Radar style transfer for metric robot localisation on lidar maps

Lidar and visual data are affected heavily in adverse weather conditions due to sensing mechanisms,which bring potential safety hazards for vehicle navigation.Radar sensing is desirable to build a more robust navigation system.In this paper,a cross-modality radar localisation on prior lidar maps is presented.Specifically,the proposed workflow consists of two parts:first,bird's-eye-view radar images are transferred to fake lidar images by training a generative adversarial network offline.Then with online radar scans,a Monte Carlo localisation framework is built to track the robot pose on lidar maps.The whole online localisation system only needs a rotating radar sensor and a pre-built global lidar map.In the experimental section,the authors conduct an ablation study on image settings and test the proposed system on Oxford Radar Robot Car Dataset.The promising results show that the proposed localisation system could track the robot pose successfully,thus demonstrating the feasibility of radar style transfer for metric robot localisation on lidar maps.

Effects of a closed-loop system against SARS-CoV-2 at the Beijing 2022 Olympic Winter Games:a descriptive and modeling study

BACKGROUND:To assess the efficacy of the epidemic prevention measures of the“closed-loop”system adopted by the Beijing 2022 Olympic Winter Games(BOWG).METHODS:We retrospectively collected and analyzed information,including age,sex,nationality,vaccination status,date of diagnosis,and date of entry,from 280 SARS-CoV-2-positive individuals identified during the BOWG.A susceptibility-exposed-infectious-remove model was employed to evaluate the effectiveness of epidemic prevention strategies on controlling the spread of SARS-CoV-2 under different scenarios during the BOWG.RESULTS:Regarding SARS-CoV-2-positive cases,97.9%were imported,and 96.4%were asymptomatic.The median age was 37 years(range:29–47 years),and 73.9%were male,with the majority of cases being broadcasters and European attendees.Regarding vaccination status,93.5%were fully vaccinated,and six cases were considered to have been infected in the closed-loop system during the BOWG.Assuming that the BOWG adopted a semi-closed-loop management system,the cumulative number of confirmed cases would be 1,137 for quick quarantine measures(3 d later)implemented and 5,530 for delayed quarantine measures(9 d later)implemented.This modeling revealed that stringent pandemic prevention measures and closed-loop management effectively controlled the spread of SARS-CoV-2 during the BOWG.CONCLUSION:Imported cases are considered the main risk factor for SARS-CoV-2 transmission during mass gatherings,but a comprehensive closed-loop system could minimize transmission among attendees and general personnel.

树脂球堵漏工艺在塔中区块的应用及认识

塔里木中部地区奥陶系油藏主要采用水平井开发模式实施长段地质目标穿越,钻井深度普遍在7 000 m左右。目的层奥陶系储层地质条件复杂、缝洞发育、钻井液安全密度窗口超窄,钻井过程中普遍发生恶性漏失,严重制约了该油藏的勘探开发进程。由于大型溶洞和裂缝的存在,传统堵漏材料结合常规堵漏技术治理塔中地区奥陶系恶性漏失成功率较低;为此,文章分析了塔中奥陶系储层漏失特征和堵漏难题,在此基础上提出了“投球架桥变缝洞为孔,多种堵漏材料协同充填封堵”的树脂球堵漏工艺技术。树脂球堵漏技术在X井恶性井漏治理中的成功应用表明,该技术可有效解决塔中区块大型缝洞恶性漏失问题。文章研究成果为塔中区块奥陶系恶性井漏的治理提供了一种新技术思路,将有助于提高该区块的堵漏作业效果。

Design of recognition algorithm for multiclass digital display instrument based on convolution neural network

Digital display instrument identification is a crucial approach for automating the collection of digital display data.In this study,we propose a digital display area detection CTPNpro algorithm to address the problem of recognizing multiclass digital display instruments.We developed a multiclass digital display instrument recognition algorithm by combining the character recognition network constructed using a convolutional neural network and bidirectional variable-length long short-term memory(LSTM).First,the digital display region detection CTPNpro network framework was designed based on the CTPN network architecture by introducing feature fusion and residual structure.Next,the digital display instrument identification network was constructed based on a convolutional neural network using twoway LSTM and Connectionist temporal classification(CTC)of indefinite length.Finally,an automatic calibration system for digital display instruments was built,and a multiclass digital display instrument dataset was constructed by sampling in the system.We compared the performance of the CTPNpro algorithm with other methods using this dataset to validate the effectiveness and robustness of the proposed algorithm.

