Multi-agent robotic system (MARS) for UAV-UGV path planning and automatic sensory data collection in cluttered environments

This paper is introduced to be the obstacle recognition, path planning and oscillating control for an automobile crane system on-line. We studied the autonomous mobile overhead traveling crane so for. In particular, the research of obstacle recognition, path plan and oscillating control is carried out. For on-line obstacle recognition, the obstacle recognition system using the ultrasonic sensor(USS) is built. And on-line partial obstacle recognition of the conveyance environment is carried out using this obstacle recognition system. For an on-line path planning, the path plan system which it could process with the information of transfer object position and the obstacle position that is recognized by obstacle recognition system in a short time was built. The feedback transfer control system in consideration of oscillating control is built. Finally, the usefulness of the system that these were integrated is proved by an experiment. Keywords-component; Automation, Mobile Robot, Overhead Traveling Crane, On-line Path Planning, Oscillating control. I. INTORODUCTION OF THIS PAPER An overhead traveling crane system has an advantage of selecting 3rd-dimentionally and freely a transfer path achieving a freedom thereof. Therefore, automation and autonomy thereof is desired to increase the operational freedom of FMS(Flexible Manufacturing System). In the present, the overhead traveling crane is mainly operated by an expert operator to ensure safety during transferring. The development of an autonomous mobile overhead traveling crane is necessary for problem of the lack of skillful operators or the problem of work efficiency. For the reason, the results of research about an autonomous mobile overhead traveling crane system are presented by us[1],[2],[4],[5]. In particular, our research for path planning was conducted from various points of view[1],[2],[4],[5]. In a past research, we has made an experimental apparatus of on overhead traveling crane shown in Fig.1, and an autonomous mobile traveling crane system with function of the obstacle recognition, path planning on-line and oscillation control has been constructed. In this visual and planning system, when there was the change of an obstacle conveying, it was necessary for the path plan to be handled in a short time and had a problem with on-line processing in a conventional study. And the path planning system is constructed[2], [4],[5]. We propose the path-planning system that can be quickly carried out with an easy algorithm on-line. The proposed online path planning system is built using two-dimensions pathplanning algorithm[3] to perform a three-dimensional path planning[4],[5]. In this proposed system, path planning can be derived by information of target position and any obstacle position that is recognized by an ultrasonic sensor (USS). This on-line path plan method performs a path plan by the partial information of a transportation environment recognized by USS of the obstacle recognition system during transfer. The path plan of the overhead traveling crane is constructed to the goal position by repeating a suggested process (algorithm). Furthermore, the inspection of the proposed path planning method was evaluated from a view point of a qualitative and a quantitative[5]. In the present condition, the transfer control system in consideration of oscillating control was a feed-forward control system which using the notch filter. Therefore this control system had the problem that oscillating control was not completed when there was remains vibration at the time of change of a path. In this paper, 2 degrees of freedom control system which added the feedback control system to the present control system are designed. And the purpose of this research is to verify the usefulness of the on-line obstacle avoidance of the proposed autonomous mobile overhead traveling crane system. 2nd International Symposium on Computer, Communication, Control and Automation (3CA 2013) © 2013. The authors Published by Atlantis Press 468 Fig. 2 Obstacle recognition system

Background/Objectives: Multi-agent Robotic Systems (MRS) with supervisory control can solve important practical tasks. For efficient MRS operation it is required to provide high speed (over 1 Gb/s) wireless communication between its agents. Methods: The implementation of the required high-speed data interchange in a multi-agent system is only possible when using wireless optical links. Low divergence of laser radiation is an important advantage of these lines, but it greatly complicates the task of establishing and reconfiguring optical information systems. Findings: The paper discusses possible algorithms for solving problems of the establishment and reconfiguration of an optical information system with respect to MRS, which is being developed within the framework of an applied research funded by the Ministry of Education and Science of the Russian Federation. Improvements/Novelty: By means of dynamic reconfiguration of the network the proposed algorithms for optical information network construction enable to provide reliable data transfer between the MRS agents at their mutual movement and link loss variation.

