Prefacedoi: 10.1088/1742-6596/2216/1/011001pmid: N/A
Due to recent pandemic, 2021 3rd International Conference on Robotics, Intelligent Control and Artificial Intelligence (ICRICA 2021) was held virtually online on December 03 - 05, 2021. The decision to hold the virtual conference was made in compliance with many restrictions and regulations that were imposed by countries around the globe. Such restrictions were made to minimize the risk of people contracting or spreading the COVID-19 through physical contact. There were 150 individuals who attended this on-line conference, represented many countries.ICRICA 2021 brings together industry professionals and academics from research institute, governmental agencies, and universities around the world to exchange information on advances in Robotics, Intelligent Control and Artificial Intelligence. The objective of the ICRICA 2021 is to facilitate the exchange between researchers and practitioners in the area of Robotics, Intelligent Control and Artificial Intelligence and related technologies, and provides attendees with a unique opportunity to share, discuss, and witness research results, thereby creating a common platform for exchanging ideas and fostering future developments in the field.During the conference, the conference model was divided into three sessions, including oral presentations, keynote speeches, and online Q&A discussion. In the first part, some scholars, whose submissions were selected as the excellent papers, were given about 5-10 minutes to perform their oral presentations one by one. Then in the second part, keynote speakers were each allocated 30-45 minutes to hold their speeches. In the second part, we invited three professors as our keynote speakers. Prof. Rüdiger Dillmann, Karlsruhe Institute of Technology, German (IEEE Fellow, IROS Fellow). His research interest is in the areas of humanoid robotics and neurorobotics with special emphasis on intelligent, autonomous, and interactive robot behavior generated with the help of machine learning methods and programming by demonstration (PbD). The second keynote speakers, Prof. Xiaofang Yuan, Hunan University, China. His research area includes intelligent control theory and application, electric vehicle control, robot drive control. Lastly, we were glad to invite Prof. Hui Zhang, Hunan University, China as our finale keynote speakers. He is mainly engaged in the research of intelligent robot vision detection, deep learning image recognition and other fields. Their insightful speeches had triggered heated discussion in the third session of the conference. Every participant praised this conference for disseminating useful and insightful knowledge.The proceedings are a compilation of the accepted papers and represent an interesting outcome of the conference. Topics include but are not limited to the following areas: Robot structure design and control, Sensor/actuator networks, Robot kinematics and dynamics, Robot operating system and other related topics. All the papers have been through rigorous review and process to meet the requirements of international publication standard.List of Committee member are available in this pdf.
A Fast Path Planing Solution For Multiple Obstacle SpacesChen, Xiaolei; Shen, Haoyang; Yuan, Junling; Han, Lu
doi: 10.1088/1742-6596/2216/1/012057pmid: N/A
Among the many path planning algorithms, the RRT* algorithm and the Informed RRT* algorithm are the most popular. Both of them can complete the single path planning effectively. However, because the planning effect of these algorithms is limited by the number of iterations, the optimal solution cannot be planned in a limited time. Therefore, a new algorithm-Self-Optimizing Growing Tree (SOGT) is proposed in this paper. On the premise of ensuring complete probability, heuristic bias sampling is used to improve the efficiency of the algorithm to explore free space. Then, the initial path is optimized by the maximum distance and the inflection point optimization using prior information to obtain an optimal path. In the simulation experiments, we give the comparison results of numerical simulations of SOGT algorithm, RRT* algorithm and Informed RRT* algorithm. The experiment proves that the SOGT algorithm can get an optimal path in less time, which fully reflects the characteristics of the algorithm with good real-time performance and strong adaptability.
Improve the spot-like coding detection of U-net auto-encoderLiu, Beibei; Hu, Weiping; Li, Fan
doi: 10.1088/1742-6596/2216/1/012095pmid: N/A
The dot-like spray code on the product packaging has always been a difficult problem in industrial inspection due to its complicated background in the printing area, diverse characters in the code, and changeable fonts. With the powerful capabilities of deep learning in the field of computer vision, related algorithms have become popular solutions in the field of computer vision in recent years. The method based on convolutional autoencoders to achieve inkjet detection on food packaging boxes has become a feasible solution. This method takes the mask of the coding character area on the food packaging box as the final goal of network learning. The network inputs the picture with the coding area, and reconstructs the original background of the coding area. At the same time the network uses the residual channel attention mechanism to restore the details of the image, and at the same time introduces the gaussian operator to calculate the loss of network reconstruction. Since the convolutional auto-encoder is an unsupervised learning method, the training data does not require a large amount of manual labeling, and a good solution is proposed for scenarios such as small data sets in industrial production and difficulty in labeling. Through real-time testing of the coding data of the pipeline, it is verified that the method can effectively detect the coding area.
