Autonomous Mobile Robots

The main problem in the guidance of Autonomous Mobile Robots is obstacle avoidance in unknown environment. This paper presents a novel technique for path fixing for obstacle avoidance using a framework of cellular logic. The images of the unknown environment obtained from local perception devices are scanned by an array of neighbourhood windows and processed by the techniques of contouring, skeletonizing and centroid determination. High risk regions and low risk regions are considered for nearby and distant obstacles. A framework of cellular logic is used to determine the probability of collision. The various possibilities are classified into equally likely classes. The optimal path is the one that has the common probability of collisions. The mission direction is accordingly fixed instantaneously to meet the challenge of obstacle avoidance.

Recently, autonomous mobile robots have gained popularity in the modern world due to their relevance technology and application in real world situations. The global market for mobile robots will grow significantly over the next 20 years. Autonomous mobile robots are found in many fields including institutions, industry, business, hospitals, agriculture as well as private households for the purpose of improving day-today activities and services. The development of technology has increased in the requirements for mobile robots because of the services and tasks provided by them, like rescue and research operations, surveillance, carry heavy objects and so on. Researchers have conducted many works on the importance of robots, their uses, and problems. This article aims to analyze the control system of mobile robots and the way robots have the ability of moving in real-world to achieve their goals. It should be noted that there are several technological directions in a mobile robot industry. It must be observed and integrated so that the robot functions properly: Navigation systems, localization systems, detection systems (sensors) along with motion and kinematics and dynamics systems. All such systems should be united through a control unit; thus, the mission or work of mobile robots are conducted with reliability.

In this study, a path smoothing strategy is proposed for sensor-based coverage problems. Smooth paths are generated for the coverage problems considering mobile robot kinematics constraints. An open agent architecture-based control structure is used to implement the proposed approach on real robots. The algorithm is coded with C++ and implemented on P3-DX mobile robots in MobileSim simulation environments. It is

Autonomous mobile robots have been used to carry out different tasks without continuous human guidance. To achieve the tasks, they must be able to navigate and avoid different kinds of obstacles that faced them. Navigation means that the robot can move through the environment to reach a destination. Obstacles avoidance considers a challenge which robot must overcome. In this work, the authors propose an efficient technique for obstacles avoidance through navigation of swarm mobile robot in an unstructured environment. All robots cooperate with each other to avoid obstacles. The robots detect the obstacles position around them and store their positions in shared memory. By accessing the shared memory, the other robots of the swarm can avoid the detected obstacles when they face them. To implement this idea, the Authors used a MATLAB® and V-REP® (Virtual Robot Experimentation Platform).

