Search

OBJECTIVE: Percutaneous sacroiliac screw internal fixation has become the main surgical procedure for the treatment of posterior pelvic ring fractures; however, the unassisted closure operation requires high operator experience and repeated fluoroscopy increases the radiation hazard for patients and medical personnel. This article compares the clinical efficacy of robot-assisted versus unassisted percutaneous sacroiliac screw placement for posterior pelvic ring fractures by meta-analysis. METHODS: Computer searches of CNKI, WanFang, VIP, CBM, PubMed, Embase, Cochrane Library and ClinicalTrials.gov were conducted from the time of database inception to December 2022. The literature on the clinical efficacy of robot-assisted versus freehand percutaneous sacroiliac screw placement in the treatment of posterior pelvic ring fractures was collected in and outside China. The data were independently screened and extracted by two investigators according to the inclusion and exclusion criteria, respectively. The quality of randomized controlled trials was evaluated using Cochrane risk assessment criteria. The quality of included cohort studies was assessed using the Newcastle-Ottawa Scale. Meta-analysis was performed using RevMan 5.4 software for inclusion metrics. Outcome metrics included operative time, intraoperative bleeding, fluoroscopy time, fluoroscopy frequency, number of holes drilled, Majeed postoperative function score, the excellent and good rates of Matta fracture reduction, the excellent and good rates of Gras screw position, fracture healing time and complications. RESULTS: (1) A total of 13 publications were included, 2 were randomized controlled trials both referring to randomized methods, 11 non-randomized controlled studies were evaluated for quality of literature according to the Newcastle-Ottawa Scale, 1 scored 8, 9 scored 7; and 1 scored 6; the quality of literature was good. A total of 748 patients were included, including 430 in the robot-assisted group and 318 in the freehand group. (2) The results of the metaanalysis showed that the operative time (MD=-28.30, 95%CI:-40.20 to -16.40), intraoperative bleeding (MD=-6.36, 95%CI:-10.06 to -2.66), intraoperative fluoroscopy time (MD=-12.13, 95%CI:-19.54 to -4.72), intraoperative fluoroscopy frequency (MD=-17.39, 95%CI:-29.00 to -5.78), number of intraoperative needle drillings (SMD=-9.50, 95%CI:-14.27 to -4.73) and the excellent and good rates of Gras screw position (OR=8.65, 95% Cl:3.26-22.92) in the robot-assisted group were significantly better than those in the freehand group (P<0.05). (3) In the robot-assisted group, the overall postoperative complication rate was significantly reduced (OR=0.10, 95% Cl: 0.02-0.48, P < 0.05). (4) No significant difference was detected in fracture healing time (MD=-0.08, 95%CI:-0.21,0.06), the excellent and good rates of Matta fracture repositioning rate (OR=2.06, 95%Cl: 0.97-4.39), and Majeed functional score (MD=0.91, 95%CI: -0.31-2.13) between both groups (P>0.05). CONCLUSION: Compared with freehand sacroiliac joint nailing, robotic assistance shortens the operative time, reduces intraoperative bleeding, decreases radiation damage to patients and medical staff, improves the excellent and good rate of screw position, and reduces the overall incidence of postoperative complications in patients, but there was no significant improvement in fracture reduction quality, fracture healing time, and postoperative function. In the future, more large-sample, multicenter, and high-quality randomized controlled trials are still needed to verify. [ABSTRACT FROM AUTHOR]

In order to study the effect of single abrasive material removal in robotic belt grinding, a single-grit scratch experiment based on robotic belt grinding was conducted. The removal behavior of robotic abrasive belt grinding of high-temperature alloys was investigated, and the variation patterns of scratch length, removal depth and pile-up ratio with grinding speed and set grinding depth were analyzed. The experimental results showed that with the increase of grinding speed, the scratch length and removal depth generally tended to decrease, and became locally larger when the grinding speed reached 10.99 m/s. The accumulation ratio showed an overall increasing trend, and locally decreased at 10.99 m/s. With the increase of the set grinding depth, both the scratch length and the removal depth increased, but they didn’t increase linearly. On the whole, the pile-up ratio showed a trend of decreasing and then increasing. The results of this study may provide an important reference for the optimization of the robotic belt grinding process. [ABSTRACT FROM AUTHOR]

