Target Positioning and Grasping of NAO Robot Based on Monocular Stereo Vision

With the continuous advancement of science and technology and the rapid development of robotics, it has become an inevitable trend for domestic robots to enter thousands of households. In order to solve the inconvenience problem of the elderly and people with special needs, because the elderly and other people in need may need the help of domestic robots due to inconvenient legs and feet, the research of the robot target position based on monocular stereo vision and the understanding of the robot NAO are very important. Research and experiments are carried out on the target recognition and positioning in the process of NAO robot grasping. This paper proposes a recognition algorithm corresponding to quantitative component statistical information. First, extract the area of interest that contains the purpose from the image. After that, to eliminate interference in various fields and achieve target recognition, the robot cameras have almost no common field of view and can only use one camera at the same time. Therefore, this article uses the monocular vision principle to locate the target, and the detection algorithm is based on the structure of the robot head material, establishes the relationship between the height change of the machine head and the tilt angle, and improves the monocular vision NAO robot detection algorithm. According to experiments, the accuracy of the robot at close range can be controlled below 1 cm. This article completes the robot’s grasping and transmission of the target. About 80% of the external information that humans can perceive comes from vision. In addition, there are advantages such as high efficiency and good stability.

Monocular 3D Object Detection Based on Uncertainty Prediction of Keypoints

Three-dimensional (3D) object detection is an important task in the field of machine vision, in which the detection of 3D objects using monocular vision is even more challenging. We observe that most of the existing monocular methods focus on the design of the feature extraction framework or embedded geometric constraints, but ignore the possible errors in the intermediate process of the detection pipeline. These errors may be further amplified in the subsequent processes. After exploring the existing detection framework of keypoints, we find that the accuracy of keypoints prediction will seriously affect the solution of 3D object position. Therefore, we propose a novel keypoints uncertainty prediction network (KUP-Net) for monocular 3D object detection. In this work, we design an uncertainty prediction module to characterize the uncertainty that exists in keypoint prediction. Then, the uncertainty is used for joint optimization with object position. In addition, we adopt position-encoding to assist the uncertainty prediction, and use a timing coefficient to optimize the learning process. The experiments on our detector are conducted on the KITTI benchmark. For the two levels of easy and moderate, we achieve accuracy of 17.26 and 11.78 in AP3D, and achieve accuracy of 23.59 and 16.63 in APBEV, which are higher than the latest method KM3D.

An improved posture evaluation method of cylindrical intersecting holes on large aerospace component based on monocular vision

Cylindrical intersecting holes(CIHs) are common connection and location reference features in assembly of large aerospace structures such as missile and rocket cabins. The posture accuracy of assembly holes significantly impacts the relative position accuracy of joined parts and fatigue strength of finished product. At present, monocular vision measurement is widely used in automatic drilling of assembly holes for its integration simplicity and lower cost, but in most research, only the front face edge of the hole is used in the measurement model, and the hole end surface is usually assumed to be plane, which inevitably leads to precision loss. In this research, a novel posture measurement method for CIHs is proposed. Firstly, by introducing an ambiguity removal strategy, a coarse posture estimation method based on plane hypothesis of the two end surfaces of CIHs is suggested. Secondly, considering that there is no simply explicit expression for CIHs edge, thus it is difficult to adopt the conventional model projection based pose optimization method. In view of this, the three-dimensional points corresponding to the edge pixels of CIHs image are derived, and the pose optimization model is established by minimizing the deviations between the distance from the points to the CIHs axis and the hole radius. Moreover, to better control the direction parameters of CIHs during the global optimization process, the approximately perpendicular and intersection constraints between CIHs axis and cylindrical component axis are involved in solution. The effectiveness of the posture measurement method is verified by comparative experiments with current methods and CMM, which demonstrates improvements on both measurement accuracy and robustness.

An Efficient Vehicle Localization Method by Using Monocular Vision

Accurate localization of surrounding vehicles helps drivers to perceive surrounding environment, which can be obtained by two parameters: depth and direction angle. This research aims to present a new efficient monocular vision based pipeline to get the vehicle’s location. We proposed a plug-and-play convolutional block combination with a basic target detection algorithm to improve the accuracy of vehicle’s bounding boxes. Then they were transformed to actual depth and angle through a conversion method which was deduced by monocular imaging geometry and camera parameters. Experimental results on KITTI dataset showed the high accuracy and efficiency of the proposed method. The mAP increased by about 2% with an additional inference time of less than 5 ms. The average depth error was about 4% for near distance objects and about 7% for far distance objects. The average angle error was about two degrees.

A Marker-Less Monocular Vision Point Positioning Method for Industrial Manual Operation Environments

Vision-assisted technologies in industry such as Augmented Reality (AR) are increasingly popular. They require high positioning accuracy and robustness in industrial manual operation environments. However the narrow space and moving hands or tools may occlude or obscure local visual features of operation environments, affect the positioning accuracy and robustness of operating position. It may even cause misoperation of operators because of misguidance. This paper proposes a marker-less monocular vision point positioning method for vision-assisted manual operation in industrial environments. The proposed method can accurately and robustly locate the target point of operation using constraint minimization method even the target area has no corresponding visual features in the case of occlusion and improper illumination. The proposed method has three phases: intersection generation, intersection optimization and target point solving. In the intersection generation stage, a certain number intersections of epipolar lines are generated as candidate target points using fundamental matrices. Here the solving constraint is converted from point-to-line to point-to-points. In the intersection optimization stage, the intersections are optimized to two different sets through the iterative linear fitting and geometric mean absolute error methods. Here the solving constraint is converted from point-to-points to point-to-point sets. In the target point solving stage, the target point is solved as a constrained minimization problem based on the distribution constraint of the two intersection sets. Here the solving constraint is converted from point-to-point sets to point-to-point and the unique optimal solution is obtained as the target point. The experimental results show that this method has a better accuracy and robustness than the traditional homography matrix method for the practical industrial operation scenes.

Tractor-trailer-train braking time sequence detection based on monocular vision

The tractor-trailer-train at the braking process prone to braking instability caused by asynchronous braking between the shafts. With respect to the lack of intelligent detection of Braking Time Sequence (BTS), a non-contact dynamic detection scheme of intelligent vehicle BTS is proposed. Based on the monocular vision principle, the edge markers of tractor-trailer train tires are identified, and the tire slip rate is solved. The noise reduction of the collected image is processed. The marker area is obtained by Blob analysis. This region at the image to be matched is identified by the template matching algorithm based on contour. The camera is calibrated by Zhang’s calibration method. In order to verify the effectiveness of the detection scheme, the real vehicle test was carried out. The test results show that the error of slip rate solution is below 4.2%.