In the automatic welding process on mid/thick plates, the precision of the welding position has an important effect on welding quality, which mainly relies on the identification of the welding seam. However, due to some possible disturbances in complex unstructured welding environments, e.g., strong arc lights, welding splashes, thermal-induced deformations, etc., it is a great challenge to identify the welding seam. In this paper, we propose a robust automatic welding seam identification and tracking method by utilizing structured-light vision. First, after the preprocessing of the welding image, the gray distribution of the laser stripe is tracked and the profile of the welding seam is searched in a small area by using the Kalman filter, with the aim to avoid some disturbances. Second, in order to extract the welding seam profile, a series of centroids obtained by scanning the columns in the rectangular window are fitted using the least-squares method. Third, a character string method is proposed to qualitatively describe the welding seam profile, which might consist of different segment and junction relationship elements. And then, these character strings acquired from the object image are matched with those from the model, so that the position of the welding seam can be determined. Finally, the advantages of the new algorithm are testified and compared through several experiments.

Multiple robots collaboratively achieve a common coverage goal efficiently, which can improve work capacity, share coverage tasks, and reduce completion time. In this paper, a neural dynamics (ND) approach is proposed for complete area coverage navigation by multiple robots. A bioinspired neural network (NN) is designed to model the workspace and guide a swarm of robots for the coverage mission. The dynamics of each neuron in the topologically organized NN is characterized by an ND equation. Each mobile robot regards other robots as moving obstacles. Each robot path is autonomously generated from the neural activity landscape of the NN and the previous robot position. The proposed model algorithm is computationally efficient. The feasibility is validated by simulation, comparison studies, and experiments.

This paper presents a simple control method for the fully automatic parking of an unmanned vehicle. This method is based on the switching control algorithm and backstepping theory. The fully automatic parking is hard to accomplish since it cannot converge to a specified norm, guarantee the convergence rate, and large uncertainties. Global exponential convergence to any prescribed norm bound (e-convergence) is guaranteed, and the convergence rate is explicitly given. For the design of steering laws, a method based on backstepping is proposed and analyzed in detail. The backstepping-based design of a multichain system is obtained. Moreover, an exponentially e-convergent control algorithm is adopted to guarantee both converge norm and convergence rate. Real road experiment results are presented and the results show the effectiveness of the control strategies.

This paper presents a skill learning based hierarchical control strategy for human-robot cooperative manipulation, which constitutes a novel learning-control system. The high-level learning strategy aims to learn the motor skills from human demonstrations by fusion with dynamical motion primitives (DMP) and Gaussian mixture model (GMM). The lower-level control strategy guarantees the compliance of the robot movement under human interaction using admittance control and integral barrier Lyapunov function (IBLF) based adaptive neural controller. Firstly, the robot learns the motor skills from observing the successful execution of the tasks by demonstrator through DMP-GMM methods. Then, the robot reproduces the complex skills and executes the interactive task by demonstrations. Finally, the effectiveness of the proposed learning-control strategy is demonstrated with experimental results. The results show that the developed hierarchical strategy has good performance in cooperation by learning and control which reacts compliantly to robot interaction with human subjects.

Multi-sensor fusion strategies have been widely applied in Human Activity Recognition (HAR) in Body Sensor Networks (BSNs). However, the sensory data collected by BSNs systems are often uncertain or even incomplete. Thus, designing a robust and intelligent sensor fusion strategy is necessary for high-quality activity recognition. In this paper, Dezert-Smarandache Theory (DSmT) is used to develop a novel sensor fusion strategy for HAR in BSNs, which can effectively improve the accuracy of recognition. Specifically, in the training stage, the Kernel Density Estimation (KDE) based models are first built and then precisely selected for each specific activity according to the proposed discriminative functions. After that, a structure of Basic Belief Assignment (BBA) can be constructed, using the relationship between the test data of unknown class and the selected KDE models of all considered types of activities. In order to deal with the conflict between the obtained BBAs, Proportional Conflict Redistribution-6 (PCR6) is applied to fuse the acquired BBAs. Moreover, the missing data of the involved sensors are addressed as ignorance in the framework of the DSmT without manual interpolation or intervention. Experimental studies on two real-world activity recognition datasets (The OPPORTUNITY dataset; Daily and Sports Activity Dataset (DSAD)) were conducted, and the results showed the superiority of our proposed method over some state-of-the-art approaches proposed in the literature.

In the original belief function (BF) theory, a precise-valued belief structure has been widely used to represent uncertain information. However, this mentioned belief structure is difficult to effectively measure the specific hesitant situation, especially when decision makers have a set of possible values for the belief assignments of focal elements. In order to model the hesitant nature of the behavior of people to make a decision under uncertainty, we propose a hesitant fuzzy belief structure (HFBS) that is based on the BF theory and the recent hesitant fuzzy set theory. We also present the novel rule of combination of HFBS that is used and evaluated in a wearable human activity recognition (HAR) system coupled with an extreme learning machine. The evaluation of this new HFBS approach is done from two benchmark datasets. We clearly show its effectiveness and its superiority compared to various methods used classically for the wearable HAR.