In the process of applying deep reinforcement learning(DRL)to realize autonomous behavioral decision-making of robotic arms, the high-dimensional continuous state-action space is prone to low data sampling efficiency and low quality of empirical samples, which ultimately leads to slow convergence of the reward function and long learning time. To address this problem, a DRL model that introduces prior knowledge was proposed. The model was combined with the inverse kinematics of the robotic arm, and prior knowledge was introduced to guide the agent during the sampling phase of DRL, addressing the issues of low data sampling efficiency and poor quality of experience samples during the learning process. Furthermore, the introduced prior knowledge DRL model’s strong generalization capabilities were verified when facing new tasks through network parameter transfer. Lastly, joint simulation experiments were conducted using Python and the CoppeliaSim platform. The results show that the DRL model with the introduction of prior knowledge improves the learning efficiency by 13.89% and 12.82%,and the success rate of completing the task increases by 16.92% and 13.25% than the original model; in the new task, the learning rate improves by 23.08% and 23.33%,and the success rate improves by 10.7% and 11.57%. [ABSTRACT FROM AUTHOR]

In order to improve the grasping detection accuracy of the multi-object grasping detection network, a robotic arm grasping detection algorithm based on the improved Cascade R-CNN model is proposed. Firstly, the introduction of the ResNeXt structure can improve the accuracy of the model without increasing the difficulty of network design. The atrous spatial pyramid pooling module is introduced to solve the problem of low resolution. Then, the grasping box regression branch and the angle classification branch are optimized by the divide and conquer method. Secondly, aiming at the lack of multi-object grasping datasets, a multi-object grasping dataset (MOGD) is constructed, which effectively expands the multi-object grasping detection dataset. Finally, a grasping detection network is designed based on the improved Cascade R-CNN model. The experimental results show that the improved algorithm is more efficient. The experimental accuracy of the PI-Cascade R-CNN is 93 %, which is 1.5 percentage higher than that of the Cascade R-CNN. [ABSTRACT FROM AUTHOR]

Continual learning, as a special machine learning paradigm that continuously learns new tasks in non-stationary data streams and can maintain the performance of old tasks, is a hot research topic in fields such as visual computing and autonomous robotics, but at this stage, the catastrophic forgetting problem is still a great challenge for continuous learning. This paper conducted a review study on the catastrophic forgetting problem of continual learning, analyzed the mechanism of catastrophic forgetting problem mitigation and explored the catastrophic forgetting problem solving strategies at three levels, included regularization strategy, replay strategy, dynamic architecture strategy and joint strategy, in terms of model parameters, training data and network architecture. According to the existing literature, this paper condensed the evaluation index of the catastrophic forgetting method and compared the performance of solving strategies for different catastrophic forgetting problems. Finally, it pointed out the future research direction of continual learning, to provide references for the study of continuous learning catastrophic forgetting problems. [ABSTRACT FROM AUTHOR]

Multi-axis force sensing is of great significance for the intelligent industries. This paper proposes a kind of strain-gauge type six-axis force sensor which is capable of measuring shear force for ±300 N, normal force for ±600 N and torque for ±25 N·m. The sensor shows a spoke shape and contains four groups of specially designed strain beams that connect the central platform and the outer support. Each group of strain beams contains a pair of L-shape beams at the two sides and a flat beam at the middle. Such kind of combination can reduce the coupling largely. By selecting proper positions for the strain gauges and designing measuring bridges, we further theoretically eliminated the coupling. Static calibration indicat that the senor possesses a precision higher than 1‰ and a safety factor larger than 300%, with the nonlinearity smaller than 0.3% and the coupling less than 1%. Test results of its response to a pulse input also confirm that the sensor has good dynamic properties. Implementation of the sensor in a robotic also further demonstrated the excellence of the sensor. This six-axes sensor will greatly advance the multi-dimensional force testing technology and play a great role in accelerating the intelligentization of modern industries. [ABSTRACT FROM AUTHOR]

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]

