A geometric method for kinematics of delta robot and its path tracking control

Yang, Xuewen; Feng, Zuren; Liu, Chenyu; Ren, Xiaodong

doi:10.1109/iccas.2014.6988043

Cited by 11 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning has been widely used in many tasks, such as image captioning [35][36][37], image to image translation [38], neural machine translation [39], robotics [40,41], fashion recommendation [42], OCR [43] etc. In this paper, we investigated a brand-new framework for multi-task learning on the spatial-temporal data.…”

Section: Discussionmentioning

confidence: 99%

Tackling Multiple Tasks with One Single Learning Framework

Yang

2022

Preprint

View full text Add to dashboard Buy / Rent full text

Deep Multi-Task Learning (DMTL) has been widely studied in the machine learning community and applied to a broad range of real-world applications. Searching for the optimal knowledge sharing in DMTL is more challenging for sequential learning problems, as the task relationship will change in the temporal dimension. In this paper, we propose a flexible and efficient framework called Hierarchical-Temporal Activation Network (HTAN) to simultaneously explore the optimal sharing of the neural network hierarchy (hierarchical axis) and the time-variant task relationship (temporal axis). HTAN learns a set of time-variant activation functions to encode the task relation. A functional regularization implemented by a modulated SPDNet and adversarial learning is further proposed to enhance the DMTL performance. Comprehensive experiments on several challenging applications demonstrate that our HTAN-SPD framework outperforms SOTA methods significantly in sequential DMTL.* https://catalog.ldc.upenn.edu/LDC2013T19 Preprint. Under review.

show abstract

Section: Discussionmentioning

confidence: 99%

Tackling Multiple Tasks with One Single Learning Framework

Yang

2022

Preprint

View full text Add to dashboard Buy / Rent full text

show abstract

“…Based on the given parameters, this study exercised inverse kinematics (Can et al, 2018; López et al, 2006; Yang et al, 2014) to calculate three motor rotations required to displace the movable platform to target positions (Jian and Lou, 2017; Zhao et al, 2015).…”

Section: Development Of Canopen-based Control System For a Parallel Robot Mechanismmentioning

confidence: 99%

Development of a control architecture for a parallel three-axis robotic arm mechanism using CANopen communication protocol

Lee

Lin

Chen

et al. 2021

Concurrent Engineering

View full text Add to dashboard Buy / Rent full text

Based upon the CANopen communication protocol and the LabVIEW graphic programing procedures, this paper develops a closed-loop control architecture for a parallel three-axis (Delta) robotic arm mechanism. The accomplishments include prototyping a parallel three-axis robotic arm mechanism, assembling servomotors with associated encoders and gearsets, coding CANopen communication scripts for servomotor controllers and a host supervision GUI, coding forward/inverse kinematics scripts to compute the required servomotor rotations and the coordinates of a movable platform or the mechanism, coding tracking error compensation scripts for effective closed-loop griper control, and coding integration scripts to command and supervise the mechanism motion on the LabVIEW-based host GUI. During the development stage, this research designed and prototyped the parallel three-axis robotic arm mechanism based upon basic Delta robot kinematics. To control the mechanism effectively and accurately, this study implemented the CANopen communication protocol, which characterizes high speed and stable transmission. The protocol applies to the CANopen communication channels among the controllers and the host supervision GUI. On the LabVIEW development platform, the coded supervision GUI performs issuing/receiving messages to the CANopen-based controllers. The controllers excite the servomotors and actuate the parallel mechanism to track prescribed trajectories in a closed-loop control fashion. Meanwhile, an electromagnet attached to the movable platform of the robotic mechanism performs satisfactory picking/placing object actions.

show abstract

“…The x A -and z A -axis are located in the base plane with z A -axis parallel to line B 2 B 3 , Whilst y A -axis is perpendicular to the base plane and forms a right-handed coordinate frame. 1) Forward kinematics: The forward kinematics of the Delta manipulator can be solved using a geometrical method [24]. As the base and end-effector always remain in the same orientation, it only allows the end-effector to move in translational motion.…”

Section: B the Delta Manipulatormentioning

confidence: 99%

An Integrated Delta Manipulator for Aerial Repair: A New Aerial Robotic System

Chermprayong

Zhang

Xiao

et al. 2019

IEEE Robot. Automat. Mag.

View full text Add to dashboard Buy / Rent full text

Unmanned Aerial Vehicles (UAVs) are capable of entering hazardous areas and accessing hard-to-reach locations at high altitude. However, small-scale UAVs are inherently unstable when exposed to challenging environments. Additionally, their capability to interact with infrastructure with high accuracy is limited due to the need to stabilize the vehicle precisely in flight. To address these challenges, this article introduces a new aerial robotic system with an integrated light-weight Delta manipulator and a kinematics-based approach allowing it to compensate fluctuations of the quadrotor platform due to wind or flight imprecision. Integrating onboard visual-inertial (VI) odometry-aided navigation, the system is characterised in various operation modes, including hovering in windy conditions. The end-effector accuracy of the integrated aerial robot is analysed and compared to the flight accuracy of the quadrotor platform using a 3D motion capture system for ground truthing. The results reveal that the end-effector of the aerial robot achieves a maximum decrease of the root-mean-square-error (RMSE) of 76.4%, 44.1% and 35.8% in X, Y and Z directions respectively in VI odometry-aided tests with 1 m/s wind along Y direction. In the same tests, the maximum fluctuations decrease by 52.8%, 46.9% and 33.6% in the directions of X, Y and Z. As a demonstration of the utility of this stabilised manipulator, we present the design of an on-board extrusion system that can deposit two component LD40 polyurethane foam for precise spot repairs. We selected the LD40 foam as the amorphous repair material due to its substantial expansion rates after deposition that allows for effective area coverage with little material carried on-board. We then demonstrate a complete aerial repair mission for sealing cracks and holes on a section of a standard oil pipe, by autonomously depositing the two component foam on the damaged areas. This work will enable a number of potential applications, including aerial repair at high altitude where access is difficult for ground vehicles and dangerous for human workers.

show abstract

A geometric method for kinematics of delta robot and its path tracking control

Cited by 11 publications

References 8 publications

Tackling Multiple Tasks with One Single Learning Framework

Tackling Multiple Tasks with One Single Learning Framework

Development of a control architecture for a parallel three-axis robotic arm mechanism using CANopen communication protocol

An Integrated Delta Manipulator for Aerial Repair: A New Aerial Robotic System

Contact Info

Product

Resources

About