Was ist es, was eine Maschine, einen Computer oder einen
Menschen überhaupt intelligent macht? Diese Frage ist weitaus schwerer zu beantworten, als man zunächst erwarten würde. Man kann hier etwa auf die Fähigkeit des Denkens oder auf eine bestimmte Art des Handelns abstellen. Der Ansatz, dass sich Künstliche Intelligenz daran festmachen ließe, ob eine Maschine den gleichen Output wie ein Mensch nachahmen kann, ist seit den Anfangstagen der Fachdisziplin der Künstlichen Intelligenz bis heute stark verbreitet. Doch ebenso lange wird auch darüber diskutiert, ob damit der Wesensbereich menschlicher Intelligenz
überhaupt erfasst wird. Seit den 50er Jahren wird darüber
debattiert, ob die Simulation eines intelligenten Outputs ausreichend
sein kann für die Frage, ob ein System intelligent ist oder nicht
und ob zur menschlichen Intelligenz nicht gerade etwas hinzuzuzählen
ist, das über einen entsprechenden Abgleich von Outputs gar nicht zu
erfassen ist. Mit dieser Kritik an der Verifikationsmethode ist eine Kritik
an der Idee, dass Maschinen prinzipiell das Niveau menschlicher Intelligenz überhaupt erreichen könnten, eng verbunden. Die Idee, dass
dies prinzipiell erreichbar ist, wird einem Vorschlag von John Searle
folgend auch als starke KI-These bezeichnet, während die Kritiker nur
einer schwachen KI-These zustimmen können, wonach artifizielle Systeme lediglich Teilaspekte menschlicher Intelligenz erfolgreich simulieren können, aber eben nie im vollen Umfang als intelligent zu bezeichnen wären.
Zwei Kritikpunkte an der Vorstellung einer starken KI sind bis heute extrem wirkmächtig:
1.: Künstliche Intelligenz könne niemals ‚wirklich‘ intelligent sein,
weil das selbstbewusste ‚Ich‘ fehle, an dem nicht nur das Denken i.e.S.,
sondern wahlweise auch Intentionalität, Emotionen, phänomenale Bewusstseinszustände, freier Wille, Intuition und Ähnliches mehr hingen.
2.: Künstlicher Intelligenz fehle es an einer Verkörperung und
menschlichen Sozialisation, sie sei nicht eingebettet in eine Welt, in der
sie lernen und mit der sie reziprok und kontinuierlich in Verbindung
steht, was aber konstitutiv für die menschliche Art von Intelligenz sei.
Diese Art der Kritik und der Gegenentwurf von Befürwortern der
starken KI-These zeigen, dass die philosophische Debatte
um Künstliche Intelligenz untrennbar mit den ganz zentralen Fragen
der Philosophie des Geistes der letzten Jahrhunderte verbunden ist. Die
KI-Debatte wirft Fragen auf, deren Antworten von den Grundpositionen
abhängen, die in ihr eingenommen werden. Drei große kartographieren das Feld: Die erste Frage lautet, was das Selbst eigentlich ist, das sich in unserem Geist seiner selbst bewusst wird: Ist es eine Seele, also eine vom Körper zu trennende Substanz, oder handelt es sich um ein stark emergentes Phänomen, das jenseits physikalischer Gesetzmäßigkeiten aus dem Zusammenspiel unseres Gehirns entsteht oder aber ist es schlicht ein besonders kluger Trick der Evolution, der im Rahmen darwinistischer Prozesse entstanden und in keiner Weise mysteriös ist, sondern auch physikalisch erklärt werden kann. Die zweite ist die metaphysische Frage nach unserer Realität, ob das Sein also monistisch oder dualistisch zu verstehen ist, ob es letztlich aus den physikalischen Elementarteilchen und den zwischen ihnen wirkenden Kräften besteht, ober ob im Falle des menschlichen Geistes etwas Spirituelles hinzukommt. Und die dritte schließlich ist die anthropologische Frage nach dem, was der Mensch ist: Ist er etwas Herausgestelltes und Besonderes, das etwa kraft seiner Vernunft allem anderen Leben enthoben ist, oder ist er ein evolutionär besonders weit entwickeltes Tier oder aber ist er letztlich auch nur eine Maschine? Je nach Position zu diesen drei Fragen ergibt sich ein anderer Raum von Optionen, wie die starke KI-These zu beurteilen ist.

In this paper it is presented an integration of algorithms that permits maps construction and navigation of mobile robots. Simultaneous Localization and Mapping (SLAM) algorithm is used based on FastSLAM method. Navigation system is based on VHF to avoid obstacle and a spiral way trajectory method. To three different complex simulation maps are used to evaluate the system.

In the movie Guardians of the Galaxy, the Yaka arrow, when shot by the Yondu Udonta, goes through a bunch of people in a flash; the weapon is highly responsive to certain high-octave whistle commands, which cause it to change trajectory as needed, return to the holster promptly or even combust into a fiery explosion on command. Real life Artificial Intelligence drone technology is making possible the deployment of autonomous weapons that could do pretty much the same and more.

It is well known that this soiling can reduce the generation efficiency in PV system. In some case according to the literature of loss of energy production in photovoltaic systems can reach up to 50%. In the industry there are various types of cleaning robots, they can substitute the human action, reducing cleaning cost, be used in places where access is difficult, and increasing significantly the gain of the systems. In this paper we present an application of computer vision method for soiling recognition in photovoltaic modules for autonomous cleaning robots. Our method extends classic CV algorithm such Region Growing and the Hough. Additionally, we adopt a pre-processing technique based on Top Hat and Edge detection filters. We have performed a set of experiments to test and validate this method. The article concludes that the developed method can bring more intelligence to photovoltaic cleaning robots.

In this study, the method of direct-motion parallel parking is introduced both in theory and in simulations for the vehicle with and without a trailer. The results show that not only a vehicle with a trailer park in parallel using direct motion, but also a vehicle with a trailer park in parallel in direct motion after the final value of the orientation angle is satisfied. Simulation results are given to verify the effectiveness of the proposed method.