A composite image recognition based approach for spontaneous combustion point detection and positioning in coal pilesWu, Fuhui; Zhou, Zhihao; He, Xingwei; Wang, Zhan; Li, Junhai; Ruan, Yaliang; Lei, Hao
doi: 10.1088/1742-6596/2216/1/012100pmid: N/A
The phenomenon of spontaneous combustion of coal piles often occurs in closed coal yards of power plants, automatic fire-fighting equipments are generally used to detect and locate the spontaneous combustion point. However, their performance (false alarm rate) are largely limited due to the complicated environment of the coal yard. To deal with this problem, this paper proposes a composite image recognition based method for detecting and positioning the spontaneous combustion point (SCP) in coal yard. Yolov5s is trained to efficiently detect SCPs and infrared information is fused to distinguish the realiability of SCP detection result via composite image registration method. In addition, an angle compensation algorithm is proposed to adjust the spray angle of the equipment for positioning the cooling area. The experimental results show that after integrating the above related technologies, the false alarm rate of the spontaneous combustion point in the scene is greatly reduced, and the work efficiency is effectively improved.
Path planning of mobile robots based on improved RRT algorithmLiu, Benxue; Liu, Chong
doi: 10.1088/1742-6596/2216/1/012020pmid: N/A
Aiming at the shortcomings of RRT (Rapidly-exploring Research Tree) algorithm such as long time cost and low utilization of sampling points, an improved RRT algorithm is proposed. By adopting the sampling strategy based on dynamic probability, the robot is prevented from falling into a local minimum during the sampling process. At the same time, the adopt of variable step strategy as the random tree expands reduces the number of sampling points. Finally, the initial path is optimized to make it more suitable for the robot to walk. The improved RRT algorithm is compared with the RRT algorithm and the Goal-bias RRT algorithm in both simulations on MATLB and experiments on robot based on ROS (Robot Operating System). And the results show that improved RRT algorithm increases the speed of path planning, reduces the length of path, and the planned path is smoother and more suitable for the real robot to move.
Research on Job-shop Scheduling Problem Based-on Improved Genetic AlgorithmWei, Bo; Qi, Jiayuan; Wen, Jiafu
doi: 10.1088/1742-6596/2216/1/012083pmid: N/A
Considering minimizing completion time and maximizing equipment utilization of job shop scheduling problem, an improved genetic algorithm was proposed. First, constructing a two-layer chromosome coding structure, with which the initial population quality and the diversity of the population were strengthened and improved. Next, in order to enhance the local search ability and improve the algorithm convergence speed, the population generated after selection, crossover, and mutation was divided into families, and the elite population were combined with explosive fireworks of the firework algorithm. Then, in order to prevent the algorithm from maturing prematurely, the disadvantaged groups were mutated through(by) the dynamic mutation mechanism to narrow the gap between the super individual and the average. Last, the parameters of the algorithm were optimized by orthogonal tests, and performance of the algorithm was verified by classical test examples.
Temporal Logic Control Synthesis for Distributed Multi-Agent Cooperative TaskingXu, Ning; Peng, Ting; Liu, Dawei; Li, Jie
doi: 10.1088/1742-6596/2216/1/012061pmid: N/A
In this work, we present a novel control synthesis method for cooperative multi-agent systems to fulfill a global mission given as linear temporal logic on finite traces (LTLf). The proposed method first synthesizes satisfiable global controllers for uncontrolled system, such that the global specification is met; and then, searches for a decomposable global controller among them over a maximum synchronization scheme; finally, further refining the synchronization scheme to obtain decomposed distributed controllers. To search for a decomposable global controller among the satisfiable ones, we present an informed searching algorithm based on the decomposability analysis of global controllers. A multi-UAV cooperative fire surveillance scenario is developed to illustrate the method.
Asynchronous Federated Learning for Elephant Flow Detection in Software Defined Networking SystemsMa, Xiaohang; Liao, Ling Xia; Li, Zhi; Chao, Han-Chieh
doi: 10.1088/1742-6596/2216/1/012085pmid: N/A
This paper introduces an Asynchronous Federated Learning (AFL) approach to train an elephant flow model over Software Defined Networking (SDN) systems with distributed controllers. The AFL addresses the issues of data privacy and communication overhead in collecting network statistics over large-scaled SDN systems. It allows each local controller to train a local model based on its local statistics using Decision Tree and upload the local model to the root in an asynchronous manner, so that the root controller can aggregate each local model into a global model once a local model is received to improve its time efficiency. The AFL proposes to weight the performance of each local model to form the global model. The evaluation based on 5 real packet traces demonstrates the accuracy of the AFL is better than any local models and two classical federated learning approaches.