Multi-robot cooperation in the MARTHA project

We present and discuss the use of a generic scheme for multi-robot cooperation called the for managing a large fleet of autonomous mobile robots. Each robot, autonomously and incrementally builds and executes its own plans taking into account the multi-robot context obtained by collecting the current plans and goals of the other robots. We describe the overall system architecture and discuss the properties of our cooperative scheme. We show how the plan-merging paradigm (PMP) can be used in a hierarchical manner and how it fills the gap between centralized planning and distributed execution. We finally illustrate this scheme through an implemented system which allows a fleet of autonomous mobile robots to perform load transfer tasks in a route network environment. The central activity is limited to task allocation and important gains are obtained in system flexibility and robustness to execution contingencies. Simulations (using up to 30 robots) as well as experiments with real robots (3) are presented and discussed.

This paper presents an implemented system which allows one to run a fleet of autonomous mobile robots in a route network with a very limited centralized activity. The robots are provided with all the necessary ingredients for planning and executing navigation missions in a multi-robot context. Multi-robot cooperation is based on a generic paradigm called plan-merging paradigm, where robots incrementally merge their plans into a set of already coordinated plans. The robot architecture is derived from the generic architecture developed at LAAS. A 3D graphic environment system allows one to display a complete system composed of a dozen (or more) robots, each running on an independent workstation. An example is presented together with numerical results on the system behavior.

Controlling a fleet of autonomous mobile robots (AMR) is a complex problem of optimization. Many approached have been conducted for solving this problem. They range from heuristics, which usually do not find an optimum, to mathematical models, which are limited due to their high computational effort. Machine Learning (ML) methods offer another potential trajectory for solving such complex problems. The focus of this brief survey is on Reinforcement Learning (RL) as a particular type of ML. Due to the reward-based optimization, RL offers a good basis for the control of fleets of AMR. In the context of this survey, different control approaches are investigated and the aspects of fleet control of AMR with respect to RL are evaluated. As a result, six fundamental key problems should be put on the current research agenda to enable a broader application in industry: (1) overcoming the “sim-to-real gap”, (2) increasing the robustness of algorithms, (3) improving data efficiency, (4) integrating different fields of application, (5) enabling heterogeneous fleets with different types of AMR and (6) handling of deadlocks.

Industrial maintenance is undergoing a process of digitalization and automation through the use of Industry 4.0 technologies. An example is the employment of digital twins which allow virtualizing assets such as a fleet of Autonomous Mobile Robots (AMR) . In this paper, we analyze two local navigation algorithms for AMRs navigation in a digitized environment: Dynamic Window Approximation (DWA) and Time Elastic Band (TEB) . For this purpose, a digital twin is implemented in the ROS ecosystem. In this environment, a combined mission of a fleet of three AMRs is simulated where they navigate together in order to compare the behavior of the algorithms in dynamic industrial environments. As a result, the trajectories of each AMR that are key for production cost planning are analyzed. Finally, we introduce in this work a web server to interact with the developed digital twin facilitating its use.

Systems composed of a fleet of autonomous mobile robots are among the most complex control systems. This control complexity is at a high level especially when those robots navigate in hazardous and dynamic environments such as chemical analysis laboratories. These systems include different dangerous and harmful products (toxic, flammable, explosive...) with different quantity. In order to perform its mission on a regular basis, this multi-robot system can be controlled according to multiple architectures. We propose, firstly, to apply the System Theoretic Process Analysis (STPA) on two selected control architectures, namely distributed and hybrid architectures in order to obtain a set of loss scenarios for each kind of architecture. For further assessment, the Analytic Hierarchy Process (AHP) is used to choose the best architecture. The proposed approach provides a risk analysis and a more practical comparison between the two control architectures of a mobile multi-robot system and facilitates decision-making, even in complex situations.

Many robotics applications involve navigating to positions specified in terms of their semantic significance. A robot operating in a hotel may need to deliver room service to a named room. In a hospital, it may need to deliver medication to a patient's room. The Building-Wide Intelligence Project at UT Austin has been developing a fleet of autonomous mobile robots, called BWIBots, which perform tasks in the computer science department. Tasks include guiding a person, delivering a message, or bringing an object to a location such as an office, lecture hall, or classroom. The process of constructing a map that a robot can use for navigation has been simplified by modern SLAM algorithms. The attachment of semantics to map data, however, remains a tedious manual process of labeling locations in otherwise automatically generated maps. This paper introduces a system called PRISM to automate a step in this process by enabling a robot to localize door signs – a semantic markup intended to aid the human occupants of a building – and to annotate these locations in its map.

