Autonomous live working robot navigation with real‐time detection and motion planning system on distribution line

Abstract

In this study, an autonomous robot navigation system is designed for live working on distribution line. The developed system features a real‐time detection and motion planning system, incorporating a manipulator capable of grasping power components. In order to accurately identify targets, the authors propose an object detection method based on the Larger Scale ‘You Only Look Once’ Version 4 (LS‐YOLOv4) algorithm for detecting the insulators and drop fuses. The LS‐YOLOv4 extracts features of power components by Convolutional Neural Network (CNN), and then performs feature fusion. Then the authors develop a motion planning method based on the Node Control Optimal Rapidly Exploring Random Trees (NC‐RRT*), which can drive the robot to realise the autonomous robot motion planning and obstacle avoidance. On the grasping function, the authors present a reliable Lightweight‐based Convolutional Neural Network (L‐CNN) grasping point detection method. Finally, the authors evaluate fully autonomous robotic system in both simulated and real‐world experiments. The experimental results demonstrate that the proposed system can effectively identify the target and complete the grasping task in an efficient way. Notably, the proposed motion planning method can take into account both planning efficiency and accuracy to manipulation tasks.

TCU-Net: Transformer and Convolutional Neural Network-Based Advanced U-Net for Concealed Object Detection

“…In particular, YOLO [25,26] has shown excellent and effective performance in bounding box-based object detection. For this reason, some studies were conducted to detect situation elements in obscure overlapping scenes [27] and support autonomous live working robot navigation using YOLO [28]. Also, other CNN-based studies were proposed for automatic target detection in infrared imagery using dual-domain feature extraction and allocation [29] and multi-player tracking with deep identification in sport video [30].…”

Benchmarking edge computing devices for grape bunches and trunks detection using accelerated object detection single shot multibox deep learning models

“…SSD and YOLO are both single-shot architectures, i.e., they only process the image once using feature maps, repositioning the object bounding boxes, and making their classification. Some authors have been exploring single-shot architectures to detect fruits and other objects in open-field environments [2,10,11,12,13,14]. Inside this group of architectures, YOLO models are undoubtedly the most common deep neural network [2,10,11,12].…”

“…Some authors have been exploring single-shot architectures to detect fruits and other objects in open-field environments [2,10,11,12,13,14]. Inside this group of architectures, YOLO models are undoubtedly the most common deep neural network [2,10,11,12]. Because, They are fast and can achieve near real-time speed easily under regular computing hardware [11], without big degradation of the metric when compared with other equivalent ANNs Magalhães et al [2].…”

“…Inside this group of architectures, YOLO models are undoubtedly the most common deep neural network [2,10,11,12]. Because, They are fast and can achieve near real-time speed easily under regular computing hardware [11], without big degradation of the metric when compared with other equivalent ANNs Magalhães et al [2]. However, they may have difficulty detecting some objects, which can be resolved by bigger and more capable CNN architecture.…”

PG-YOLO: A Novel Lightweight Object Detection Method for Edge Devices in Industrial Internet of Things

“…YOLOv4 has made a lot of improvements based on the previous single-stage algorithm, absorbing many excellent ideas, such as data augmentation, CSP structure, etc. The related algorithms also have a large number of applications in the industry [19,20]. And then YOLOv4 introduced YOLOv4-tiny optimized for edge-side devices has greatly improved the real-time performance of the model, but there is still room for optimization.…”