An Robotic Arm System for Automatic Welding of Bars Based on Image Denoising

Ma, Shuhua; Tang, Tiang; You, Hairong; Zhao, Y. B.; Ma, Xianchun; Wang, Jinhua

doi:10.1109/icrcv52986.2021.9546976

Cited by 1 publication

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Software processing involves the development and implementation of algorithms for real-time decisionmaking and control. In line with this, a study on an automatic welding robotic arm system based on image de-noising explored the optimization of vision modules in robotic systems for improved accuracy and efficiency in complex environments [13]. There are two submodules in this particular segment; one is to detect cracks within the provided video media, and the other is the Reinforcement Learning (RL) agent, as depicted in Figure 4.…”

Section: Software Processing Segmentmentioning

confidence: 99%

“…The kinematic chain is typically defined using transformation matrices that express the relationship between the joints. For each joint, a transformation matrix is constructed [13] that describes the position and orientation of that joint relative to the previous one, ultimately leading to a cumulative transformation matrix that describes the position and orientation of the torch in space. As detailed in Table 1, the lengths vary considerably, with the shortest link being 6.12 cm and the longest extending to 31.73 cm.…”

Section: Kinematic Chain and Transformation Matricesmentioning

confidence: 99%

See 1 more Smart Citation

MIG-Assisted Kernel-enabled Robot (MAKER) Arm for Seamless Automobile Maintenance and Service

Wang,

Korlam,

Reddy

et al. 2023

Int. J. Robot. Autom. Technol.

View full text Add to dashboard Cite

There is a definitive increase of excellence in the field of robotic automation, with automated vehicles that can drive people anywhere to automated robots that can perform high-risk surgeries remotely. Robotic automation was initiated as an industrial-grade asset capable of performing complex tasks and replacing humans limited by fatigue. With the advent and rise of Industry Revolution 4.0 (IR 4.0), in the modern world, one of the major markets that IR 4.0 occupies is the automobile industry. The automobile industry heavily employs robotic technology for vehicle manufacturing and assembly, yet post-sale servicing and maintenance remain predominantly manual. This discrepancy results in a gap in the efficient and timely maintenance of vehicles once they’re in the hands of customers. According to a report of Allied Market Research [1], the expected Compound Annual Growth Rate (CAGR) of the global automobile repair and service market from 2022 - 2031 is expected at 7.6%, corresponding to 1,656.21 billion US dollars by 2031. This establishes the scale of the market that the proposed solution is going to be primarily based on. This paper proposes a MIG-based solution for providing welding service to damaged and sheared automobiles, thus reducing the stated discrepancy. The proposed solution creates a kernel environment where the twin-headed robotic arm can assess its surroundings and perform appropriate action from its operation pool using Reinforcement Learning and Machine Learning. The twin-headed robotic arm holds a torch and lead (Al) on the heads to perform the desired operations. This innovative approach is equipped with advanced sensors and programming to accurately detect, diagnose, and service vehicles by leveraging On Board Diagnostic (OBD) systems. This study delves into the theoretical and technical complexities of building an automated welder that explores the practical application of robotic technology in the automobile aftermarket. Notably, this technology promises improved accuracy, consistency, and timeliness in car maintenance, significantly reducing human error, improving service times, increasing productivity, and inducing economic growth.

show abstract

Section: Software Processing Segmentmentioning

confidence: 99%

Section: Kinematic Chain and Transformation Matricesmentioning

confidence: 99%