BACKGROUND: Traditional rehabilitation training has limited potential to improve functional recovery from chronic injuries. Increasing attentions have been paid to the application of rehabilitation robots in rehabilitation training of chronic injuries. OBJECTIVE: To analyze and track the hot spots and frontiers of related research in the field of rehabilitation robot in the past 10 years, thereby providing some guidance for future research. METHODS: The literatures regarding rehabilitation robots published from 2010 to 2020 were retrieved in the Web of Science core database by computer. Search strategy was TS=(rehabilitation robot OR rehabilitation robotics). CiteSpace 5.7 visualization software was used to analyze the hot spots and frontiers of rehabilitation robot research from the aspects of high-influence countries/regions, institutions, authors, high-frequency keywords and burst words. RESULTS AND CONCLUSION: A total of 3 194 literatures were included. In recent years, the research on rehabilitation robots has been growing steadily. The number of relevant literatures published annually shows a steady increase trend. The number of articles published by the United States ranks first, followed by China. Northwestern University in the United States ranks first with 161 articles published. Professor Riener R, from the University of Zurich, Switzerland, has published 48 articles, ranking the first among the authors. Nine representative keyword clusters have formed, and the research emphasis and direction change over time. In recent 10 years, the relevant research focuses on intelligent control of rehabilitation robots, task analysis and learning, performance and reliability, and how to realize the natural and accurate interaction between robot and human through the integration of machine intelligence and biological intelligence. At present, rehabilitation robots are the most widely used in the field of upper limb and nerve injuries, and the interest in brain-machine interface, virtual reality, flexible wearable, task analysis and the exoskeletons has increased in the research of rehabilitation robot, which are the frontiers and hot issues in recent years, representing the development trend of future studies, and referring to the future research direction. Future research in the field of rehabilitation robots should focus on the following aspects: First, focus on the functional needs of patients to improve the quality of life. Secondly, strengthen multidisciplinary cooperation and build a cooperation network among regional countries. [ABSTRACT FROM AUTHOR]

A trajectory tracking control method was proposed based on improved Funnel control and with RBF adaptive neural network to address the steady-state and transient performance constraints of a flexible joint robotic manipulator system with unknown input saturation. The non-differentiable in the control law was avoided by designing improved Funnel control variables. The construction of time-varying transient performance constraint function made it possible to qualitatively design the overshoot amount and convergence speed in the initial stage of the system output; The problem of excessive computational burden in the back-stepping step method and the unknown function of the flexible-joint robotic manipulator system were approximated by the RBF adaptive neural network with minimum parameter learning method, which simplified the design of the controller; The Lyapunov stability theory justified that all variables in the closed-loop system are semi-global uniformly ultimately bounded (SGUUB), and simulation experiments verified the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

During the research of using manipulators to detect avionics buttons in the avionics joint debugging and commissioning robotics system, two compliant detection algorithms for avionics buttons based on joint torque sensors are proposed to solve the problems of complex detection environment and the requirement of adapting to different types of buttons and localization errors from visual system. The algorithms are used to detect the three main types of buttons appeared in the avionics joint detection environment. The contact localization and operation algorithm based on external force threshold detection is used to realize the relocalization and safe operation of buttons and lever switches. The algorithm first estimates the external force appiled to the end effector through a generalized momentum observer, and then sets an operating force threshold when the manipulator is moved to detect buttons. The compliant button operation algorithm based on impedance control is used for compliant clamping operation of the rotary switch. The manipulator is changed to low impedance mode when the switch is clamped, so that the end effector can comply with the internal force during button operation. Button detection experiments are carried out in both the simulated cabin and the actual avionics joint detection environment. Experiment results show that the proposed algorithms have advantages of high adaptability to different button types and localization errors, and can improve the success rate and safety of detecting avionics buttons. [ABSTRACT FROM AUTHOR]

In the aviation manufacturing industry, complex aircraft components can hardly be completely measured in the digital measurement process. This paper proposes a scanning path generation method based on feature recognition. For the digital model of an aircraft component, based on its slot and rib features, we aim at providing several scanning paths for the scanner holder, i.e., a robotic arm, to finely and completely scan features. We segment and extract the surfaces of aircraft components into parts based on the region segmentation method. Considering that the surfaces of hard-to-scan areas, i. e., slots and ribs, are usually approximately perpendicular to the scanning direction, the parts that satisfy the perpendicular criterion are gathered as a basis for subsequent processing among the surface of parts after segmentation. By analyzing the extracted features of these surfaces, we plan the scan path as follow：Each surface is projected into a twodimensional plane, and a suitable scanning path is generated；After projecting the path back into three dimensions, it is adjusted along a specific angle to generate the final scanning path. The experimental results demonstrate that the proposed method can accurately generate the scanning path, which is practical for digital measurement in the aviation manufacturing industry. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the local path planning algorithm is only applicable to single-vehicle robots, this paper proposed a dynamic window algorithm for trailer-type mobile robots. Firstly, it used the equation of multi-vehicle structure to realize the motion control of the trailer mobile robot. Then, it used the evaluation function to evaluate both the tractor and the trailer and add them according to the weights. Finally, for the structural characteristics of the trailer, it added the angle constraint between the tractor and the trailer during the movement to ensure the stability of the motion track. The simulation experiments show that the motion control of the trailer-type mobile robot can satisfy the convergence. At the same time, the proposed algorithm realized the task of the local path planning of the trailer-type mobile robot, and the variation of the angle was beyond the limit during the motion. This research has great reference value for the autonomous navigation of trailer-type mobile robots. [ABSTRACT FROM AUTHOR]