Paper videos can be reached from this URL: http://www.youtube.com/playlist?list=PLENSkat0854vszuVfu9mnrEvHsVQGBBgB

In this case study, we describe a fleet of autonomous mobile robots (AMR) that move non-conveyable products/items in the courier industry using detachable carts. The main purpose of this case study is to find the positional accuracy and repeatability of LiDAR-driven AMRs for the design of docking applications. We conducted several trials for collecting the positional data using a docking test bed at different speeds and times. The process uses a Kalman filter and Six-Sigma methods to define the docking constraints. Using these min and max positional constraints, we designed the detachable cart that can be used to move "non-conveyable" (NC) products. The current product has completed a trial deployment of a system that automates the transportation of NC or "irregular" (IRR) parcels at courier facilities at scale. This system is a first step toward our research goal of developing an architecture for robust robot planning, control, adaptation, error monitoring, error recovery, and interaction with users. We describe the current system, lessons learned from our earlier failures, organizing principles employed in the current system, and limits to the current approach. Currently, NC products are manually pre-sorted and placed on carts that are assigned to a designated outbound location. Once the cart is full, a tug operator manually moves the full cart to outbound destination. The tug allows up to 4 carts to be transported from the NC load station to the outbound unload station. The large batch operation comes at the expense of having to wait for 4 carts be become available, loaded and ready for transport. The proposed robot system is a drop-in replacement to the current carts in operation. While current carts may also be detachable, they are manually attached to the train of carts and rely on a tug operator for transportation in the facility. In the proposed system, the robots facilitate the operation of a LEAN Pull System. When a cart is loaded, it is immediately positioned for delivery to the appropriate outbound sorter, resulting in a reduction of time that the full carts sit idle thus improving workflow and decreasing congestion points. NC sorting and loading to detachable carts in the robotic fleet is depicted in figure 1. The components are described according to the order of operations / flow. Figure 1 NC Cart Loading Station

Rechtlichen Anforderungen an automatisiertes Fahren basieren unter anderem auf dem Wiener Übereinkommen über den Straßenverkehr von 1968, das einen Rechtsrahmen für nationale Straßenverkehrsgesetze vorgibt. In Deutschland erfolgte mit Wirkung vom 21. Juni 2017 die Ergänzung der Paragraphen 1a und 1b in das Straßenverkehrsgesetz (StVG). Entsprechend dem § 1a Absatz 1 StVG ist der Betrieb eines Kraftfahrzeugs „mittels hoch- oder vollautomatisierter Fahrfunktion“ grundsätzlich zulässig, unter der Bedingung, dass die Funktion bestimmungsgemäß verwendet wird. Wegen der Bedeutsamkeit des Themas hatten sich 2015, 2018 und 2019 Arbeitskreise beim deutschen Verkehrsgerichtstag für Empfehlungen zum automatisierten Fahren ausgetauscht.
Hier wurde auch auf den bereits mehrfach von dem Juristen Prof. Dr. Dr. Hilgendorf zitierten „Aschaffenburger Fall“ von Januar 2012 hingewiesen. Dabei wurde davon ausgegangen, dass ein wegen Schlaganfall bewusstloser Fahrzeugführer durch einen aktivierten Lenkassistent in einen Ort eingefahren ist und im Anschluss zwei Menschen getötet hat. Das Fahrzeug entsprach dem Stand der Technik und Hilgendorf begrenzt in diesem konkreten Fall die Sorgfaltspfl icht des Herstellers durch den Grundsatz des erlaubten Risikos. Im Rahmen der Produktbeobachtungspflicht müssen jedoch seiner Meinung nach zukünftige Neuentwicklungen Konsequenzen aus diesem nun bekannten Verkehrsunfall ziehen. Als weiteres Beispiel wurde der tödliche Unfall in Tempe im US-Staat Arizona angesprochen, bei dem ein Uber-Testfahrzeug im selbstfahrenden autonomen Modus mit einer Fußgängerin und ihrem Fahrrad kollidierte. Es handelt sich dabei um den ersten aufgezeichneten tödlichen Fußgängerunfall mit einem selbstfahrenden Uber-Testfahrzeug. Auf der Basis von veröffentlichten Fotos des Deformierten Volvo XC90, der Unfallstelle mit den Endlagen konnte vom Verfasser eine Unfallrekonstruktion mit PC-Crash angefertigt werden. Unter Annahme einer Geschwindigkeit von 64 km/h (17,8 m/s) und einer sofort wirkenden Notbremsung 1,3 Sekunden vor Kollision mit einer Verzögerung von 6,8 m/s2 wäre der Unfall vermieden worden.
Als Basis für systematische Unfallanalysen mit künstlicher Intelligenz und Risikobewertungsmethoden (beispielsweise AcciMap, das Systems-Theoretical Accident and Process Model - STAMP und die Functional Resonance Analysis Method - FRAM) im Rahmen der Produktbeobachtung, dem Freigabeprozess und der Entwicklung von automatisierten empfiehlt sich eine flächendeckende Speicherung der Unfall-, Verkehrsfluss-, Wetter- und Fahrzeugbetriebsdaten.

