Search

Addressing the issues of slow speed and poor performance in multi-object grasping detection in unstructured environments, a method of performing object detection before grasping detection is pro- posed. In object detection, to accelerate the network's running speed, this paper improved the YOLOv5 network by employing depth wise separable convolutions and coordinate attention mechanisms. For the grasping task.a single-stage grasping pose detection algorithm was designed. Firstly, considering the in- terference present in unstructured environments, RGB-D images were selected as the input data for the grasping network, and GG-CNN was chosen as the backbone network. Secondly, to enhance the feature extraction capabilities of the grasping network, the parallel use of different size convolutional kernels in the Inception-ResNet module was utilized to broaden the network's receptive field. Additionally, the inte gration of a parameter-free three-dimensional attention mechanism enabled the network to focus more on grasping information features and suppress background noise. Finally, a grasping quality evaluation was employed to refine the grasping boxes, and the grasping box with the highest confidence score was out- put. The experimental results indicate that the improved object detection network has a parameter count of 2 776 708 and achieves 102 frames per second (FPS). On the public Cornell dataset, the improved grasping detection network achieves an accuracy of 96. 57% with a FPS of 54, 17. The combination of the two improved networks can be deployed on robotic arms and effectively accomplish grasping tasks in multi-object scenarios, making them suitable for practical industrial applications. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

A multi-modal deep neural network grasping detection network was proposed to address the issue of low accuracy in robot grasping detection tasks for unknown objects. Firstly, residual modules were introduced in both RGB and depth channels to further enhance the feature extraction capability of the network. Secondly, a multimodal feature fusion module was introduced for feature fusion. Finally, the best grasping detection result was obtained by fusing features through fully connected layer regression. The experimental results demonstrate that the algorithm proposed achieves a precision rate of 95. 7% for grasping and 94. 6% for object segmentation on the Cornell dataset. In addition, it has been demonstrated through ablation experiments that introducing residual modules can improve the performance of network crawling detection. [ABSTRACT FROM AUTHOR]

This paper proposed a particle swarm algorithm based on pyramid layer topology to optimize energy consumption trajectories of industrial robots. The algorithm introduced a pyramid layer topology to sort and stratify the particles thus improving the competitive strategy of the algorithm and increasing the population diversity. The algorithm introduced a new cooperation strategy to update the speed and position of the particles. It introduced a victory percentage to adaptively adjust the weight coefficients of the particle swarm algorithm and improved the search efficiency of the particles. In order to verify the effectiveness of the algorithm, this paper tested it on the set of test functions and compared it with other eight variants of particle swarm algorithms. The results show that the performance of the proposed algorithm has significant advantages. Finally, it applied the algorithm to industrial robot trajectory planning. Simulation experiments show that the algorithm can effectively solve the optimal trajectory of the robot's energy consumption, and the energy consumption of the robot is significantly reduced, which meets the kinematics and dynamics constraints of industrial robots. [ABSTRACT FROM AUTHOR]

For traditional machine learning algorithms, visual recognition algorithms have low recognition accuracy and slow running time. This research studies the scene of the robot doing housework in the family scene, and uses the RGB image information as input to complete the grasping pose estimation of the target object. Based on the object detection model YOLOv5s, the network architecture is built by combining data enhancement and transfer learning with its advantages of lightweight and fast speed. After building a family scene data set to enhance the data of a small number of training samples, the model is trained on the target data set using transfer learning, and the parameters are fine-tuned at the same time. The positioning information of the target object is transformed into the grasping pose of the robotic arm through coordinate transformation, and the robotic arm is controlled to finally complete the grasping task with a fixed grasping posture. Finally, the effectiveness of the algorithm is verified by building an experimental platform and manipulating the UR5 robotic arm to carry out actual grasping experiments. The proposed method based on target detection is fast, has high real-time performance, and has a false/missed recognition rate of less than 2%. The application in the robotic arm can efficiently complete the task.

Copyright of Journal of Xinyang Normal University Natural Science Edition is the property of Journal of Xinyang Normal University Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Fly Ash Comprehensive Utilization is the property of Hebei Fly Ash Comprehensive Utilization Magazine Co., Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

As the key equipment of data acquisition in oil and gas exploration, the node can be replaced by a mechanical arm because of its long-term continuous work and high efficiency, but the structure rigidity is weak and the motion ability is poor, so the structure optimization and lightweight design are carried out to improve the structure rigidity and motion ability. Based on the screw theory, the forward kinematics equation of the manipulator with node placement is established, the global static stiffness index and the global velocity index considering the direction of the task are proposed, and the mathematical model of the size optimization of the node-placing manipulator is established. Based on the multi-objective particle swarm algorithm and the variable density method, the size optimization and lightweight design of the node-distributed manipulator arm are carried out. The results show that the overall static stiffness index and the overall velocity performance in the mission direction are improved by 19.8% and 8.8% respectively, and the lightweight design of the upper arm reduces the mass by 14.7%, which is beneficial to improve the response speed of the movement ability. The research results are of great significance for improving the accuracy and efficiency of oil and gas exploration.

