Deep reinforcement learning for high precision assembly tasks
The high precision assembly of mechanical parts requires precision that exceeds that of
robots. Conventional part-mating methods used in the current manufacturing require …
robots. Conventional part-mating methods used in the current manufacturing require …
Admittance control for physical human–robot interaction
AQL Keemink, H Van der Kooij… - … International Journal of …, 2018 - journals.sagepub.com
This paper presents an overview of admittance control as a method of physical interaction
control between machines and humans. We present an admittance controller framework and …
control between machines and humans. We present an admittance controller framework and …
Guided policy search
Direct policy search can effectively scale to high-dimensional systems, but complex policies
with hundreds of parameters often present a challenge for such methods, requiring …
with hundreds of parameters often present a challenge for such methods, requiring …
Autonomic robotic ultrasound imaging system based on reinforcement learning
G Ning, X Zhang, H Liao - IEEE transactions on biomedical …, 2021 - ieeexplore.ieee.org
Objective: In this paper, we introduce an autonomous robotic ultrasound (US) imaging
system based on reinforcement learning (RL). The proposed system and framework are …
system based on reinforcement learning (RL). The proposed system and framework are …
A practical approach to insertion with variable socket position using deep reinforcement learning
Insertion is a challenging haptic and visual control problem with significant practical value
for manufacturing. Existing approaches in the model-based robotics community can be …
for manufacturing. Existing approaches in the model-based robotics community can be …
Reinforcement learning control
AG Barto - Current opinion in neurobiology, 1994 - Elsevier
Reinforcement learning refers to improving performance through trial-and-error. Despite
recent progress in developing artificial learning systems, including new learning methods for …
recent progress in developing artificial learning systems, including new learning methods for …
Compare contact model-based control and contact model-free learning: A survey of robotic peg-in-hole assembly strategies
J Xu, Z Hou, Z Liu, H Qiao - arXiv preprint arXiv:1904.05240, 2019 - arxiv.org
In this paper, we present an overview of robotic peg-in-hole assembly and analyze two main
strategies: contact model-based and contact model-free strategies. More specifically, we first …
strategies: contact model-based and contact model-free strategies. More specifically, we first …
A framework for robot manipulation: Skill formalism, meta learning and adaptive control
L Johannsmeier, M Gerchow… - … Conference on Robotics …, 2019 - ieeexplore.ieee.org
In this paper we introduce a novel framework for expressing and learning force-sensitive
robot manipulation skills. It is based on a formalism that extends our previous work on …
robot manipulation skills. It is based on a formalism that extends our previous work on …
Reinforcement learning
AG Barto - Neural systems for control, 1997 - Elsevier
Reinforcement learning refers to ways of improving performance through trial-and-error
experience. Despite recent progress in developing artificial learning systems, including new …
experience. Despite recent progress in developing artificial learning systems, including new …
Deep reinforcement learning for robotic assembly of mixed deformable and rigid objects
J Luo, E Solowjow, C Wen, JA Ojea… - 2018 IEEE/RSJ …, 2018 - ieeexplore.ieee.org
Reinforcement learning for assembly tasks can yield powerful robot control algorithms for
applications that are challenging or even impossible for “conventional” feedback control …
applications that are challenging or even impossible for “conventional” feedback control …