Objective To analyze the hotspots and development trends of robots in the nursing field to provide reference for the robot related nursing research and clinic. Methods The literatures on the application of robots in the nursing field included in the CNKI and Web of Science databases during 1998-2018 were collected as the study objects and performed the bibliometric and cluster study by using the BICOMB 2.0 software and SPSS 19.0 statistical software . Results The number of documents on the robots application in the nursing field has increased rapidly in recent years; the research hotspots in CNKI focus on the 4 aspects: robot assisted laparoscopic surgical nursing, Da Vinci robotic surgical cooperation, perioperative nursing key points and related nursing of robot in rapid rehabilitation surgery. The research hotspots in the Web of Science database mainly focus on the 5 aspects: robot care assistant, aged care, rehabilitation care, assisted operation nursing, and research and design of nursing robot. Conclusion There search of robots in the nursing field has been widely carried out, and the research direction tends to be diversified. The future research has broad space in the aspects of robot assisted surgery, aged care, rehabilitation nursing and intelligent nursing assistant. [ABSTRACT FROM AUTHOR]

This paper proposed an uncalibrated 3 D robotic arm grabbing method based on improved YOL0v2 in a multi-object environment. Firstly, in order to reduce the depth learning algorithm YOL0v2 detection multi-obj ect bounding box overlapping rate and 3D distance calculation error, it proposed an improved algorithm for YOL0v2. It used this algorithm to detect and identify the target object in the image, obtained the pos ition information of the target object in the RGB image, and then used the K-means + + clustering algorithm to quickly calculate the distance from the target object to the camera according to the depth image information, and estimate the target object size and pose. Simultaneously, it used the improved YOL0v2 to get the bounding box of the gripper and calculated the distance from the robot to the target object. Then the system estimated the distance between the fixture, camera and obj ect in the manipulator coordinate system. Finally, the system used the PID algorithm to control the gripper to grab the object according to the size and posture of the object and the distance from the object to the gripper. The detected boundary boxes of the target obj ect was more accurate based on the improved YOL0v2 than on old one. It also enhanced the distance from the fixture to the object and the size of the object as well as the accuracy of the pose estimation. In addition, in order to avoid complicated calibration, this paper proposed a non-calibration method. The learning scheme was different from the traditional uncalibrated estimation method based on Jacobian matrix, because it had good universality. A simulation experiment shows that the proposed method can accurately classify and locate the objects in the image. The Universal Robot 3 robotic arm uses this framework to verify the effectiveness of capturing objects in a cluttered environment. [ABSTRACT FROM AUTHOR]

In order to solve the problems of warehousing mobile robots autonomous navigation in full dynamic environment, this paper established a mathematical model of robots and dynamic obstacles, designed a platform of environmental awareness based on 2-dimensional lidar, and proposed an improved artificial potential field method. In the traditional artificial potential field method, it introduced the relative speed and relative acceleration to obtain an improved artificial potential field model, which could realize the autonomous movement of the robot in full dynamic environment. It verifies that the improved artificial potential field method is used to plan path, which can effectively avoid the dynamic obstacles and track the dynamic target, and the movement path is smooth. [ABSTRACT FROM AUTHOR]