Legal requirements for automated driving are based, amongst others, on the Vienna Convention on Road Traffic of 1968, which provides a legal framework for national road traffic laws pretends. In Germany, paragraphs 1a and 1b were added to the Road Traffic Act (StVG) with effect from 21 June 2017. According to Section 1a, Paragraph 1 of the StVG, the operation of a motor vehicle "by means of a highly or fully automated driving function" is generally permissible, provided that the function is used as intended. Due to the importance of the topic, working groups had exchanged recommendations for automated driving at the German Traffic Court Conference in 2015, 2018 and 2019.
Here reference was also made to the "Aschaffenburg case" of January 2012, which has already been quoted several times by the lawyer Prof. Dr. Dr. Hilgendorf. This case was based on the assumption that a driver who was unconscious due to a stroke had entered a town by means of an activated steering assistant and subsequently killed two people. The vehicle was state of the art and Hilgendorf limited the manufacturer's duty of care in this specific case by the principle of permissible risk. In his opinion, however, future new developments must draw consequences from this now known traffic accident within the framework of the product monitoring obligation. As a further example, the fatal accident in Tempe in the US state of Arizona was mentioned, in which an Uber test vehicle collided with a pedestrian and her bicycle in self-propelled autonomous mode. This is the first recorded fatal pedestrian accident involving a self-propelled Uber test vehicle. On the basis of published photos of the deformed Volvo XC90, the accident site with the end positions, the author was able to make an accident reconstruction with PC-Crash. Assuming a speed of 64 km/h (17.8 m/s) and an immediately effective emergency braking 1.3 seconds before collision with a deceleration of 6.8 m/s2 the accident would have been avoided.
As a basis for systematic accident analyses and risk assessment or Artificial Intelligence methods (e.g. AcciMap, the Systems-Theoretical Accident and Process Model - STAMP and the Functional Resonance Analysis Method - FRAM) in the context of product monitoring, the release process and the development of automated ones, it is recommended that accident, traffic flow, weather and vehicle operating data be stored area-wide.

This paper represents the design, implementation, and experimental results of RF based wireless control of a distributed PLC Controlled Automated Guided Vehicle , which is known as MTAB ROVER. It was designed in-house as a general purpose guide path following mobile platform for material handling and transportation within a manufacturing facility.

An integrated network of mobile robots, personal smart devices, and smart spaces called " Robots-Assisted Ambient Intelligence " (RAmI) can provide for a more effective user assistance than if the former resources are used individually. Additionally, with the application of distributed network optimization, not only can we improve the assistance of an individual user, but we can also minimize conflict or congestion created when multiple users in large installations use the limited resources of RAmI that are spatially and temporally constrained. The emphasis of RAmI is on the efficiency and effectiveness of multiple and simultaneous user assistance and on the influence of an individual's actions on the desired system's performance. In this paper, we model RAmI as a multi-agent system with AmI, user, and robot agents. Moreover, we propose a modular three-layer architecture for each robot agent and discuss its application and communication requirements to facilitate efficient usage of limited RAmI resources. Our approach is showcased by means of a case study where we focus on meal and medicine delivery to patients in large hospitals.

In this study, a Best First Search (BFS) Based Intelligent PID Tuning Method is proposed for a mobile robot path tracking problem. BFS is an informed search strategy in Artificial Intelligence (AI). It has been used in many areas of intelligent systems. Here, it is used to search values of both ultimate period and ultimate gain of Ziegler-Nichols (ZN) PID Tuning Method. So, using these ultimate period and gain, PID parameters can be c from tables of ZN method. The performance measure in this problem is described as minimizing total error during any specified trajectory tracking. Thus the proposed method does not depend on the system model. It only needs error information during the tracking control. So, this method can be used to tune PID parameters of any tracking controller for a system with unknown system dynamics. The proposed method is tested with simulations in MATLAB during trajectory tracking of a mobile robot. In addition, it is compared with classical PID and conventional PID tuning methods including Ziegler-Nichols method, Tyreus-Luyben method, and Shinskey method.

Keywords: Intelligent PID tuning, best first search, autonomous mobile robot, mobile robot path tracking problem, computed torque PID control, dynamic model, Ziegler-Nichols, Tyreus-Luyben, Shinskey.

