Ten autonomous mobile robots (and even more) in a route network like environment

The MARTHA project objectives are the control and the management of a fleet of autonomous mobile robots for transshipment tasks in harbors, airports and marshalling yards. One of the most challenging and key problems of the MARTHA project is multi-robot cooperation. A general concept for the control of a large fleet of autonomous mobile robots has been developed, implemented and validated in the framework of the MARTHA project. This is the first study in the autonomous mobile robot field to add multi-robot cooperation capabilities to such a large fleet of robots.

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.

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.

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.

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.

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.

In this work we propose a behaviour-based architecture, which can also be seen as a multi-agent architecture, to control a situated and embodied autonomous mobile robot, under a close sensing action relationship. Pre-existing knowledge can play a meta-level role, being used in order to provide an adviser capability which is combined with the basic reactive feature of the robot. One of the challenges of the behaviour-based approach is the integration and coordination of multiple different behaviours. This problem was faced using combination operators applied to lower level behaviours and producing useful and coherent higher level behaviours. Our autonomous mobile robot also exhibits learning capabilities, namely the ability to learn new behaviours in an autonomous way. In this context it was designed to the elementary behaviours a connectionist architecture that encompasses the capabilites of building specific basic competences.Through the exploration of the proposed control architecture a mobile platform has become an useful autonomous mobile robot It is able to deal with dynamic environments, evolving in a coherent, relevant and adequate way according to both the current situation as well as with its assigned missions.

A Spatial Data Structure for the 3D Graphical Facility Management System

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

In the control of autonomous mobile robots there exist two types of control: global control and local control. The requirement to solve global and local tasks arises respectively. This chapter concentrates on local tasks and shows that robots can learn to cope with some local tasks within minutes. The main idea of the chapter is to show that, while creating intelligent control systems for autonomous mobile robots, the beginning is most important as we have to transfer as much as possible human knowledge and human expert-operator skills into the intelligent control system. Successful transfer ensures fast and good results. One of the most advanced techniques in robotics is an autonomous mobile robot on-line learning from the experts’ demonstrations. Further, the latter technique is briefly described in this chapter. As an example of local task the wall following is taken. The main goal of our experiment is to teach the autonomous mobile robot within 10 minutes to follow the wall of the maze as fast and as precisely as it is possible. This task also can be transformed to the obstacle circuit on the left or on the right. The main part of the suggested control system is a small Feed-Forward Artificial Neural Network. In some particular cases – critical situations – “If-Then” rules undertake the control, but our goal is to minimize possibility that these rules would start controlling the robot. The aim of the experiment is to implement the proposed technique on the real robot. This technique enables to reach desirable capabilities in control much faster than they would be reached using Evolutionary or Genetic Algorithms, or trying to create the control systems by hand using “If-Then” rules or Fuzzy Logic. In order to evaluate the quality of the intelligent control system to control an autonomous mobile robot we calculate objective function values and the percentage of the robot work loops when “If-Then” rules control the robot.

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 kinematic model identification algorithm of the autonomous mobile robot using dynamical recurrent neural network is presented. The structure and the learning algorithm of dynamical recurrent neural network are analyzed. Data in the training set are from an autonomous mobile robot and are filtered with /spl alpha/-/spl beta/ filter. Experiments on the autonomous mobile robot show that it is practically feasible to represent the nonlinearities and dynamic characters of the autonomous mobile robot. The forward model is also an essential segment to control the autonomous mobile robot motion with generalized predictive control algorithm.

Fuzzy drive control of an autonomous mobile robot