BACKGROUND: Traditional fluoroscopy-guided pedicle screw fixation is not highly accurate and can lead to serious surgical complications. To reduce surgical complications and improve the success rate of surgery, robotic assistive technology emerges as the times require. OBJECTIVE: To compare the difference of robot-assisted and fluoroscopy-guided pedicle screw placement using meta-analysis. METHODS: The study included clinical controlled trials on robot-assisted and fluoroscopy-guided pedicle screw placement published in and outside China from December 2008 to December 2018. The retrieval was performed in the online databases include Embase, PubMed, Central, CNKI, CQVIP, Wanfang, and CBM. Keywords used for search were robot assisted, fluoroscopy guided, conventional, freehand, pedicle screw in English and Chinese. After the data were extracted, statistical software Review Manager 5.3 was used for data-analysis. RESULTS AND CONCLUSION: (1) Based on the above search strategy, 1 615 studies were retrieved, and 13 were included. (2) Statistical analysis found that placement accuracy in the robot-assisted group was better than that of the fluoroscopy group [95%CI(1.55, 4.06), P=0.000 2]. Radiation intensity in the fluoroscopy group was lower than that in the robot-assisted group [95%CI(0.42, 0.82), P < 0.001], and the difference was statistically significant. (3) However, the incidence of complications [95%CI(0.23, 4.65), P=0.96] and revised surgery [95%CI(0.03, 3.17), P=0.33] were not statistically significant between the robot-assisted group and the fluoroscopy group. Intraoperative fluoroscopy time was similar between the two groups [95%CI(-38.55, 78.26), P=0.51]. Postoperative back pain [95%CI(-0.58, 0.38), P=0.68], leg pain score [95%CI(-0.20, 0.19), P=0.94] and operation time [95%CI(-6.33, 53.02), P=0.12] were also similar between the two groups, and the differences were not statistically significant. (4) Compared with fluoroscopy, robot-assisted technique has higher pedicle screw placement accuracy, especially under percutaneous conditions. Inevitably, the intraoperative radiation intensity is also more than conventional fluoroscopy. [ABSTRACT FROM AUTHOR]

BACKGROUND: In the past, the main end-stage treatment of osteoarthritis was joint replacement surgery. In recent years, with the prevalence of the concept of knee-protection and the continuous development of internal fixation materials and surgical techniques, unicompartmental replacement, a minimally invasive technique, has been widely used in the treatment of patients with single-chamber osteoarthritis. OBJECTIVE: To compare the efficacy of unicompartmental knee arthroplasty in osteoarthritis patients using robotic-assisted or traditional manual methods by meta-analysis systematically. METHODS: We searched for clinical control studies published from 1999 to March 2019. The retrieved databases included Embase, PubMed, Central, Cinahl, PQDT, CNKI, CQVIP, Wanfang, Cochrane Library, CBM and other databases. Five outcomes including tibial component implantation accuracy, femoral component implantation accuracy, tibiofemoral component safety zone, operation time and complications were selected to compare the efficacy differences between robotic-assisted techniques and traditional manual methods systematically. RESULTS AND CONCLUSION:(1) According to the above retrieval strategies, eight foreign literatures were included.(2) By comparison, we found that the robotic-assisted unicompartmental knee arthroplasty was superior to manual methods in the accuracy of tibial component placement [95%CI(-2.13,-0.63), P=0.000 3], femoral component placement [95%CI(-2.49,-0.32), P=0.01] and the tibiofemoral component safety zone [95%CI(1.05, 17.57), P=0.04] with significant statistical difference.(3) Although robotic assistant technology took longer operation time [95%CI(12.58, 42.33), P=0.000 3], it did not increase the incidence of complications [95%CI(0.75, 3.71), P=0.21].(4) In unicompartmental replacement surgery, robotic assistant technology has higher accuracy and does not increase the incidence of complications. It is a more ideal surgical method than traditional manipulation. These conclusions need to be validated by a larger sample and a higher quality randomized controlled study. [ABSTRACT FROM AUTHOR]

BACKGROUND: Femoral prosthesis placement with correct osteotomy in total knee arthroplasty is crucial to the success of the operation. OBJECTIVE: To review the research progress of femur plus other in total knee arthroplasty by referring to relevant papers for summary. METHODS: We retrieved the relevant literatures from CNKI, WanFang and PubMed databases. The keywords were "knee; arthroplasty; femoral prosthesis; rotational alignment; measuring resection; gap balance; computer aided navigation; 3 D printing; robotics" in Chinese and English, respectively. Retrieval time was from January 1976 to January 2019. The types of articles included clinical research, basic research, review, and experience exchange.RESULTS AND CONCLUSION: The rotation of the femoral prosthesis positioning in total knee arthroplasty can be measured by method of bone cutting and gap balance method, but computer aided navigation technology, 3 D printing technology and robotics due to a variet y of factors in clinic cannot be used widely. It is still based on traditional bone cutting method until now. With the development of science and technology and the introduction of concept of minimally invasive, it is believed that in the near future, computer aided navi gation technology, 3 D printing technology and robot technology will be widely used in clinic, thereby speeding up the development of total knee arthroplasty, and improving clinical efficacy after arthroplasty. [ABSTRACT FROM AUTHOR]