Localization and mapping at the same time is one of our problems in this century, specially in autonomous vehicles. The project revolves around implementing a SLAM algorithm on a two-wheeled robot equipped with a camera and sensor. To do this, we use the robot operating system known as ROS to simulate our robot in the real world. Our robot configuration was studied in detail using Gmapping on ROS.From the configuration we study, we believe that the combination of Kinect and sensor will be the best choice for our sensor, which is supported by empirical evidence.

Due to the threat of the COVID-19 pandemic, opportunities for service robots in the Philippines are increasingly bright. More service robots worldwide are currently operational to contribute to a very simple, fast, and thorough disinfection in local facilities. This paper's paradigm presents the design and development of a service robot focused on disinfecting indoor spaces. The authors successfully developed and assessed a base prototype of an omnidirectional germicidal indoor carrier assistant robot with a line following function. First, an initial model was designed to visualize the general idea of the study; base plate simulation was done to ensure that the base plate can handle external loads brought by the frame, enclosure box, and the liquid disinfectant container. Then, the researchers built a base prototype to assess the prototype's navigation performance on various track patterns and a demanding path in the closed-loop test. In designing a course for the robot to n...

Today, human activities constitute the primary environmental impact on the planet. In this context, commitments to sustainability, or minimization of damage, prove insufficient. To develop regenerative, futuring capabilities, architectural design needs to extend beyond the form and function of things and engage with the management of complex systems. Such systems involve multiple types of dynamic phenomena—biotic and abiotic, technical and cultural—and can be understood as living. Engagement with such living systems implies manipulation of pervasive and unceasing change, irrespective of whether it is valued by design stakeholders or actively managed towards homeostatic or homeorhetic conditions. On one hand, such manipulation of continuity requires holistic and persistent design involvements that are beyond natural capabilities of human designers. On the other hand, practical, political, or creative implications of reliance on automated systems capable of tackling such tasks are as yet underexplored. In response to this challenge, this paper considers an experimental approach that utilized methods of critical making and speculative designing to explore potentials of autonomous architecture. Presented experiments combined knowledge of animal architecture with intelligent behaviors of robotic devices.

In this chapter, a survey of the current state of research on autonomous driving is given and is set in the context of the requirements of an autonomous vehicle following the vision of an automated taxi. The overview is based on (scientific) publications and self-reports of the developing teams. Aspects of interest for this summary are approaches on environmental perception, self-perception, mission accomplishment, localization, cooperation, map usage, and functional safety. Typically, emphasis is given to reliance on global satellite systems (e.g., GPS) and map data. Only a few approaches focus on environmental perception and scene understanding. Even though impressive demonstrations of autonomous driving have been presented in recent decades, this overview concludes that many aspects still remain only partially solved or even unsolved, especially when driving autonomously in public road traffic.

The aim of this paper is to implement metrics and to define indicators to provide a unified criteria for evaluation method of the performance of autonomous mobile robots using different control algorithms. There is a first description of the mobile robot problem and the importance of a standardized process for evaluation of robot performances. There is a comparison between a simple navigation controller and an intelligent prototype based on consciousness. The architecture main features are also outlined. Test cases with and without conscious controller show that the latter performs an optimized source-to-target path.

We kindly ask you to participate in this research devoted to the adoption of service robots by travel, tourism and hospitality companies. By completing the questionnaire, you will be eligible to participate in an opportunity for one of five electronic 100-dollar gift cards, redeemable as Amazon gift vouchers, among other options. Once you have completed the survey, a separate link will be sent to you allowing you to register for the opportunity. The researchers will not be able to identify your responses to the survey questions and the identifying information you will leave for the purposes of the opportunity for the gift vouchers.

For questions about your rights as a research subject, please contact the Director, Office of Research Integrity, Ball State University, Muncie, IN 47306, (765) 285-5070 or at irb@bsu.edu. IRB Protocol Number: 1194315-1

Please complete the questionnaire if only you are at least 18 years of age.
Thank you in advance for your participation!