Assisting elderly individuals in indoor environments is crucial, as they often encounter mobility and safety challenges. Autonomous Unmanned Aerial Vehicles (UAVs) navigation offers a transformative solution, significantly enhancing safety, efficiency, and quality of life. These UAVs can perform tasks such as monitoring, delivering essential items, and responding to emergencies, providing invaluable support and promoting greater independence for elderly individuals. To achieve effective assistance, autonomous UAV navigation relies on robust path planning with obstacle avoidance to ensure optimal performance. A newly developed path planning, based on a new hybrid Water Cycle Algorithm (WCA), stands out by addressing the challenge of avoiding obstacles while adhering to non-holonomic constraints and conserving energy in complex, cluttered indoor environments. In Population-Based Algorithms (PBAs), the initial population plays a crucial role, as it greatly impacts the algorithm’s efficiency in exploring the search space and its rate of convergence. The new developed hybrid algorithm, called WCA-HS, is based on using the Harmony Search (HS) algorithm to identify the optimal initial population for the WCA. The results indicate that the hybrid WCA-HS outperforms classical WCA and other metaheuristic algorithms, such as HS, Firefly Algorithm (FA), Cuckoo Search (CS), Genetic Algorithm (GA), Differential Evolution (DE), Ant Colony Optimization (ACO), and Artificial Bee Colony (ABC), over 20 independent runs, highlighting the effectiveness of the population initialization technique. Additionally, the developed indoor path planning system was evaluated in highly cluttered and low-light environments, showcasing its robustness and real-world applicability, making it highly effective for assisting elderly individuals in complex indoor environments.

This paper proposes a methodology for developing multi-agent systems. Several design considerations for robotic agents are discussed. A script specifies a multi-agent system by defining the behavior of each agent. An agent is modeled by an extended finite state automaton. By using the state transition rules as the building blocks, an agent as well as a multi-agent system can be developed efficiently. This methodology is further applied to multi-agent robotic systems in which reactivity and interaction are important issues. A script-based architecture is developed to implement the agents in multi-agent robotic systems. This architecture considers not only the control architecture of a single agent, but also the interactions among multiple agents and their environments. A script for the object-sorting task problem is utilized for demonstration.

홈 서버와 가정용서비스 로봇, 다양한 Device를 포함하는 홈 네트워크 시스템을 이용하여 가정환경 내에서 발생 가능한 다양하게 분산된 임무들을 수행하는데 있어서 Multi-Agent 시스템을 응용하는 것은 효율적이라고 알려져 있다. 이러한 시스템에서 휴먼 인터페이스와 물리적 서비스 제공의 중추 역할을 하는 것은 바로 지능형 서비스 로봇이다. 따라서, 기존의 Multi Agent System을 응용하여 Multi Agent Robot System을 정의할 수 있다. 가정이라는 'open'된 특성의 환경에서 Multi Agent Robot System이 사용자에게 좀 더 효율적인 서비스를 제공하기 위해서는 존재하는 모든 Agent 간의 유기적인 정보교환과 협력이 필요하다. 이것을 위하여 자율구동하며 사용자에게 물리적 서비스를 제공할 수 있는 다수의 로봇들을 Agent로 정의하고, 로봇 Agent간의 통신과, 로봇 이외의 Agent로써의 역할을 감당할 수 있는 홈 서버 등의 Agent와 로봇 Agent들의 통신을 사용자 interface에 직접 표현할 수 있는 시뮬레이터를 설계, 제시한다. Using home network system including home server, home service robot, a variety of device, it is generally known that application of Multi Agent System for performing variously distributed process that can be occur in home environment, is efficient method. In this system, it is intelligent service robot that a key of human interface and physical service offer Therefore, using application of established multi agent system, we can defined Multi Agent Robot System. In 'open' home environment, between all agent data interaction and cooperation are needed for Multi Agent System offer to user that more efficient service. For this, we focus our attention on define as agent that can autonomic drive and offer to user that physical service robots and, design, suggest the simulator can display that between robot agents communication or between other agents, like home server, and robot agents communication information to user interface.

In the path planning of UAVs, autonomous decision-making and control are challenging tasks in the uncertain 3D environment consisting of static and dynamic obstacles. Hence, the selection of appropriate path-planning approaches is essential. In the proposed work, we have considered the meta-heuristic approaches only for an in-depth review. Metaheuristic approaches have been remarkably known for solving complex problems, optimal solutions, and lesser computational complexity compared to deterministic approaches that produce an inefficient solution. An in-depth review has been made by considering the approaches used for path planning, their advantages, disadvantages, applications, the type of time domain (offline or online), type of environment (simulation or real time), hybridization with other approaches, single or multiple UAV system, and obstacle handled (static or dynamic). It is observed that current meta-heuristic methods face constraints like inadequate convergence rates, entrapment in local optima, and complex operations, necessitating continuous development of novel approaches. Implementation of path-planning approaches are very much limited to simulation study over experimental analysis. Hybrid algorithms emerge as a potential solution for tackling these hurdles and optimizing UAV navigation, particularly in dynamic environments involving multiple UAVs. The paper highlights key research gaps, trends, along with prospects in the field of research.

