Reinforcement Learning of Shared Control Policies for Dexterous Telemanipulation
نویسندگان
چکیده
منابع مشابه
Feedback strategies for shared control in dexterous telemanipulation
– Shared control represents a middle ground between supervisory control and traditional bilateral control in which the remote system can exert control over some aspects of the task while the human operator maintains access to low-level forces and motions. Our telema-nipulation system includes tactile, force and motion sensors that allow the slave to regulate grasp forces and impart rolling moti...
متن کاملLearning Preconditions for Control Policies in Reinforcement Learning
This paper describes a method which senses changing environment by collecting failed instances, uses concept learning for acquiring a precondition for a control policy, and modifies the policy partially in reinforcement learning. The precondition of a policy represents the condition for reaching goals using the policy. Our method learns the precondition of a policy from the instances of policy ...
متن کاملRobust dexterous telemanipulation following object-orientation commands
Purpose This paper presents a procedure to change the orientation of a grasped object using dexterous manipulation. The manipulation is controlled by teleoperation in a very simple way with the commands introduced by an operator using a keyboard. Design/methodology/approach The paper shows a teleoperation scheme, hand kinematics and a manipulation strategy to manipulate different objects using ...
متن کاملImitative Policies for Reinforcement Learning
We discuss a reinforcement learning framework where learners observe experts interacting with the environment. Our approach is to construct from these observations exploratory policies which favor selection of actions the expert has taken. This imitation strategy can be applied at any stage of learning, and requires neither that information regarding reinforcement be conveyed from the expert to...
متن کاملDeep Reinforcement Learning for Dexterous Manipulation with Concept Networks
Deep reinforcement learning yields great results for a large array of problems, but models are generally retrained anew for each new problem to be solved. Prior learning and knowledge are difficult to incorporate when training new models, requiring increasingly longer training as problems become more complex. This is especially problematic for problems with sparse rewards. We provide a solution...
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: Transactions of the Institute of Systems, Control and Information Engineers
سال: 2016
ISSN: 1342-5668,2185-811X
DOI: 10.5687/iscie.29.346