The reliability method was introduced into the prediction of modal coupling chatter in robotic milling. Firstly， the reliability model was established and the limit state equation was obtained. Secondly， the fourth-order moment method was used to calculate the reliability and sensitivity to analyze the influence of various parameters on the milling stability. Finally， an example was given based on the engineering background of robotic milling bone. The results showed that the two-degree-freedom stiffness， cutting force coefficient and feeding direction of the robot will affect the stability of the milling process. Within a certain range， increasing the stiffness in X divection，reducing the stiffness in Y direction， reducing the cutting force coefticient and choosing the feed divection resonably are helpful to avoiding modal coupling chatter. The system is more sensitive to the change of cutting force coefficients than to the stiffness in X and Y directions， and has more significant benefit influence on stability. [ABSTRACT FROM AUTHOR]

With the development of remote sensing,robotics,computer vision and artificial intelligence,plant phenomics research has been developing rapidly in recent years. Here,we first introduced a concise history of this research domain,including the theoretical foundation,research methods,biological applications,and the latest progress. Then,we introduced some important indoor and outdoor phenotyping approaches such as handheld devices,ground-based manual and automated vehicles,robotic systems,Internet of Things(IoT)based distributed platforms,automatic deep phenotyping systems,and large-scale aerial phenotyping,together with their advantages and disadvantages during the applications. In order to extract meaningful information from big image-and sensor-based datasets generated by the phenotyping process,we also specified key phenotypic analysis methods and related development procedures. Finally,we discussed the future perspective of plant phenomics,with recommendations of how to apply this research field to breeding,cultivation and agricultural practices in China. [ABSTRACT FROM AUTHOR]

This paper described the current work of designing a virtual laboratory of coordinate transformation in robotics, which was based on Qt and Ogre3D. It was a drive to cater the requirement of robotics learning and laboratory learning. At the stage of robotics virtual laboratory, the coordinate transformation was focused. It adopted a step and step fashion to show the relationship of Euler-angle, RPY angle, axis/angle, unit quaternion and homogeneous transformation matrix and the space meaning of DH parameter by virtual technologies. Numerical computation along with virtual display provided a detailed illustration of the concept. It detailed described the usage of virtual experiments. To judge the effectiveness of virtual experiments, it arranged a teaching experiment. The experiment result shows that virtual experiments can make the teaching process more reasonable and are bound to play an important role in robotics learning. [ABSTRACT FROM AUTHOR]

In order to solve the collision in the detection process of robotic ultrasonic automatic detection system, the ultrasonic detection system is divided into collision and stationary bodies, and the collision detection algorithm based on the distance field is introduced. Based on the kinematics equation of robot, the collision detection is carried out in the virtual environment of the ultrasonic automatic detection system, and the anti-collision detection of the system during the detection process of magnesium alloy shell is realized. The variation law of the shortest distance between the stationary body and the collision body is analyzed by comparing the detected results of different scanning parameters, and the ultrasonic detection process optimization of magnesium alloy shell is realized. The experimental results show that the improved algorithm can improve the efficiency of collision detection by 80. 62%, which can meet the requirements of collision efficiency during ultrasonic testing of magnesium alloy shell and guarantee the same precision as the traditional distance field detection algorithm at the critical position [ABSTRACT FROM AUTHOR]

Aimed at two different structures configuration of modular manipulator,this paper completed the quantitative comparison analysis of its workspace. Firstly,it derived the kinematics model by using the DH method. Secondly,it built the simulation platform of two different conformation arm based on the robotics toolbox in MATLAB,then solved the workspace of the two arm configuration by applying Monte Carlo method and acquired the point cloud of its workspace by using visual approach. Thirdly,it plotted the 3D workspace of two arm configuration by means of combining computer-aided design software,then analyzed and handled the workspace of two arm configuration quantitatively using SLI index. Lastly,it analyzed the advantages and disadvantages of the two arm configurations by comparing the point cloud of the workspace,the 3D solid workspace and the SLI performance index of two arm configurations,it lays a foundation for subsequent optimization of structure parameters and spatial flexibility research of modular manipulator. [ABSTRACT FROM AUTHOR]