Dynamic modeling of a wave glider

水波滑翔器是一种能够利用海面波浪起伏获得前进动力的海面移动装置,本文研究一种该装置的动力学建模方法。水波滑翔器由水面浮子和水下滑翔装置两部分构成,可视为一个双质点系统。本文采用Kane方程建立该系统的动力学模型,并提出一种水池试验装置来测试模型的有效性,得到了滑翔器在不同海况条件下的速度性能。同时,该模型还可用于优化滑翔器的结构参数。本文提出的水波滑翔器动力学模型具有解析形式,是滑翔器运动控制得以实现的前提,也为滑翔器离线运动规划和装置结构优化提供了重要基础。

A Survey on Design,Actuation,Modeling,and Control of Continuum Robot

Inthis paper,we describethe advances inthe design,actuation,modeling,and controlfield of continuum robots.After decades ofpioneering research,many innovativeve structural designandUntethered magnetic robots are agood example;its external actuationcharteristigotten a lot of interest fromacademics.Furthermoodeling,modeling approachesbased on continuunnechals after years oof research.Geometricexactcontilodeling when combined withnumerical analytic methodschtFifecodle-b realized.In the control,closed.loop and hybrid control methodscombined with sensor feedbackinformation.On the other hand,tladeg and control of continum robotseasier.The data-driven modeling technique simplifies modeling aproves anti-interference and generalization abilities.This paper discusses the current development and challenges of continum robots in the above felds and provides prospectsfor the future.

Analysis and control for a bioinspired multi-legged soft robot

Untethered soft miniature robots are considered to have a wide range of applications in biomedical field.However,researchers today still have not reached a consensus on its configuration design and actuation method.Here,inspired by the tentacles of a certain kind of echinodermata,we propose a soft multi-legged robot with a total weight of 0.26 g capable of multiple locomotion modes.Based on the magnetic field distribution of a square permanent magnet,we qualitatively analyze the motion mechanism of the robot.Finally,we carried out relevant experimental research.The research shows that the robot can move forward,backward,steering and cross obstacles under the control of the magnetic field,and can combine these abilities to navigate the maze.

A hybrid visual servo control method for simultaneously controlling a nonholonomic mobile and a manipulator

Visual servo control rules that refer to the control methods of robot motion planning using image data acquired from the camera mounted on the robot have been widely applied to the motion control of robotic arms or mobile robots.The methods are usually classified as image-based visual servo,position-based visual servo,and hybrid visual servo(HVS)control rules.Mobile manipulation enhances the working range and flexibility of robotic arms.However,there is little work on applying visual servo control rules to the motion of the whole mobile manipulation robot.We propose an HVS motion control method for a mobile manipulation robot which combines a six-degreeof-freedom(6-DOF)robotic arm with a nonholonomic mobile base.Based on the kinematic differential equations of the mobile manipulation robot,the global Jacobian matrix of the whole robot is derived,and the HVS control equation is derived using the whole Jacobian matrix combined with position and visual image information.The distance between the gripper and target is calculated through the observation of the marker by a camera mounted on the gripper.The differences between the positions of the markers’feature points and the expected positions of them in the image coordinate system are also calculated.These differences are substituted into the control equation to obtain the speed control law of each degree of freedom of the mobile manipulation robot.To avoid the position error caused by observation,we also introduce the Kalman filter to correct the positions and orientations of the end of the manipulator.Finally,the proposed algorithm is validated on a mobile manipulation platform consisting of a Bulldog chassis,a UR5 robotic arm,and a ZED camera.

Untethered quadrupedal hopping and bounding on a trampoline

For quadruped robots with springy legs,a successful jump usually requires both suitable elastic parts and well-designed control algorithms.However,these two problems are mutually restricted and hard to solve at the same time.In this study,we attempt to solve the problem of controller design with the help of a robot without any elastic mounted parts,in which the untethered robot is made to jump on a trampoline.The differences between jumping on hard surfaces with springy legs and jumping on springy surfaces with rigid legs are briefly discussed.An intuitive control law is proposed to balance foot contact forces;in this manner,excessive pitch oscillation during hopping or bounding can be avoided.Hopping height is controlled by tuning the time delay of the leg stretch.Together with other motion generators based on kinematic law,the robot can perform translational and rotational movements while hopping or bounding on the trampoline.Experiments are conducted to validate the effectiveness of the proposed control framework.

Building a dense surface map incrementally from semi-dense point cloud and RGB images

目的:针对仅能通过轻型激光测距仪获取半稠密点云的环境地图构建问题,提出一种构建稠密表面模型的方法。该方法使机器人能够利用所构建的稠密表面模型地图完成定位、导航及目标搜索等任务。创新点:提出一种基于点云分割的点云表面重采样方法及一种基于点云概率模型的表面模型融合方法。对半稠密点云进行保留表面结构特性的重采样来获取观测数据的稠密表面模型。并递增式地将新获得的稠密表面模型融合进已有的稠密表面地图中,从而获得几何一致性较好的环境表面模型地图。实验效果:图6、7展示了基于本文方法所构建的稠密表面模型地图的效果。其几何结构精确且表面纹理清晰。此外,图8、9分别重点展示了表面重采样的作用以及本文提出的重采样方法的效果。图11则展示了本文方法对表面模型动态更新的较好支持。结论:使用本文所提方法,机器人可携带轻便式激光测距仪,获取半稠密点云后再进一步处理和融合得到几何一致性较高、表面精细的稠密表面问题模型地图,更好地实现定位、导航及目标搜索等任务。