A fleet of autonomous mobile robots are used in the hospital for the delivery service. To increase the efficiency of using multiple robots, an appropriate task allocation algorithm is required. This paper explains the task allocation procedure for multiple robots and introduces two multi-task allocation (MT) algorithms to be applied in the hospital delivery service. The algorithms are tested via simulation, and the performance are compared according to the criteria. The result shows that proposing combinatorial search algorithm with limited capacity performed better among others.

The construction of a smart autonomous mobile robot system that can operate in an anonymous environment can be difficult. Building an autonomous mobile robot requires collecting data from sensors and cameras in order to recognize the surrounding environment, get knowledge of existing landmarks, and figure out its position and orientation. Many research studies have been carried out in recent years providing algorithms for achieving autonomous motion of mobile robot systems and object detection. The most common platform utilized for robot motion design is ROS (Robot Operating System) and for object detection YOLO (You Only Look Once) is a common choice. Additionally, the autonomous system needs motion planning in a systematic way to avoid obstacles by using LIDAR or other sensing methods generating the feedback signals required for control of motion around occupied spaces. One of the most effective and versatile feedback systems for mobile robot control can be constructed using visual feedback, which relies on a high-resolution camera that processes the image in real-time and the result is fed back to the control system for decision making. Visual feedback can be employed alone without sensors for feedback control of autonomous mobile robots, and it can be used for multiple tasks like path planning, obstacle avoidance, object detection, object recognition in addition to motion control. In this research, results of design and construction of an autonomous mobile rescue robot for finding victims through video data are presented. It is aimed to find victims via applying video as a data collection and feedback generation tool in the autonomous mobile robot control system. The visual feedback and YOLO v3 are used not only for finding victims but also for motion control. Our autonomous mobile robot is designed to move smoothly to the victim's direction and avoids obstacles by using ROS Global Planner. The robot is tested in multiple scenarios in different locations, various obstacle and victim numbers, and satisfactory results with good performances are obtained.

Introduction: Autonomous mobile robots (AMRs) represent a transformative technology revolutionizing various industries, from manufacturing and logistics to healthcare and service sectors. These robots, equipped with advanced sensors, artificial intelligence (AI), and navigation systems, can operate independently in dynamic environments without human intervention. The emergence of AMRs has significantly impacted traditional workflows, offering enhanced efficiency, flexibility, and safety in diverse operational settings. The development of AMRs stems from the increasing demand for automation solutions to address challenges such as labor shortages, rising operational costs, and the need for faster and more accurate task execution. Unlike traditional industrial robots confined to fixed locations or predefined paths, AMRs possess the capability to navigate complex environments, adapt to changing conditions, and collaborate seamlessly with humans and other machines. The significance of research in the field of autonomous mobile robots (AMRs) extends across various domains, reflecting their transformative impact on industries, economies, and society as a whole. Understanding the importance of research in this field is essential for harnessing the full potential of AMRs and addressing the challenges and opportunities they present. Technological Advancements: Research in AMRs drives technological advancements, leading to the development of more sophisticated sensors, AI algorithms, and navigation systems. These advancements enhance the capabilities of AMRs, enabling them to operate in complex and dynamic environments with greater autonomy, efficiency, and safety. Industrial Automation: AMRs play a crucial role in industrial automation, revolutionizing manufacturing, warehousing, and logistics operations. Research in this area focuses on optimizing AMR deployment, task allocation, and coordination to improve productivity, reduce costs, and streamline processes in diverse industrial settings. Robo Navigator 3000, Auto Rover X, Smart Path Pro, Nav Bot Elite, Intelli Scout. Battery Life (hours), Navigation Accuracy (%), Maintenance Requirement (Rating), Noise Level (dB). The results indicate that Smart Path Pro achieved the highest rank, while Auto Rover X received the lowest rank being attained. “The value of the dataset for Autonomous Mobile Robot lies, according to the Weighted Sum Method (WSM), demonstrates that Smart Path Pro achieves the highest ranking.”

The commercially available battery management and mission scheduling systems for fleets of autonomous mobile robots use different algorithms to calculate the current state of charge of the robot's battery. This information alone cannot be used to predict whether it will be possible for a single robot in the fleet to execute all of the scheduled missions. This paper provides insight into how to develop a universal battery discharge model based on key mission parameters, which allows for predicting the battery usage over the course of the scheduled missions and can, in turn, be used to determine which missions to delegate to other robots in the fleet, or if more robots are needed in the fleet to accomplish the production plan. The resulting model is, therefore, necessary for mission scheduling in a flexible production system, including autonomous mobile robot transportation networks.