For the problem that the RRT (rapidly-exploring random tree) path planning algorithm generates a huge number of nodes when planning the obstacle avoidance path of robotic arm in high-dimensional space, resulting in a large burden of algorithm operation, poor obstacle avoidance performance, and easy to fall into local extremes, an improved RRT algorithm combining A* judgment function is proposed. The sampling method of RRT is changed to generate a sequence of multiple randomly sampled points each time, and the improved A* judgment function is used for sorting. Distance judgment is performed on each generated node to prevent it from falling into local search. Finally, a repetitive greedy strategy is used to remove redundant nodes, and cubic B-spline is used to make path smooth. The performance of the algorithm is analyzed in 2D and 3D maps and robot arm simulations and prototype experiments. The improved RRT algorithm can effectively reduce the number of nodes for the robotic arm to reach the target poses, alleviate the local extremes, and avoid obstacles to reach the target poses quickly and stably, which proves the effectiveness and superiority of the improved RRT algorithm. [ABSTRACT FROM AUTHOR]

In order to reduce the weight of the metal robot, the big arm of the 6-DOF robot is taken as the research object, and combined the forming process of the three-dimensional braided carbon fiber composite material, a lightweight design method of the manipulator based on the CFRP/QT (carbon fiber reinforced polymer/castiron QT 500-7) hybrid structure is proposed to design the structure of the manipulator. Through the static analysis of the hybrid structure manipulator by the finite element analysis method, the final scheme of the hybrid structure of the mechanical arm is obtained under the requirements of strength and stiffness. At the same time, the dynamic simulation results show that the robot equipped with a 24% weight reduction hybrid structure manipulator has good motion performance, and the driving torque of the hybrid structure manipulator robot at the J1 joint after weight reduction is smaller. [ABSTRACT FROM AUTHOR]

Motion characteristics of the robotic arm can dominate the performance of mango harvesting vehicles during picking. In this study, the kinematics analysis was carried out using the multi-body dynamics theory. An initiative was first undertaken to conceptualize and engineer a mango harvesting vehicle. The higher efficiency and labor-saving harvesting was achieved within tropical agricultural regions, compared with the manual. The equipment was designed with walking, lifting, and harvesting functions that were tailored to the Hainan mango planting environment, growth and harvesting agronomy. The core components of the vehicle included a hexapod bionic walking device, a robotic arm, and an end-effector. However, the harvested mangoes were of a modest size within the available operational range, resulting in a low load on the harvesting vehicle. The kinematics model of the robotic arm was established using the Denavit-Hartenberg (D-H), according to the growth of mangoes, the geometric and vector configuration of the robotic arm. The variable separation was employed to conduct the inverse kinematics on the joint variables of the robotic arm. The end-effector motion space planning was also conducted to systematically clarify the motion. The trajectory planning showed that the stability of end-effector motion fully met the motion requirements of the robotic arm during picking. The dynamic model of the robotic arm was constructed by the Lagrangian method. The forward and inverse dynamics simulation was carried out on the joint motion of the robotic arm under constant torque and only periodic swing using Adams software. The dynamic analysis showed that there was a certain periodicity movement under the constant torque in the telescopic and swing devices. The peak of the stage reached about 1.25, 2.3, and 4.15 s. In the case of only oscillating periodic motion, the driving torques of the rotating and oscillating device were approximately cyclically changed, with the peak values of 72.5, and 52 N·mm, respectively, indicating two maximum values in one motion cycle. A vibration analysis was also performed to determine the dynamic performance of the robotic arm. The feasibility of the multi-body dynamics model was verified using linear modal calculations and experiments. A vibration element was then created at the bottom of the robotic arm, in order to explore the effect of the bottom vibration excitation on the motion of the end-effector. The frequency response curve showed that the end-effector was subject to the greatest vibration in the y-direction during the operation of the robotic arm, leading to the overall vibration. Moreover, there was a relatively gentle amplitude in the y-direction between 0-10 Hz. Parametric calculations were then performed, where the y direction of the end-effector was defined as the target for optimization. The maximum response value of the robotic arm was 0.1665, indicating the minimal vibration to fully meet the specified smooth operation. In conclusion, the mango harvesting vehicle can be an effective solution to the challenges posed by manual mango picking in tropical agricultural areas. The trajectory planning shared the efficient and precise movement of the end-effector, meeting the requirements of mango harvesting. The multi-body dynamics model of the mango-picking robotic arm was verified by experiments. The findings can provide a strong reference for the picking performance of the robot arm for its high reliability and stability. [ABSTRACT FROM AUTHOR]

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Objective:To improve the defect detection efficiency of the enclosure structure of food storage devices. Methods: A robotic arm inspection trolley based on host computer control was proposed. The acquisition path was planned according to the area of the enclosure structure. The improved Ostu image segmentation method was used to analyze the acquired thermal infrared images and output the "defect" parts. Size and position coordinates, and finally verify the effectiveness of the detection through the defect detection rate and false detection rate. Results: The detection mechanism can completely scan and collect thermal infrared images of the enclosure structure of food storage and transportation devices. The image segmentation method can clearly describe the size of the heat source. The detection rate and false detection rate of "defects" were 92% and 6.6%, respectively. Conclusion: The detection mechanism can completely scan and collect the thermal infrared image of the food storage room envelope, and the image segmentation method can clearly describe the size of the heat source, which meets the practical application requirements of mechanical vision detection.

