Defects on rail surfaces, which have become critical problems, need to be detected and removed as quickly as possible to ensure the fast, safe, and stable operation of trains. At present, although many solutions have been proposed to address these problems, the comprehensiveness, rapidity, and accuracy of defect detection remain unsatisfactory. This study aims to resolve these existing problems and accordingly proposes a multi-model rail surface defect detection system based on convolutional neural networks (MRSDI-CNN) from the standpoint of studying the squat on the rail surface. The convolutional neural networks utilized include the improved Single Shot MultiBox Detector (SSD) and You Only Look Once version 3(YOLOv3)—two types of one-stage networks. We expounded and analyzed the performance of the convolutional neural networks as well as their applicability to rail surface defect detection. We used a diverse range of rail defect sizes to improve the detection performance of the two deep learning networks, following which they could identify three types of squats in parallel with improved accuracy and without reduction of the detection speed. The experimental results confirm the effectiveness and superiority of the proposed method over those of previous studies.

The pose estimation is the critical technology in industrial robot. Nowadays, many machine vision-based approaches have applied the technology and achieved excellent results. However, the rapid detection of the pose estimation in complex multiscene environments is still a challenge, due to the interference of multiangle light and multibackground. To address these issues, this article proposes a practical robotic grasping method by using the 6-D pose estimation with protective correction. In this method, the synthetic dataset by self-production is used to train the improved deep object pose estimation network and then use the standard perspective-n-point algorithm to estimate the 6-DoF pose for each object instance. Meanwhile, in order to prevent grasp collisions cause by misrecognition, we propose the corrected grasping pose algorithm for protective correction by measured translation and predicted translation. Finally, the proposed grasping method has an average grasping success rate of 83.3% for the three objects under normal light, and the network for single-image detection speed has been to 1.490 frames/s. The code is available at https://github.com/aimiplus/Practical_Robotic_Grasping_Method .

Purpose: This paper aims to solve the problem between detection efficiency and performance in grasp commodities rapidly. A fast detection and grasping method based on improved faster R-CNN is purposed and applied to the mobile manipulator to grab commodities on the shelf.Design/methodology/approach: To reduce the time cost of algorithm, a new structure of neural network based on faster R CNN is designed. To select the anchor box reasonably according to the data set, the data set-adaptive algorithm for choosing anchor box is presented; multiple models of ten types of daily objects are trained for the validation of the improved faster R-CNN. The proposed algorithm is deployed to the self-developed mobile manipulator, and three experiments are designed to evaluate the proposed method.Findings: The result indicates that the proposed method is successfully performed on the mobile manipulator; it not only accomplishes the detection effectively but also grasps the objects on the shelf successfully.Originality/value: The proposed method can improve the efficiency of faster R-CNN, maintain excellent performance, meet the requirement of real-time detection, and the self-developed mobile manipulator can accomplish the task of grasping objects.

A mobile robot uses an odometer system for localization, and uses a lidar sensor to obtain environmental information, to complete the process of Simultaneous Localization and Mapping (SLAM). This paper proposes an efficient Double Simultaneous Majorization Particle Filter (DSM-PF) algorithm, which is based on the majorization of the Rao-Blackwellized Particle Filtering (RBPF) method. The main purpose of the algorithm is to improve the accuracy of particle pose and maintain the weight of particles, to improve the quality of the results. For the motion distortion generated by the mobile robot, a particle pose majorization algorithm is proposed to improve the localization accuracy of the robot while in motion. At the same time, a weight majorization algorithm is proposed to maintain the weight of each particle, slow down the degradation of particles and improve the accuracy of the map carried by particles. In addition, for different particles that require resampling, an adaptive hierarchical resampling method is performed to maintain particles with higher weights. In this paper, the feasibility of the proposed algorithm is verified in different indoor environments. The experimental results show that the algorithm can slow down the degradation of particles and prevent the number of particles from declining. What is more, the experimental results of particle resampling show that the proposed algorithm has better mapping ability.

The actuator dead zone of free-form surface grinding robots (FFSGRs) is very common in the grinding process and has a great impact on the grinding quality of a workpiece. In this paper, an improved trajectory tracking algorithm for an FFSGR with an asymmetric actuator dead zone was proposed with consideration of friction forces, model uncertainties, and external disturbances. The presented control algorithm was based on the machine learning and sliding mode control (SMC) methods. The control compensator used neural networks to estimate the actuator’s dead zone and eliminate its effects. The robust SMC compensator acted as an auxiliary controller to guarantee the system’s stability and robustness under circumstances with model uncertainties, approximation errors, and friction forces. The stability of the closed-loop system and the asymptotic convergence of tracking errors were evaluated using Lyapunov theory. The simulation results showed that the dead zone’s non-linearity can be estimated correctly, and satisfactory trajectory tracking performance can be obtained in this way, since the influences of the actuator’s dead zone were eliminated. The convergence time of the system was reduced from 1.1 to 0.8 s, and the maximum steady-state error was reduced from 0.06 to 0.015 rad. In the grinding experiment, the joint steady-state error decreased by 21%, which proves the feasibility and effectiveness of the proposed control method.