Robot skill acquisition in assembly process using deep reinforcement learning

F Li, Q Jiang, S Zhang, M Wei, R Song - Neurocomputing, 2019 - Elsevier
Uncertain factors in environments restrict the intelligence level of industrial robots. Based on
deep reinforcement learning, a skill-acquisition method is used to solve the posed problems …

A computationally efficient optimization approach for battery systems in islanded microgrid

A Das, Z Ni - IEEE Transactions on Smart Grid, 2017 - ieeexplore.ieee.org
In islanded microgrids, it is a challenge to optimize battery energy storage systems (BESSs)
with other power supply units (eg, renewable energy and traditional power generator) and …

An improved dueling deep double-q network based on prioritized experience replay for path planning of unmanned surface vehicles

Z Zhu, C Hu, C Zhu, Y Zhu, Y Sheng - Journal of Marine Science and …, 2021 - mdpi.com
Unmanned Surface Vehicle (USV) has a broad application prospect and autonomous path
planning as its crucial technology has developed into a hot research direction in the field of …

Action-Dependent Heuristic Dynamic Programming With Experience Replay for Wastewater Treatment Processes

J Qiao, M Zhao, D Wang, M Li - IEEE Transactions on Industrial …, 2024 - ieeexplore.ieee.org
The wastewater treatment process (WWTP) is beneficial for maintaining sufficient water
resources and recycling wastewater. A crucial link of WWTP is to ensure that the dissolved …

Skill learning for robotic assembly based on visual perspectives and force sensing

R Song, F Li, W Quan, X Yang, J Zhao - Robotics and Autonomous Systems, 2021 - Elsevier
An environment cannot be effectively described with a single perception form in skill
learning for robotic assembly. The visual perception may provide the object's apparent …

Prioritizing useful experience replay for heuristic dynamic programming-based learning systems

Z Ni, N Malla, X Zhong - IEEE Transactions on Cybernetics, 2018 - ieeexplore.ieee.org
The adaptive dynamic programming controller usually needs a long training period because
the data usage efficiency is relatively low by discarding the samples once used. Prioritized …

Online event-triggered optimal control for multi-agent systems using simplified ADP and experience replay technique

Y Xu, T Li, W Bai, Q Shan, L Yuan, Y Wu - Nonlinear Dynamics, 2021 - Springer
This paper studies an optimal control problem for multi-agent systems under adaptive
dynamic programming (ADP) framework. To overcome the restrictions resulting from the …

Optimal control for earth pressure balance of shield machine based on action-dependent heuristic dynamic programming

X Liu, S Xu, Y Huang - ISA transactions, 2019 - Elsevier
Earth pressure balance (EPB) shield has been widely used in underground construction.
The excavation face stability is crucial to avoid the accidents caused by EPB shield …

Event-driven-modular adaptive backstepping optimal control for strict-feedback systems through zero-sum differential games

Y Ji, H Zhou, B Bai - IEEE Access, 2020 - ieeexplore.ieee.org
This paper addresses the event-driven-modular optimal tracking control problem for
nonlinear strict-feedback systems with external disturbances. Through the backstepping …

Generative models for learning robot manipulation skills from humans

AK Tanwani - 2018 - infoscience.epfl.ch
A long standing goal in artificial intelligence is to make robots seamlessly interact with
humans in performing everyday manipulation skills. Learning from demonstrations or …