Rigid-Soft Interactive Learning for Robust Grasping
نویسندگان
چکیده
منابع مشابه
Robust Interactive Learning
In this paper we propose and study a generalization of the standard active-learning model where a more general type of query, class conditional query, is allowed. Such queries have been quite useful in applications, but have been lacking theoretical understanding. In this work, we characterize the power of such queries under two well-known noise models. We give nearly tight upper and lower boun...
متن کاملA General Framework for Robust Interactive Learning
We propose a general framework for interactively learning models, such as (binary or nonbinary) classifiers, orderings/rankings of items, or clusterings of data points. Our framework is based on a generalization of Angluin’s equivalence query model and Littlestone’s online learning model: in each iteration, the algorithm proposes a model, and the user either accepts it or reveals a specific mis...
متن کاملSoft Hands for Reliable Grasping Strategies
Recent insights into human grasping show that humans exploit constraints to reduce uncertainty and reject disturbances during grasping. We propose to transfer this principle to robots and build robust and reliable grasping strategies from interactions with environmental constraints. To make implementation easy, hand hardware has to provide compliance, low inertia, low reaction delays and robust...
متن کاملForce Control for Grasping Soft Tissue
Tissue grasping is a crucial component of surgical procedures that involves simultaneously satisfying two competing criteria – maintaining grasp stability while avoiding damage due to excessive grip force. Automation of grasp force control thus requires a controller to apply grasping forces just sufficient to maintain grasp stability. This task is complicated by the serially connected dynamics ...
متن کاملRelatively robust grasping
In this paper, we present an approach for robustly grasping objects under positional uncertainty. We maintain a belief state (a probability distribution over world states), model the problem as a partially observable Markov decision process (POMDP), and select actions with a receding horizon using forward search through the belief space. Our actions are world-relative trajectories, or fixed tra...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Robotics and Automation Letters
سال: 2020
ISSN: 2377-3766,2377-3774
DOI: 10.1109/lra.2020.2969932