As online shopping is becoming mainstream, driven by the social impact of Coronavirus disease-2019 (COVID-19) as well as the development of Internet services, the demand for autonomous delivery mobile robots is rapidly increasing. This trend has brought the autonomous mobile robot market to a new turning point, with expectations that numerous mobile robots will be driving on roads with traffic. To achieve these expectations, autonomous mobile robots should precisely perceive the situation on roads with traffic. In this paper, we revisit and implement a real-time traffic light recognition system with a proposed lightweight state recognition network and ratio-preserving zero padding, which is a two-stage system consisting of a traffic light detection (TLD) module and a traffic light status recognition (TLSR) module. For the TLSR module, this work proposes a lightweight state recognition network with a small number of weight parameters, because the TLD module needs more weight parameters to find the exact location of traffic lights. Then, the proposed effective and lightweight network architecture is constructed by using skip connection, multifeature maps with different sizes, and kernels of appropriately tuned sizes. Therefore, the network has a negligible impact on the overall processing time and minimal weight parameters while maintaining high performance. We also propose to utilize a ratio-preserving zero padding method for data preprocessing for the TLSR module to enhance recognition accuracy. For the TLD module, extensive evaluations with varying input sizes and backbone network types are conducted, and then appropriate values for those factors are determined, which strikes a balance between detection performance and processing time. Finally, we demonstrate that our traffic light recognition system, utilizing the TLD module’s determined parameters, the proposed network architecture for the TLSR module, and the ratio-preserving zero padding method can reliably detect the location and state of traffic lights in real-world videos recorded in Gumi and Deagu, Korea, while maintaining at least 30 frames per second for real-time operation.

In this paper, we describe a basic sensing system for self-diagnosing an autonomous mobile robot. In recent years, many researches on intelligent robots and systems have been done. But, when such robots and systems work in the real environment, it is important for those robots and systems to have the ability to recognize their own conditions for detecting faults. On the point of view, we should consider pay more attention to diagnose in such intelligent systems. Therefore we try to construct an internal sensing system as a self-diagnosis system on a real robot. Especially, in this paper, we discuss about motor system of an autonomous omnidirectional mobile robot, which was developed in RIKEN. The self-diagnosis system consists of multiple sensors, which are voltage, current, encoder, and magnetic sensors. We show some diagnosing experimental results using the real system. From the results, we could collect basic data for fault detection of the system.

Energy costs account for a significant proportion of total costs in production systems. Since energy is becoming an increasingly expensive resource, therefore, it is critical to consume it as efficiently as possible. Focusing on energy efficiency is also important in terms of reducing greenhouse gas (GHG) emissions and the effects of other pollutants on the environment. One of the possible ways for businesses to reduce energy consumption is to use available transportation means as efficiently as possible. In the operational phase, this can be achieved by reducing unnecessary transport, selecting the most efficient delivery routes, and by optimized assignment of available vehicles to transportation orders. We present in this article a novel dynamic assignment of transportation orders to fleet with energy minimization criterion in internal transport system of a printing company. The novelty of the proposed model is that, in contrast to most existing models, it can handle a heterogeneous fleet of human-operated and autonomous mobile robots (AMRs). The minimization of the energy consumption by transportation vehicles was modeled with reference to VDI 2198 standard. The need for such a model is justified by the fact that it better reflects a real production environment in many companies. The proposed optimization model was tested in simulation experiments imitating real production conditions in a large web printing house. The obtained results show that the proposed model allows for a significant reduction of energy consumption in internal transportation. The proposed model is general enough to be used in various companies with a heterogeneous fleet of internal transportation vehicles. In addition, the energy consumption factor VDI for AMRs has been determined, which can be useful in solving various problems related to energy optimization of internal transportation.

Summary form only given, as follows. In trying to build complete autonomous and self-contained mobile robots that can operate in dynamic environments the authors have developed a set of constraints on both sensing and action that are somewhat different from the traditional assumptions. The authors have built a number of small (on the order of a few pounds in weight) totally autonomous mobile robots which do real-time sensing, some including vision, as they navigate about. This paper focuses on the connection of sensing to action and how that constrains each of them. >

The definition of good experimental methodologies is a topic of growing interest in autonomous mobile robotics. Recently, researchers in this field have started to recognize that their experimental methodologies have not yet reached the level of maturity of other disciplines. In the effort of improving the quality of experimental activities, some proposals have been made to take inspiration from how experiments are performed in traditional sciences. However, a comprehensive analysis of the peculiar features involved in the experimentation of autonomous mobile robots intended as engineering artifacts is, to the best of our knowledge, still lacking. In this paper, we aim at contributing to fill this gap by discussing experiments in autonomous mobile robotics from an engineering point of view. We start by considering autonomous mobile robots as technical artifacts, namely as physical entities designed for a technical function and provided with a use plan. Then, we show that, due to the nature of the field, scientific and engineering aspects are strongly interrelated in the experimental activities performed to assess and evaluate autonomous mobile robots. To make our discussion more concrete, we refer to some examples taken from the specific robotic application of search and rescue of victims after a disaster.KeywordsExperimentsAutonomous mobile robotsTechnical artifacts