Grannen, Priya Sundaresan, Brijen Thananjeyan, Ashwin Balakrishna, Ellen Novoseller, Jeffrey Ichnowski, Michael Laskey, Joseph E. Gonzalez, Ken Goldberg. IEEE/RSJ International Conference on Robots and Systems (IROS), Prague, Sept 2021 [paper]
Disentangling two or more cables requires many steps to remove crossings between and within cables. We formalize the problem of multiple cable disentangling and present an iterative, graph-based algorithm, Iterative Reduction Of Non-planar Multiple cAble kNots (IRON-MAN), that outputs moves to remove crossings from the scene. We instantiate it with a learned perception system, inspired by prior work in single-cable untying, to disentangle two cable twists, three cable braids, and knots of two or three cables, such as the overhand, square, carrick bend, sheet bend, crown, and fisherman’s knots from image input. IRON-MAN keeps track of task-relevant keypoints corresponding to target cable endpoints and crossings and iteratively disentangles the cables by identifying crossings that are critical to knot structure and undoing them. Using a da Vinci surgical robot, we experimentally evaluate the effectiveness of IRON-MAN on the task of untangling a class of multiple cable knots present in the training data, as well as generalizing to novel classes of multiple cable knots involving two to three cables. Results suggest that IRON-MAN is effective in disentangling knots involving up to three cables with 80.5% success, with generalization to knots that are never seen during training on cables that are either distinct or uniform in color.
A Multi-Chamber Smart Suction Cup for Adaptive Gripping and Haptic Exploration. Tae Myung Huh, Kate Sanders, Michael Danielczuk, Monica Li, Ken Goldberg, Hannah S. Stuart. IEEE/RSJ International Conference on Robots and Systems (IROS), Prague, Sept 2021] [paper]
We present a novel robot end-effector for gripping and haptic exploration. Tactile sensing through suction flow monitoring is applied to a new suction cup design that contains multiple chambers for air flow. Each chamber connects with its own remote pressure transducer, which enables both absolute and differential pressure measures between chambers. By changing the overall vacuum applied to this smart suction cup, it can perform different functions such as gentle haptic exploration (low pressure) and monitoring breaks in the seal during strong astrictive gripping (high pressure). Haptic exploration of surfaces through sliding and palpation can guide the selection of suction grasp locations and help to identify the local surface geometry. During suction gripping, this design localizes breaks in the suction seal between four quadrants with up to 97% accuracy and detects breaks in the suction seal early enough to avoid total grasp failure.
Mechanical Search on Shelves using Lateral Access X-RAY. Huang Huang*, Marcus Dominguez-Kuhne, Jeff Ichnowski, Vishal Satish, Mike Danielczuk, Kate Sanders, Andrew Lee, Anelia Angelova, Vincent Vanhoucke, Ken Goldberg. IEEE/RSJ International Conference on Robots and Systems (IROS), Prague, Sept 2021 [paper] [website]
Efficiently finding an occluded object in a lateral access environment such as a shelf or cabinet arises in many contexts such as warehouses, retail, healthcare, shipping, and homes. While this mechanical search problem has commonly been studied in the overhead access environment, the lateral access setting introduces novel constraints both on the poses of the objects and on available grasp actions that can render pushing actions more efficient in this setting. We propose LAXRAY (Lateral Access maXimal Reduction in support Area of occupancY distribution): a system that combines a target object occupancy distribution predictions with a mechanical search policy that sequentially pushes occluding objects to efficiently reveal the target. For scenarios with extruded polygonal objects occluding a known stationary target, we introduce two lateral access search policies that encode a history of predicted target distributions and can plan up to three actions into the future. We evaluate these policies both in 200 random shelf environments per policy using a novel First-Order Shelf Simulator (FOSS) and in 5 physical shelf environments using a Fetch robot with an embedded PrimeSense RGBD Camera and an attached blade, where they outperform baselines by up to 25% and up to 60% in physical experiments as the number of occluding objects increases. Additionally, the two-step prediction policy is the highest performing in simulation with an 87.3% average success rate, suggesting a tradeoff between future information and prediction errors. Code, videos, and supplementary material can be found at https://sites.google.com/berkeley. edu/lax-ray.
For more information on each paper, please visit the google doc here!