Achieving a real-time and accurate detection of drones in natural environments is essential for the interception of drones intruding into high-security areas. However, a rapid and accurate detection of drones is difficult because of their small size and fast speed. In this paper a drone detection method as proposed by pruning the convolutional channel and residual structures of YOLOv3-SPP3. First, the k-means algorithm was used to cluster label the boxes. Second, the channel and shortcut layer pruning algorithm was used to prune the model. Third, the model was fine tuned to achieve a real-time detection of drones. The experimental results obtained by using the Ubuntu server under the Python 3.6 environment show that the YOLOv3-SPP3 algorithm is better than YOLOV3, Tiny-YOLOv3, CenterNet, SSD300, and faster R-CNN. There is significant compression in the size, the maximum compression factor is 20.1 times, the maximum detection speed is increased by 10.2 times, the maximum map value is increased by 15.2%, and the maximum precision is increased by 16.54%. The proposed algorithm achieves the mAP score of 95.15% and the detection speed of 112 f/s, which can meet the requirements of the real-time detection of UAVs.

Tracking-and-inserting a moving peg using a robot manipulator is a challenging task in manufacturing. In the past decades, various visual-based methods have been proposed for robotic manipulating static targets, which usually ignore the time delay in robot command transmission and image processing. However, for tracking and inserting a moving peg, time delays cannot be overlooked because they can reduce the tracking performance and even cause manipulations to fail. In this article, a robot visual-based control with a time-delay compensator is presented to solve the problem of inserting a moving peg. The time-delay compensator was designed using radial basis function neural network, a feedback compensator aimed at eliminating the tracking errors caused by the time delays. Thus, we could manipulate a moving object using a commercial industry robot, even with the time-variant delays in the control loop. Furthermore, the visual-based controller with the pseudoinverse image Jacobian matrix was designed using a linearization model. Thus, the matrix could be efficiently updated using the model. In the experiment, we inserted a peg into a moving hole using an eye-in-hand robot with precision.

It is important for Mars exploration rovers to achieve autonomous and safe mobility over rough terrain. Terrain classification can help rovers to select a safe terrain to traverse and avoid sinking and/or damaging the vehicle. Mars terrains are often classified using visual methods. However, the accuracy of terrain classification has been less than 90% in read operations. A high-accuracy vision-based method for Mars terrain classification is presented in this paper. By analyzing Mars terrain characteristics, novel image features, including multiscale gray gradient-grade features, multiscale edges strength-grade features, multiscale frequency-domain mean amplitude features, multiscale spectrum symmetry features, and multiscale spectrum amplitude-moment features, are proposed that are specifically targeted for terrain classification. Three classifiers, K-nearest neighbor (KNN), support vector machine (SVM), and random forests (RF), are adopted to classify the terrain using the proposed features. The Mars image dataset MSLNet that was collected by the Mars Science Laboratory (MSL, Curiosity) rover is used to conduct terrain classification experiments. The resolution of Mars images in the dataset is 256 × 256. Experimental results indicate that the RF classifies Mars terrain at the highest level of accuracy of 94.66%.

On-orbit operation tasks require the space robot to work in an unstructured dynamic environment, where the end-effector’s trajectory and obstacle avoidance need to be guaranteed simultaneously. To ensure the completability and safety of the tasks, this paper proposes a new obstacle-avoidance motion planning method for redundant space robots via reinforcement learning (RL). First, the motion planning framework, which combines RL with the null-space motion for redundant space robots, is proposed according to the decomposition of joint motion. Second, the RL model for null-space obstacle avoidance is constructed, where the RL agent’s state and reward function are defined independent of the specific information of obstacles so that it can adapt to dynamic environmental changes. Finally, a curriculum learning-based training strategy for RL agents is designed to improve sample efficiency, training stability, and obstacle-avoidance performance. The simulation shows that the proposed method realizes reactive obstacle avoidance while maintaining the end-effector’s predetermined trajectory, as well as the adaptability to unstructured dynamic environments and robustness to the space robot’s dynamic parameters.

This paper presents the methods, results and applications of visual localization and topographic mapping for Zhurong rover in China's Tianwen-1 mars mission. New techniques, namely vignette correction and online camera mast calibration, were developed for the images captured by the rover's Navigation and Terrain Cameras (NaTeCam) to enhance the mapping qualities. During surface operations, photogrammetric techniques were routinely applied at the travelling waypoints. The NaTeCam images were obtained to generate 3D topographic mapping products with centimeter level to support obstacle analysis and rover path planning. Cross-site visual localization at adjacent waypoints was conducted to reduce the accumulated position errors in the onboard dead-reckoning result. Visual localization refinement was also employed by matching of the digital orthophoto map (DOM) from the rover images and the orbital basemap at waypoints where distinct terrain features were available to further eliminate the localization errors. Comparing with the reference rover traverse extracted from a HiRISE image in which the actual rover track is visible, the accuracies of the rover traverses generated from cross-site visual localization and DOM matching refinement are estimated to be 1.75% and 0.50% of the traverse length. The actual total traverse length is 2009 m, which is 88 m longer than 1921 m from odometer reading, revealing a forward wheel slipping caused by the downslope trend of the southward traverse. The visual localization and topographic mapping results of Zhurong rover have greatly supported the surface exploration planning, object approaching and scientific investigations in the mission.

2020年12月17日，嫦娥五号返回器成功返回地面着陆，获取1731克月壤样品，这标志我国探测工程“绕落回”三步走战略圆满收官。月面采样是采样返回任务的核心环节，是我国首次在月球表面实施的复杂操控类任务。月面采样包括岩心钻探取样和月壤表取采样任务两个部分，受制于月面采样任务的复杂性和探测器自主能力的局限性，采样工作在地面遥操作中心的监视、引导与控制下开展。本文在对嫦娥五号月面采样的难点进行分析的基础上，将月面采样遥操作关键技术归纳为采样任务规划、多特征融合视觉定位、机械臂采样最优构型设计和采样虚拟仿真四个方面，并对四个方面技术的发展与研究现状进行综述，结合嫦娥五号任务特点，阐述了四项技术的主要实现途径及其创新性应用特点，分析了各种技术在月面采样任务实施中的关键性支撑作用，评述了其未来发展潜力和应用前景，对我国后续地外天体表面采样任务的实施和遥操作模式的设计具有重要的指导意义。