The transformations of medical pattern bring the challenge for the minimally invasive surgical. With the innovation of the science and medical technology, minimally invasive technology developed quickly in recent 20 years. It has been applied to the management of gynecologic malignancies with promising result. Its advantage involving the relatively small incision, less intraoperative blood loss and operative complication, shorter hospital stay, faster recovery and so on. Not only that, compared with traditional laparotomy, it has no obvious difference with regard to the number of dissected lymph nodes, overall and disease-free survival rates. So it is safety and feasibility to treat endometrial cancer. At present, minimally invasive operation technologies for endometrial cancer, including traditional laparoscopic surgery, laparoscopic single-site surgery, robotic surgery and robot assisted laparoscopic single-site surgery. In this article the application of minimally invasive surgical in treating endometrial cancer is reviewed, involving the advantages, limitations and future direction of minimally invasive surgery. Hoping to provide some help for clinicians according to patients condition to choose operation. [ABSTRACT FROM AUTHOR]

A variety of heterogeneous electronic equipment were difficult to integrated with each other in intelligent home system, this paper adopted a universal plug and play standard to integrate the service robot into the intelligent home system, emphatically introduces the new derivative service. Firstly, it introduced the details of UPnP standard and service robot Rovio. Then, it developed a PC application program as the virtual bridge between the service robot and intelligent home network, and formed a control circuit to control the service robot to provide service for intelligent home system. Finally, it used some practical operation to test the performance of the UPnP Rovio virtual bridge, and demonstrate the possibility of the integration between service robot and intelligent home network by the practical services, such as path tracking, rubbish monitoring and so on, especially, the advanced services show that the huge potential benefits are expected. [ABSTRACT FROM AUTHOR]

Minimally invasive surgery has made rapid development in recent years and has become one of the most hot fields in procedural medicine. As science and medical technology have been improved, it has also made great progress in applications of gynecology. Although traditional open surgery is still has an important role in gynecology, minimally invasive surgery are attracting more and more attentions from researchers. As a representative of minimally invasive surgery, traditional laparoscopy has been a standard minimally invasive approach for gynecological diseases, which also can treat gynecological malignancies. Since traditional laparoscopy has been proven a mature technology, in this article, two evolving minimally invasive surgeries, endoscopic surgery through natural channels and robotic-assisted laparoscopic surgery are respectively reviewed. We review the main advances of these minimally invasive surgeries and their recent applications in gynecological treatments. [ABSTRACT FROM AUTHOR]

Aiming at the problem of the inefficient artificial feeding, the production cycle which cannot meet the requirements and the surface finish of the brass pin which cannot be ensured of the automotive valve tappets' assembly line, an automatic brass pin fitting device was studied. Several automatic feeding schemes such as vibrating hopper, belt conveyor, cartridge and gantry robot were discussed. An automatic feeding scheme consisting of the cartridge, the gantry robot and the receiving and dropping mechanism was chosen. The repetitive positioning accuracy and anti-collision between the pins were guaranteed by the cartridge; the pin grabbed and travelled rapidly were affected by gantry robot; the pin fitted in the right place was completed by the receiving and dropping mechanism which can turn over right-angle to make the pin drop in assembly station by means of its gravity. The results indicate that this device makes the asembly line run smoothly, improves productivity and ensures the surface finish of the brass pin. [ABSTRACT FROM AUTHOR]

Aiming at tracking human target's position, the working principile of the two-dimensional laser scanner was summed up, the algorithm of the analysis of data was researched, an algorithm based on the technolog of laser image scanning was designed. An elliptical model of the body's shoulder was built up. distance, angle and azimuth information of human target was acquired, and was displayed through Mat-lab QUI. A two-dimensional scanning plane was formed thorugh Two-dimensional laser scanner used the rotating optical components the function of regional scanning and profile measurement was realized. The results indicate that the position information of human target is acquired by laser scanner and have the basic agreement with the real position information, distance range is 0 ~4 m, the accuracy is better than 0.05 m, scope of angle is 240°,angular tracking accuracy is better than 2°, azimuth range is 360°,azimuth accuracy is 1°, the algorithm can be applied to engineering applications such as mobile platforms or robots which need tracking human targets in real time. [ABSTRACT FROM AUTHOR]

