An experimental robot system for power distribution line maintenance robots - System architecture and bolt insertion experiment -

Tsukahara, Kiyoshi; Tanaka, Yorihiko; He, Yingxin; Hori, Ryosuke; Mano, Kunihiro; Hibino, Akihiro; Taru, Yoshikazu; Tatsuno, Kyoichi

doi:10.1109/iros.2008.4650852

Cited by 26 publications

(10 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are assumed to be independent of each other and with normal probability distributions (Gaussian white noise) [4].…”

Section: B Data Fusion Using Kalman Filtermentioning

confidence: 99%

“…A bolt tightening robot for power transmission line is proposed in [2]- [3].A semiautonomous robot system that performs tasks using tasklevel instructions is proposed in [4].These robots are manual remote-controlled, since people are far away from the operating scene, it is difficult for operators to pinpoint the spanner at the bolt, i.e. it is inefficient for these kinds of robots because the instructions from people are not always reliable.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Study of Control Strategy for Bolt Tightening Robot on Power Transmission Lines

Zhong¹,

Fan²,

Li³

et al. 2017

Proceedings of the 2017 International Conference on Electronic Industry and Automation (EIA 2017)

View full text Add to dashboard Cite

Abstract-A new control strategy and its real-time implementation were presented for a power transmission line bolt tightening robot. In order to overcome the influence of the wind, a prediction algorithm of multi-sensor information fusion optimal Kalman filter is adopted to predict the trajectory of the camera. The trajectory of the bolt uses a least squares method based on the interest area. Torque coefficient control method was presented to assure the conformity of the pre-tightening force of different screw threads. Experimental results show that the proposed bolt aligning and tightening strategy can achieve the work timely and have high efficiency.

show abstract

“…They are assumed to be independent of each other and with normal probability distributions (Gaussian white noise) [4].…”

Section: B Data Fusion Using Kalman Filtermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The Study of Control Strategy for Bolt Tightening Robot on Power Transmission Lines

Zhong¹,

Fan²,

Li³

et al. 2017

Proceedings of the 2017 International Conference on Electronic Industry and Automation (EIA 2017)

View full text Add to dashboard Cite

show abstract

“…It is very important for the live working robot in the distribution network to replace the manual live working operation, which has attracted the attention of a large number of researchers [6,7]. Figure 1 shows the self-control flow chart of the live working robot.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Detection of Insulators and Drop Fuses Based on Improved YOLOv4

Yang

Rong

Guo

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

During the power grid system maintenance and overhaul, real-time detection of the insulators and drop fuses is important for the live working robots in the distribution network to plan motion. The visual system of the robot needs object detection algorithms with high detection precision, fast speed, and robustness to image brightness changes. In this paper, the improved YOLOv4 is proposed for detecting the insulators and drop fuses based on the YOLOv4. The improved YOLOv4 extracts features of power components through convolutional neural networks (CNN) and then performs feature fusion. After feature extraction and fusion, the algorithm generates prediction boxes based on anchor boxes that are clustered by fuzzy C-means algorithm (FCM) instead of K-means algorithm to detect the objects. Finally, the nonmaximum suppression algorithm (NMS) is used to obtain the final prediction results. In order to detect small targets, the improved YOLOv4 is added to a larger detection layer. For enhancing the robustness of the algorithm, data augmentation methods are carried out to enrich the data set. Combining the improvements, the test results show that the improved YOLOv4 gets higher accuracy and faster detection speed compared with the other detection algorithms based on deep learning. The mean average precision is 97.0%, and the average detection time is 0.012 s. Therefore, the improved YOLOv4 is suitable for the live working robots in the distribution network to detect the insulators and drop fuses fast and accurately.

show abstract

“…Tsukahara et al used a computer graphics simulator to simulate and verify a semiautomatic distribution line maintenance robot system [12]- [15]. Research on controller framework design and visual algorithms was carried out [16], and semiautomatic bolt insertion tests [17] and nut twist tests [18], [19] were realized in the laboratory. The above studies all aimed to reduce the operation difficulty of the robot system, improve the operation efficiency and reduce the training cost.…”

Section: Introductionmentioning

confidence: 99%

Autonomous Live-Line Maintenance Robot for a 10 kV Overhead Line

Feng

Zhang

2021

IEEE Access

View full text Add to dashboard Cite

Live work is a dangerous and complex operation that endangers the lives of operators. This paper presents an autonomous live-line maintenance robot (ALMR), which is applied to 10 kV overhead lines. The ALMR can complete most of the operations automatically, requiring only a small amount of correction and operation. The paper briefly introduces the overall design of the ALMR. The main part of the paper describes the work carried out to realize automatic operation: (1) Propose a dynamic hierarchical task planning method that can decompose complex operations into a sequence of instructions that the robot can directly execute and can effectively deal with unexpected situations during operation; (2) solve the problem of recognition and positioning of cables under outdoor sunlight interference and complex backgrounds;(3) realize the robot's motion planning in the live-line scene; (4) build a virtual environment to solve the telepresence problem of remote operation. Field experiments show that the ALMR can replace manual operations such as connecting and disconnecting lead-flow lines, and the operating efficiency is close to that of manual operations.

show abstract

An experimental robot system for power distribution line maintenance robots - System architecture and bolt insertion experiment -

Cited by 26 publications

References 1 publication

The Study of Control Strategy for Bolt Tightening Robot on Power Transmission Lines

The Study of Control Strategy for Bolt Tightening Robot on Power Transmission Lines

Real-Time Detection of Insulators and Drop Fuses Based on Improved YOLOv4

Autonomous Live-Line Maintenance Robot for a 10 kV Overhead Line

Contact Info

Product

Resources

About