In multi-agent robotic systems, the overlap of actions selected by each agent results in poor cooperation, while, at the same time, conventional reinforcement learning entails a large computational cost because every agent must learn. In this paper, we propose a novel method to solve these problems. The agent uses a rule set to conduct its behavior. Our system consists of reinforcement learning with an Action Selection Priority Level (ASPL) module and a generalized rules module. Using the ASPL, the reinforcement learning module chooses a proper cooperative behavior while the generalized rule module can accelerate the learning process. By applying the proposed method to robot soccer, the learning process can be accelerated by reducing the search space. The results of simulation and real experiments indicate the effectiveness of the proposed method.

Multi-agent Robots Systems (MARS) can be defined as sets of autonomous robots coordinated through a communication system to achieve cooperative tasks. During the last 20 years, MARS have found a wide range of applications in terrestrial, spatial and oceanic explorations emerging as a new research area (Cao et al. (1997)). Some advantages can be obtained from the collective behavior of MARS. For instance, the kind of tasks that can be accomplished are inherently more complex than those a single robot can accomplish. Also, the system becomes more flexible and fault-tolerant (Yamaguchi (2003)). The range of applications includes toxic residues cleaning, transportation and manipulation of large objects, alertness and exploration, searching and rescue tasks and simulation of biological entities behaviors (Arai et al. (2002)). The study ofMARS extends the classical problems of single robotswith new issues likemotion coordination, task decomposition and task assignment, network communications, searching and mapping, etc. Therefore, the study of MARS encompass distributed systems, artificial intelligence, game theory, biology, ethology, economics, control theory, etc. Motion coordination is an important research area of MARS, specifically formation control (Chen & Wang (2005)). The main goal is to coordinate a group of mobile agents or robots to achieve a desired formation pattern avoiding inter-agent collisions at the same time. The formation strategies are decentralized because it is assumed that every agent measures the position of a certain subset of agents and, eventually, it detects the position of other agents when a minimal allowed distance is violated and collision danger appears. Thus, the main intention is to achieve desired global behaviors through local interactions (Francis et al. (2004)). Also, the decentralized approaches offer greater autonomy for the robots, less computational load in control implementations and its applicability to large scale groups (Do (2007)). According to Desai (2002); Muhammad & Egerstedt (2004), the possible inter-agent communications and the desired relative position of every agent with respect to the others can be represented by a FormationGraph (FG). The application of different FG’s to the same group of robots produces different dynamics on the team behavior. In the literature, some special FG topologies are chosen and the convergence to the desired formation and non-collision is analyzed for any number of robots. A decentralized formation strategy must comply with two fundamental requirements: Global convergence to the desired formation and inter-agent collision avoidance (Cao et al. (1997)). 6

This paper addresses the leader–follower consensus control problem for a nonlinear multi-agent robot system with control input constraint and external disturbances. Robot system is one of the most important practical systems in the industry. Due to the presence of disturbances in most practical systems, this paper considers the issue of finite-time leader–follower consensus control of the nonlinear multi-agent robot system along with actuator saturation and bounded disturbance. The modified terminal sliding mode control method is suggested for the system which is able to guarantee the stability of the overall system and fast finite-time leader–follower consensus control. For two different scenarios, the simulation of multi-agent robot system has been performed. The results show the effectiveness of the proposed control method.

A smart mobility platform aiding in guidance of disabled people is a concept that can facilitate people’s everyday life. However, design and manufacturing of such a system faces many issues in terms of agility in design, implementation and usability verification. To this end, the concept of Product-Service System (PSS) seems to be the solution; being an emerging concept oriented towards the dematerialisation of the economy, meeting also the requirement of manufacturing industries to cope with the radical changes in the global market. In this study, the development of a context awareness and path planning system under the prism of PSSs is examined. This module is considered to be promoted as a pay per service unit that can be implemented in different operational scenarios and environments. The key objective is to deliver the obstacle avoidance and path planning functionality and add value to the customer, but at the same keep the production lean and flexible. To this end, Round Robin parts are presented, taking into account mounts and jigs for controllers dealing with supervised machine learning techniques and path planning, light-weight system-of-sensors and structural integrity of the module. The concept evaluation is outlined through a case study based on the integration of the system in a smart mobility platform to provide autonomous mobility. The mobility platform is expected to operate within a predefined area, characterized by a complex environment.