To improve the robotic arm system’s ability of perceiving the environment, a multi-station precise alignment technique of robotic arms guided by far-near-sight vision system is proposed. First, a configuration is built with one far-sight camera and one near-sight camera, and an eye-in-hand robotic arm is built up. Second, intrinsic and extrinsic parameters of the vision system and the transformation relationship between the vision system and the robotic arm are calibrated and a task table is established by a local priori alignment method. Third, a three-stage alignment strategy is proposed, i.e., the acquisition of the starting pose of the multi-station operation, the initial positioning of the global camera, and the fine alignment of the local camera. Thus, the robotic arm can achieve precise alignment between the end tool and targets in multiple stations. The feasibility of our method is verified experimentally. The angle’s standard deviation is below 0.015° by 50 times repeated single-station pin-hole alignment, and the position standard deviation is below 0.078 mm. The three-stage alignment experiment in multi-stations alignment shows that the angle error is below 0.05° and the position error below 0.17 mm. [ABSTRACT FROM AUTHOR]

Copyright of Food & Machinery is the property of Food & Machinery Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The disposal of recyclable waste in China primarily relies on manual sorting, which is inefficient, suffers from harsh working environment and high cost. In this study, an intelligent recyclable waste sorting system is proposed, which employs RGB image as visual information input. Then the class and coordinates of the moving waste on the conveyor belt are obtained through object detection algorithm. Finally, the recyclable waste is picked up by the robotic arm and delivered to different bins. As recyclable waste has various appearance, it collects 36 572 frames of waste pictures and establishes a recyclable waste dataset for model training. This is to improve the generalization ability of the object detection model. Based on YOLOv4, an attention-based detection algorithm, Attn-YOLOv4 is proposed, and the mAP of Attn-YOLOv4 algorithm is 0.16% higher than that of the original YOLOv4. Besides, a multithreaded object tracking algorithm is proposed, which achieves an accuracy of 0.945 within a tolerance of 20 mm. Furthermore, a post-processing module acquires the orientations of the waste, which is further converted to world coordinates and orientations for the robotic arm. In the end, the feasibility and practical effect of the intelligent recyclable waste sorting system are verified and evaluated on a continuous recycling production line. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Shanghai University of Engineering Science / Shanghai Gongcheng Jishu Daxue Xuebao is the property of Journal of Shanghai University of Engineering Science Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Setting the multi degree-of-freedom robotic arm of aerial manipulator systems as study object,this paper proposed a new approach based on Leap Motion through which robotic arm could follow the movement of human hand. It used DU method to build mathematical model of the robotic arm and presented derivation process of mapping human hand movement captured by Leap Motion to the end of robotic arm. To avoid abrupt change of servo’s angular acceleration and ease the impact on the aircraft, it adopted 7-sections S curve method to adjust the servo speed. This paper designed and fabricated a prototype machine to test realizability of the control method,and during flight test,the method successfully control the robotic arm to pick up an object in the distance by using Leap Motion. [ABSTRACT FROM AUTHOR]

Brain-computer interface (BCI) has great potential to replace lost upper limb function. Thus, there has been great interest in the development of BCI-controlled robotic arm. However, few studies have attempted to use noninvasive electroencephalography (EEG)-based BCI to achieve high-level control of a robotic arm. In this paper, a high-level control architecture combining augmented reality (AR) BCI and computer vision was designed to control a robotic arm for performing a pick and place task. A steady-state visual evoked potential (SSVEP)-based BCI paradigm was adopted to realize the BCI system. Microsoft's HoloLens was used to build an AR environment and served as the visual stimulator for eliciting SSVEPs. The proposed AR-BCI was used to select the objects that need to be operated by the robotic arm. The computer vision was responsible for providing the location, color and shape information of the objects. According to the outputs of the AR-BCI and computer vision, the robotic arm could autonomously pick the object and place it to specific location. Online results of 11 healthy subjects showed that the average classification accuracy of the proposed system was 91.41%. These results verified the feasibility of combing AR, BCI and computer vision to control a robotic arm, and are expected to provide new ideas for innovative robotic arm control approaches.

The kinematic model parameter deviation is the main factor affecting the positioning accuracy of neurosurgical robots. To obtain more realistic kinematic model parameters, this paper proposes an automatic parameters identification and accuracy evaluation method. First, an identification equation contains all robot kinematics parameter was established. Second, a multiple-pivot strategy was proposed to find the relationship between end-effector and tracking marker. Then, the relative distance error and the inverse kinematic coincidence error were designed to evaluate the identification accuracy. Finally, an automatic robot parameter identification and accuracy evaluation system were developed. We tested our method on both laboratory prototypes and real neurosurgical robots. The results show that this method can realize the neurosurgical robot kinematics model parameters identification and evaluation stably and quickly. Using the identified parameters to control the robot can reduce the robot relative distance error by 33.96% and the inverse kinematics consistency error by 67.30%.