Synergetic Control System for Multi-Robot Assembly Based on Multisource Heterrogeneous Information Fusion

Zhu, Dachang; Puchen, Zhu; Li, Zhifu; Tang, Bin; Ma, Ge; Feng, Yan

doi:10.1109/cac.2018.8623183

Cited by 2 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Humans will make relative choices to avoid them according to the corresponding situation. Robots will be helpless in unknown environments, and external factors will lead to sensor failure, resulting in a lack of information from external reconnaissance [9]. So, an algorithm is needed to predict that the robot will make relatively accurate predictions when the sensor fails or is disturbed.…”

Section: Problem Formulationmentioning

confidence: 99%

Analysis of Multi-Robot Patrolling Algorithms

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

This article is dedicated to analyzing the common problems of robots when patrolling indoors and the corresponding solution algorithms. In the article, four problems of patrol robots (whether centralized or non-centralized) during operation are listed: the overload of data to be processed when the robotic sensors are transmitting the data, the repetitiveness and simultaneity of the robot work, the incorrect execution of the algorithm and how to deal with the inevitable unknown external factors. The simultaneity of the robots is to be eliminated because robots need to explore independently in the patrol task. Subsequently, four algorithms and functionalities are introduced (Monte Carlo Tree Planning Algorithm, Rapid Exploring Random Tree Planning, Mutual Exclusion Algorithm, and Kalman Filter Algorithm). The question of how the four algorithms address the corresponding factors will be illustrated by an elaboration of the process by which the algorithms solve the problem.

show abstract

Section: Problem Formulationmentioning

confidence: 99%

Analysis of Multi-Robot Patrolling Algorithms

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

Robot grasping method optimization using improved deep deterministic policy gradient algorithm of deep reinforcement learning

Zhang

Wang

et al. 2021

Review of Scientific Instruments

View full text Add to dashboard Cite

Robot grasping has become a very hot research field so that the requirements for robot operation are getting higher and higher. In previous research studies, the use of traditional target detection algorithms for grasping is often very inefficient, and this article is dedicated to improving the deep reinforcement learning algorithm to improve the grasping efficiency and solve the problem of robots dealing with the impact of unknown disturbances on grasping. Using the characteristic that deep reinforcement learning actively explores the unknown environment, a Gaussian parameter Deep Deterministic Policy Gradient (Gaussian-DDPG) algorithm based on the Importance-Weighted Autoencoder (IWAE) is proposed to realize the robot’s autonomous learning of the grasping task. Traditional coordinate positioning methods and deep learning methods have poor grasping effects for disturbed situations (such as the movement of the target object). The IWAE algorithm is used to compress the high-dimensional information of the original visual input to the hidden space and pass it to the deep reinforcement learning network as part of the state value. Based on the classic DDPG algorithm, it smoothly adds Gaussian parameters to improve the exploratory nature of the algorithm, dynamically sets the robot grasping space parameters to adapt to the workspace of multiple scales, and finally, realizes the accurate grasping of the robot. Relying on the possible position information deviation of the visual information, the control of the grasping position by the manipulator torque information is further optimized to improve the grasping efficiency of disturbed objects.

show abstract

Synergetic Control System for Multi-Robot Assembly Based on Multisource Heterrogeneous Information Fusion

Cited by 2 publications

References 8 publications

Analysis of Multi-Robot Patrolling Algorithms

Analysis of Multi-Robot Patrolling Algorithms

Robot grasping method optimization using improved deep deterministic policy gradient algorithm of deep reinforcement learning

Contact Info

Product

Resources

About