Full Workspace Generation of Serial-link Manipulators by Deep Learning based Jacobian Estimation

Liao, Peiyuan; Mao, Jiajun

doi:10.48550/arxiv.1809.05020

Cited by 2 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Objective of the next scenario set is to analyze the performance of the proposed conjugated visual predictive control scheme and its ability to handle the existing constraints. 4 For this purpose, the same camera as described in previous scenarios is considered to be attached to the 6 DOFs Puma560 (Programmable Universal Manipulator for Assembly) robot and similar to [36,52,71], the Robotics Toolbox in MATLAB [17] is utilized to simulate the described visual servo system. Without loss of generality, it is assumed that the system has eye-in-hand configuration where the camera attached firmly to the robot's end-effector and its frame is coincident with the end-effector frame.…”

Section: Experimental Simulationsmentioning

confidence: 99%

Hybrid Visual Predictive Control for Single and Multi-Agent Systems

Fallah

2024

Preprint

View full text Add to dashboard Cite

<p>Visual servoing (VS) is a technique which utilizes information acquired from a visual sensor to control the motion of a robot. Despite the advantages of the classic VS techniques in controlling of the robots- specifically in unstructured environments- they suffer from some system’s shortcomings such as the lack of an effective mechanism for handling the existing constraints within the control procedure. To alleviate these issues, among the several approaches proposed in the literature, the receding horizon or model predictive control (MPC) technique is an appropriate candidate to be employed by the system. Any combination of the model predictive control and visual servoing is called visual predictive control (VPC) which is categorized as the classic and hybrid methods. The classic VPC schemes are developed based on the classic VS approaches and the hybrid ones employ the hybrid VS schemes to be integrated by MPC. On the other hand, to guarantee the convergence of the system in presence of the noises and uncertainties, the proposed VPC schemes are embedded in internal model control (IMC) framework.</p> <p>This work contributes by utilizing the available VPC scheme in control of different robots, such as 3 DOF catheter as a continuum robot and a 6 DOF manipulator from Denso robotics as a robot arm, and by developing two hybrid predictive controllers, conjugated VPC and depth-based VPC, with higher constraint handling capabilities. By utilizing the proposed VPC methods, some of the available limitations could be resolved in the single-robot control level. In addition, to enable the system to perform more sophisticated tasks under difficult conditions such as unexpected occlusions, a multi-agent system controlled by the mentioned VPC methods is employed. Under these conditions, by utilizing the data sharing ability among neighboring agents inside the network, the obstructed one could be provided with enough information to complete the task. At each stage, the performance of the proposed algorithm is verified through numerous simulations and experiments to show their capability in handling existing constraints while accounting for system uncertainties.</p>

show abstract

Section: Experimental Simulationsmentioning

confidence: 99%

Hybrid Visual Predictive Control for Single and Multi-Agent Systems

Fallah

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The paper states that the computational time is lower than classical methods of workspace generation. The paper [ 22 ] presented a development of the work from [ 21 ], i.e., the generation of the full workspace of serial robots using a deep-learning framework for a given pose.…”

Section: Introductionmentioning

confidence: 99%

Estimation of the Kinematics and Workspace of a Robot Using Artificial Neural Networks

Boantă

Brişan

2022

Sensors

View full text Add to dashboard Cite

At present, in specific and complex industrial operations, robots have to respect certain requirements and criteria as high kinematic or dynamic performance, specific dimensions of the workspace, or limitation of the dimensions of the mobile elements of the robot. In order to respect these criteria, a proper design of the robots has to be achieved, which requires years of practice and a proper knowledge and experience of a human designer. In order to assist the human designer in the process of designing the robots, several methods (including optimization methods) have been developed. The scientific problem addressed in this paper is the development of an artificial intelligence method to estimate the size of the workspace and the kinematics of a robot using a feedforward neural network. The method is applied on a parallel robot composed of a base platform, a mobile platform and six kinematic rotational-universal-spherical open loops. The numerical results show that, with proper training and topology, a feedforward neural network is able to estimate properly values of the volume of the workspace and the values of the generalized coordinates based on the pose of the end effector.

show abstract

Full Workspace Generation of Serial-link Manipulators by Deep Learning based Jacobian Estimation

Cited by 2 publications

References 23 publications

Hybrid Visual Predictive Control for Single and Multi-Agent Systems

Hybrid Visual Predictive Control for Single and Multi-Agent Systems

Estimation of the Kinematics and Workspace of a Robot Using Artificial Neural Networks

Contact Info

Product

Resources

About