Aiming at the dynamic modeling andcontrol of actuator system under the influence of nonlinear conditions such as clearance and friction, compared with the conventional nonlinear model, the variable stiffness and wear...
Aiming at the dynamic modeling andcontrol of actuator system under the influence of nonlinear conditions such as clearance and friction, compared with the conventional nonlinear model, the variable stiffness and wear sliding characteristics of the transmission mechanism is considered. A dynamic modeling andcontrol method of actuator system with time-varying meshing stiffness and backlash is proposed. The minimum circumferential backlash and the maximum circumferential backlash are obtained by the method of backlash deviation correction. The mechanism of grease film effect on time-varying backlash and meshing impact is studied, and the thermal lubrication behavior of grease film thickness change and backlash change is revealed. The analysis shows that the transmission mechanism of the autuator system is in the state of boundary lubrication. The dead zone model of continuous differentiable function approximating the backlash nonlinearity is designed, and the accurate compensation of backlash nonlinearity is realized. The simulation results verify the effectiveness of the proposed method.
Considering the current teleoperation robot technology, this article provided a solution to accomplish the task of endotracheal intubation operation. An intubation mechanism is designed based on laryngeal mask, which ...
Considering the current teleoperation robot technology, this article provided a solution to accomplish the task of endotracheal intubation operation. An intubation mechanism is designed based on laryngeal mask, which is attached to the end of the robot. A corresponding robot teleoperation control system is established according to the characteristics of the mechanism design. This system is expected to have good performance in solving the problems of the current endotracheal intubation robots, including the difficulty of intubation movements; the high risk to cause secondary injury; the dependency of manual assistance in close distance, and the difficulty to achieve teleoperation. In order to test its performance, virtual environment simulation and corresponding experiments on human model are carried out. The results showed that surgeries using our system consumed shorter intubation time while keeping high intubation success rate, which met the needs of endotracheal intubation surgery.
Visual perception networks are often used to provide the necessary environmental information such as semantics and depth for mobile robots or autonomous driving. However, these networks can usually only complete one t...
Visual perception networks are often used to provide the necessary environmental information such as semantics and depth for mobile robots or autonomous driving. However, these networks can usually only complete one task. In practical applications, people often hope that an visual perception network can complete multiple tasks at the same time. In this work, We propose a lightweight visual perception network called LSEPNet with two branches of semantic segmentation and disparity estimation based on binocular vision system, which is composed of lightweight feature extraction module, feature fusion module based on attention mechanism, semantic decoder and disparity refinement module. Through feature fusion and joint loss function, LSEPNet can jointly train disparity estimation and semantic segmentation tasks end-to-end in real time. We evaluate the proposed network LSEPNet on KITTI2015 and Cityscapes datasets, and compare it with classic disparity estimation network and semantic segmentation network respectively, proving that LSEPNet can complete semantic segmentation task and disparity estimation task together in real-time with acceptable speed and accuracy.
This paper describes and analyzes the problem of satellite cluster trajectory planning based on improved grey wolf algorithm. Firstly, the mathematical model of satellite cluster is established. In this paper, the ful...
This paper describes and analyzes the problem of satellite cluster trajectory planning based on improved grey wolf algorithm. Firstly, the mathematical model of satellite cluster is established. In this paper, the fully distributed structure model is used to solve the control problem of three-degree-of-freedom autonomous satellites, and the dynamic topological interaction model is used to solve the communication problem between satellites, and the constraints that need to be met are indicated. Then, they are constructed as finite functions for path evaluation. In order to solve the path planning problem under the constraint conditions, we propose a new path planning method-differential evolution gray wolf algorithm, which also improves the diversity of wolf offspring through cross mutation, and obtains the nearest optimal path based on iterative rules. At the end of the paper, we have carried out simulation experiments on MATLAB. The simulation results show that the improved grey wolf algorithm is in good agreement with the control model, which not only satisfies the boundary constraints and direction constraints, but also greatly shortens the attitude maneuver time and reduces the number of times of falling into local optimum. The simulation has achieved good results.
The trend of intelligent and unmanned industries benefited from the rapid development of information technology is more and more obvious. The unmanned combat platform has become a new combat force in anti-terrorism op...
