Residual learning from demonstration: Adapting dmps for contact-rich manipulation
Manipulation skills involving contact and friction are inherent to many robotics tasks. Using
the class of motor primitives for peg-in-hole like insertions, we study how robots can learn …
the class of motor primitives for peg-in-hole like insertions, we study how robots can learn …
Online reinforcement learning for a continuous space system with experimental validation
Reinforcement learning (RL) for continuous state/action space systems has remained a
challenge for nonlinear multivariate dynamical systems even at a simulation level …
challenge for nonlinear multivariate dynamical systems even at a simulation level …
Insertionnet-a scalable solution for insertion
O Spector, D Di Castro - IEEE Robotics and Automation Letters, 2021 - ieeexplore.ieee.org
Complicated assembly processes can be described as a sequence of two main activities:
grasping and insertion. While general grasping solutions are common in industry, insertion …
grasping and insertion. While general grasping solutions are common in industry, insertion …
[HTML][HTML] Actor–critic reinforcement learning and application in developing computer-vision-based interface tracking
This paper synchronizes control theory with computer vision by formalizing object tracking
as a sequential decision-making process. A reinforcement learning (RL) agent successfully …
as a sequential decision-making process. A reinforcement learning (RL) agent successfully …
Parareal with a learned coarse model for robotic manipulation
A key component of many robotics model-based planning and control algorithms is physics
predictions, that is, forecasting a sequence of states given an initial state and a sequence of …
predictions, that is, forecasting a sequence of states given an initial state and a sequence of …
[Retracted] Simulation Design of a Live Working Manipulator for Patrol Inspection in Power Grid
T Xie, Z Li, Y Zhang, B Yuan, X Liu - Journal of Robotics, 2022 - Wiley Online Library
The distribution line network is the electric power infrastructure directly facing the users, with
the characteristics of large coverage and complex network, and its operation safety is …
the characteristics of large coverage and complex network, and its operation safety is …
Review on Peg-in-Hole Insertion Technology Based on Reinforcement Learning
L Shen, J Su, X Zhang - 2023 China Automation Congress …, 2023 - ieeexplore.ieee.org
Peg-in-hole insertion is a critical process in industrial production. Traditional peg-in-hole
insertion methods are based on planning the robot's motion trajectory through the analysis …
insertion methods are based on planning the robot's motion trajectory through the analysis …
Reinforcement Learning-based Process Control Under Sensory Uncertainty
O Dogru - 2023 - era.library.ualberta.ca
Process industries involve processes that have complex, interdependent, and sometimes
uncontrollable/unobservable features that are subject to a variety of uncertainties such as …
uncontrollable/unobservable features that are subject to a variety of uncertainties such as …
Mutual Deep Deterministic Policy Gradient Learning
Z Sun - 2022 International Conference on Big Data, Information …, 2022 - ieeexplore.ieee.org
In deep reinforcement learning (DRL), policy gradient (PG) and actor-critic (AC) based
methods are among the most populous and effective methods for training DRL agents. One …
methods are among the most populous and effective methods for training DRL agents. One …
Robust physics-based robotic manipulation in real-time
WC Agboh - 2021 - etheses.whiterose.ac.uk
This thesis presents planners and controllers for robust physics-based manipulation in real-
time. By physics-based manipulation, I refer to manipulation tasks where a physics model is …
time. By physics-based manipulation, I refer to manipulation tasks where a physics model is …