Recently, autonomous systems in agriculture have garnered increased attention among research communities and industries due to their greater significance. With rapid technological advances, numerous autonomous systems have been actively deployed in agriculture to accomplish complex tasks, such as surveying agricultural fields, managing the water cycle, resolving soil compaction issues, etc. Swarm robotics, path planning, and task assignment systems play a crucial role in agricultural automation and pave the way for smart, sustainable agriculture. However, the major problem here is that this system depends on dynamic path planning activities, which are the most crucial task for autonomous robots. This is because in smart agriculture, multiple agents are associated with the system to perform various activities on their way to the destination, making the path planning actions more complicated than ever. To address these constraints, this paper presents a cost-efficient, reliable, and safe navigable swarm approach, called the Self-Supervised Learning Graphical Neural Network Driven Prediction Model (SGNN), for smart sustainable agriculture. The proposed SGNN approach enables swarm robots to select the most optimized paths, thereby reducing the distance travelled by the robots. The work’s prime focus is on developing a forecasting model for the efficient navigation and landing of swarm robots in innovative agricultural systems. The Semantic Drone Dataset is used for experimentation purposes. It is observed from the analysis that the proposed approach offers more than 85% percent accurate results in comparison to standard ResNet architectures. Additionally, this approach yields a score of around 0.8, indicating a good balance between precision and recall measures. Further, the result suggests a correlation coefficient factor of around 0.685, representing the effective classification of the target classes. Thus, the proposed SGNN approach has been experimentally proven to be more robust and efficient than existing approaches.

This article presents an innovative approach to mobile robot path planning and control systems specifically designed for cancer detection and treatment applications in medical environments. This article introduces a novel prioritized path-planning algorithm that enables multiple robots to navigate collision-free while maintaining precise coordination during medical procedures. The system architecture integrates advanced technologies, including ATL COM/VC++ components, digital/analog interfacing, and COM/.NET interoperable objects with C# user controls and XML for comprehensive machine management. This article incorporates fuzzy logic and machine learning techniques for intelligent collision avoidance, alongside artificial neural networks and generative AI models for pattern classification and forecasting. The implementation leverages multiple communication protocols, including TCP/IP, RS232, CAN, and USB, to ensure robust connectivity across all system components. Extensive testing through black/white box methodologies, regression testing, and simulation of pneumatic, hydraulic, and PLC components demonstrates the system's reliability and precision. This article shows significant improvements in path planning efficiency, control system response times, and overall system reliability compared to existing solutions. This article suggests that this integrated approach not only enhances the accuracy of cancer detection and treatment procedures but also provides a scalable framework for future medical robotics applications. The system's successful validation in clinical settings indicates its potential for widespread adoption in medical facilities, marking a substantial advancement in automated medical robotics.

In this paper, a vision‐based navigation system including support vector machine (SVM) path planner and fuzzy sliding‐mode controlled (SMC) path follower is developed for a wheeled agent. The developed system, comprising image acquisition, map formatting, path planning, label assignment, and path tracking inference mechanisms, aims to gracefully follow a planned smooth path. To obtain accurate coordinate values, the captured images are first adjusted by calibration processing. As a roadmap method for path generation, theVoronoi diagram is employed as a preprocessor and theGaussian kernelSVMpostprocessor is applied consecutively. To deal with the uncertainties, a path follower based on fuzzySMCis embedded to track the planned path on line. In this study, a practical framework is implemented to assess the performance. With the real devised system, a series of experiments are carried out and analyzed to confirm the expected performance. The experiments show a robust capability of the system for both path planning and path tracking under various obstacle layouts.

In laboratory automation, more and more mobile robots have been employed for kinds of transportation among distributed automated ‘islands’. To direct those mobile robots effectively, in this paper a standard robot path planning system (RPPS) has been developed. In the RPPS: (a) to let the RPPS suit for any kind of mobile robots and any size laboratory, a TCP/IP based Client/Server architecture is adopted. A new robot distributed for a new laboratory can be added to the RPPS conveniently with a new IP; (b) an independent Robot Board Center (RBC) is developed for every robot. So even a robot loses its connection to a Robot Remote Center (RRC), it still can finish a given P2P task rightly; (c) to provide flexible robot paths for mobile tasks with different destinations, a map based path planning method is proposed. The map is comprised of waypoints which can be initialized quickly using a RBC. To calculate the shortest path for every P2P task, a hybrid calculation method based on Floyd algorithm and Genetic algorithm is designed; (d) to get low cost and extendable robot indoor localization for a large environment, a ceiling landmark localization is utilized; and (e) to avoid solving the complicated kinematic models for robot arm control, a way using a training arm is presented. Two experiments show that the proposed RPPS is effective for mobile robots in laboratory automation.

Distributed autonomous robotic systems exhibit complex behavior that-although programmed, but due to the impact of the environment- only materializes as the process unfolds. Thus, the actual behavior of such a system cannot be known in advance but must be observed to be evaluated or verified. In this paper we propose to use process mining techniques to extract, compare, and enhance models of the actual behavior of a multi-agent robotic system through analyzing collected log data. We use the example of robot soccer as such a multi-agent robotic system, and we demonstrate which types of analysis are currently possible in the context of the process mining tool set ProM.