With the advancement of science and technology, laparoscopic and robot-assisted laparoscopic and other minimally invasive surgery has become the preferred method of surgical treatment of cervical cancer. At present, surgical treatments of cervical cancer include radical hysterectomy, nerve-sparing radical hysterectomy, radical trachelectomy, and pelvic and para-aortic lymphadenectomy, even para-uterine tissue and pelvic organ excision performed with single port or multi port laparoscopic and robot-assisted laparoscopic surgery. Its advantages include the expansion of the surgical field and visualization, to reduce the amount of bleeding and operative complication, reduce the need for analgesics, shorter hospital stay, faster recovery and so on. Minimally invasive surgical treatment of cervical cancer represents the future direction of cancer treatment, randomized multi-center clinical studies through a large sample, obtained category one of evidence to provide the most effective and advanced surgical treatment for cervical cancer patients. [ABSTRACT FROM AUTHOR]

A multi-agent reinforcement learning method based on action prediction of other agents is proposed. In the multi-agent system, the action selection of a learning agent must be effected by other agents' action. Therefore, joint-state and joint-action are involved in reinforcement learning system. The method of agent action prediction based on the probabilistic neural network is proposed. So the joint-action is formed and multi-agent reinforcement learning is implemented. Furthermore, the application of the proposed method in cooperation strategy learning of robot soccer is studied. Through mutually learning with environment, multiple robot system can master behavior strategy and realize multiple robots coordination and cooperation. [ABSTRACT FROM AUTHOR]

As the world's biggest robot soccer match with the highest level and the widest influence, RoboCup (Robot Soccer World Cup) is held to promote researches on artificial intelligence and robotics. RoboCup 2D match provides an excellent emulational platform, which is both appropriate for students to compete in science and technology, and suitable for researching on artificial intelligence theory. Firstly, the system framework of RoboCup 2D including the overall framework, the server framework and the client framework are introduced. Secondly, based on example team agent2d, planning model of DreamWing2D soccer team is designed and implemented. Lastly, the setup and experimental approaches of RoboCup 2D platform are demonstrated. The team specially improved in planning model performs much better and has achieved good results in RoboCup China Open. [ABSTRACT FROM AUTHOR]

This paper presented a production line splicing flexibility technology based on robot 3D simulation technology scheme and set up a robot load boundary model after analyzed the difficulties of the flexible welding line solution. According to the design demand of grid-style flexible fixture from the robot load, it set up the robot selection and quick change device selection scheme based on load boundary model. It presented the design method for flexible grid-style fixture and set up the corresponding scheme and test and stress analysis of grid-style assembly with white body flexible welding production line for example. It researched the off-line programming technology oriented flexible splicing and analyzed the project authorization management and workstation simulation workflow in 3D simulation of robot. It validated the scheme in welding production line in the project production line of the two models ( NL-1 &NL-2 ) in an automobile factory and meet the demand that the two vehicle production line splicing flexibility. [ABSTRACT FROM AUTHOR]

In view of the shortcoming of the old man fall detection based on threshold algorithm and detection method based video is easy to leak privacy, this paper proposed a decision analysis fall detection algorithm based on statistics. The algorithm extracted the behavior of the characteristic value and established the characteristic vector space mainly through the experiment, then used the sampling values and behavior characteristics of space distance to determine whether the behavior matched the falling value of the state space. At the same time, the algorithm introduced the idea of intelligent robot as auxiliary detection. Finally, through the experiment shows that the algorithm has good robustness. [ABSTRACT FROM AUTHOR]

Considering the aviation cost and combat effect of aerocrafts team, this thesis investigated the way of aerocrafts' cooperative path planning based on task assignment, constructed aerocrafts team's cooperative path planning model and designed decomposition algorithm. This can effectively balance multiple objective presence, get reasonable task allocation and path planning schemes. The simulation results show that this method can not only guarantee the cooperative paths of aircrafts reasonable, but also get the best combat effect and effectively improve the combat benefit-cost ratio. [ABSTRACT FROM AUTHOR]