The trend of intelligent and unmanned industries benefited from the rapid development of information technology is more and more obvious. The unmanned combat platform has become a new combat force in anti-terrorism operations, relying on sensor, machine vision, communication, information fusion and other technologies. A design scheme of pan-tilt target tracking system based on machine vision is proposed here for the visual perception requirements of unmanned combat platform. A combination of YOLOv4-tiny and DeepSORT is used to identify and track personnel with cameras mounted on ball gears. When the target moves to the edge of view, the position information will be sent to the control circuit through serial communication, and the camera will be adjusted with the PID control algorithm to keep the target in the center of view. The experimental results showed that this system can achieve target tracking effectively in real time and the tracking success rate can reach 80% by optimizing with K-Means++ algorithm and PID controller.
Aiming at the problems of low automation level and efficiency in agricultural production of sorting and transportation facilities, an automatic sorting and transportation system for fruits and vegetables is designed b...
Aiming at the problems of low automation level and efficiency in agricultural production of sorting and transportation facilities, an automatic sorting and transportation system for fruits and vegetables is designed based on the Dobot Magician robotic arm. The technique combines software with hardware and consists of four parts: a robotic arm, PC, industrial camera, and conveyor belt. The PC receives the information about the conveyor belt, writes the Python script to control the industrial camera to collect images of fruits and vegetables, and loads the YOLOv5s target detection model to identify the target for fruits and vegetables. According to the recognition results and the transformation relationship of the coordinate system, the system can precisely control the robotic arm to complete the sorting of fruits and vegetables and realize the high-efficiency automatic sorting and transportation for the whole process. The system separates the model loading process from YOLOv5s target detection, improves the JUMP movement mode, optimizes the movement path, avoids collisions during movement, and reduces the time spent on target detection and robotic arm movement. After testing, the accuracy rate of fruit and vegetable identification can reach 95%, and the accuracy rate of robotic arm grasping is about 90%.
This paper aims to study a co-simulation method of underwater robots based on Webots and Matlab. With the increasingly extensive use of underwater vehicles, higher requirements are put forward for their control perfor...
详细信息
End-to-end grasp detection networks show state-of-the-art grasp accuracy in the standard datasets; these datasets use oriented rectangles to represent grasp poses and evaluate based on intersection over union (IoU) sc...
End-to-end grasp detection networks show state-of-the-art grasp accuracy in the standard datasets; these datasets use oriented rectangles to represent grasp poses and evaluate based on intersection over union (IoU) score. However, the model trained on these datasets, while being able to accurately localize to the object itself, does not necessarily predict the robust grasp pose, as it does not take into account the geometric features of the object. In this paper, we propose a Grasp Refinement Algorithm using RGBD images, which constrains the grasping detection network to output more robust grasp poses by extracting shallow features (e.g., object central axis) of the target object. The grasp refinement algorithm mainly consists of a feature extraction module and a grasp refinement module. The feature extraction module extracts the central axis of the target object and the object skeleton based on the depth threshold, which are then fed sequentially into the grasp refinement module to optimize the grasp pose predicted by the grasp detection network. The proposed algorithm achieves state-of-the-art grasp detection accuracy on both the Cornell grasp dataset, the Jacquard grasp dataset, and a simulated grasp environment based on the YCB dataset, which shows that our algorithm outperforms its counterparts in terms of grasp robustness.
It is important to build somatotopic mapping of human hands at cortex level. The devices published in previous studies could not provide precise tactile stimuli output covering the whole hand. We introduce a novel tac...
It is important to build somatotopic mapping of human hands at cortex level. The devices published in previous studies could not provide precise tactile stimuli output covering the whole hand. We introduce a novel tactile stimulation device including the actuating system and the control system. The device could generate multi-channel independent reciprocating stimuli actuated by bimorph based on the inverse piezoelectric effect. The actuating system consists of a position-adjusting part which could cover the whole hand and23 independent stimulation dots array actuators which could improve the stability of the stimulus and the hand-conformability of equipment layout under high-intensity magnetic field. A prototype tactile stimulation system is designed to verify the output characteristics. The results show that the actuator unit of the device could generate stable 1.6mm displacement from 0–20 Hz under 200V driving voltage, which could be used in future somatotopic mapping of human tactile perception study.
In order to achieve accurate imaging and positioning of targets with a wide field of view in the ocean, and to accomplish high-precision imaging in the region of space-borne point calibration, this article utilizes a ...
详细信息
暂无评论