Here is the link to the survey:

https://bsu.qualtrics.com/jfe/form/SV_4PdOOi6ERWHw97v

Sincerely,

Dr. Craig Webster, Ball State University, USA, email: cwebster3@bsu.edu
Prof. Stanislav Ivanov, Varna University Management, Bulgaria, email: stanislav.ivanov@vumk.eu

In this paper, the design, implementation and control of a humanoid robot, which enables humanlike walk and a path planning of humanoid robot for obstacle avoidance by using infrared sensors (IRs) is proposed. As the focus is to obtain human-like walk, the robot is designed to resemble human proportions. Based on the obtained information from IR sensors, a software flow proposed to decide the behaviour of robot so that the robot avoids obstacles and goes to the destination. Furthermore the hardware and software necessary to obtain a fully autonomous system is developed and implemented. Human-like walk was not obtained on the real system, due to system limitations. If a new interface to the DC-motors in the servos was developed, and a faster on-board computer was chosen, human-like walk should be possible.

In this study, the functionality of an autonomous mobile robot is improved by interfacing it with Microsoft Kinect for finding and tracking a previously identified human target while avoiding obstacles both while searching and tracking.  A suitable platform for fixing Microsoft Kinect and a laptop on a mobile robot is designed considering simplicity and practicality. The human identification and tracking methodology and algorithm is analysed for real life scenarios. The developed algorithm is applied to the mobile robot using robotics software and evaluated through real life scenarios achieving pleasing results. The mobile robot is able to identify humans, search for them and track them while avoiding static obstacles both while searching and tracking at indoor environments where no direct sunlight is present.

The project aims to build a monocular vision autonomous car
prototype using Raspberry Pi as a processing chip. An HD
camera along with an ultrasonic sensor is used to provide
necessary data from the real world to the car. The car is
capable of reaching the given destination safely and
intelligently thus avoiding the risk of human errors. Many
existing algorithms like lane detection, obstacle detection are
combined together to provide the necessary control to the car.

In this study, the method of direct-motion diagonal and perpendicular parking is introduced both in theo-ry and in simulations for the vehicle with and without a trailer. The results show that not only a vehicle with a trailer park in diagonal or perpendicular using direct motion, but also a vehicle with a trailer park in diagonal and perpendicular in direct motion after the final value of the orientation angle is satisfied. Simulation results are given to verify the effec-tiveness of the proposed method. Keywords: diagonal, perpendicular, direct motion, parking, trailer, car-like vehicle Paper videos can be reached from this URL: http://www.youtube.com/playlist?list=PLENSkat0854vGceT1fX4Yr6Yw0UqqW_vl

A crucial prerequisite for recycling forming an integral part of municipal solid waste (MSW) management is sorting of useful materials from source-separated MSW. Researchers have been exploring automated sorting techniques to improve the overall efficiency of recycling process. This paper reviews recent advances in physical processes, sensors, and actuators used as well as control and autonomy related issues in the area of automated sorting and recycling of source-separated MSW. We believe that this paper will provide a comprehensive overview of the state of the art and will help future system designers in the area. In this paper, we also present research challenges in the field of automated waste sorting and recycling.

Due to the threat of the COVID-19 pandemic, opportunities for service robots in the Philippines are increasingly bright. More service robots worldwide are currently operational to contribute to a very simple, fast, and thorough disinfection in local facilities. This paper's paradigm presents the design and development of a service robot focused on disinfecting indoor spaces. The authors successfully developed and assessed a base prototype of an omnidirectional germicidal indoor carrier assistant robot with a line following function. First, an initial model was designed to visualize the general idea of the study; base plate simulation was done to ensure that the base plate can handle external loads brought by the frame, enclosure box, and the liquid disinfectant container. Then, the researchers built a base prototype to assess the prototype's navigation performance on various track patterns and a demanding path in the closed-loop test. In designing a course for the robot to navigate, a less complicated pre-planned course must be considered to ensure a smooth and precise line tracking of the robot. The derived concepts and analysis from the prototype led the authors to several base design recommendations.

Autonomous Weapon Systems (AWS) are defined as robotic weapons that have the ability to sense and act unilaterally depending on how they are programmed. Such human-out-of-the-loop platforms will be capable of selecting targets and delivering lethality without any human interaction. This weapon technology may still be in its infancy, but both semi-autonomous and other pre-cursor systems are already in service. There are several drivers to a move from merely automatic weapons to fully autonomous weapons which are able to engage a target based solely upon algorithm-based decision-making. This requires material step-change in both hardware and software and, once deployed, posits a significant change in how humans wage war. But complex technical difficulties must first be overcome if this new independent and self-learning weapon category can legally be deployed on the battlefield. AWS also pose basic statutory, moral and ethical challenges.

This thesis identifies the manifest complexity involved in fielding a weapon that can operate without human oversight while still retaining value as a battlefield asset. Its key research question therefore concerns the practical and technical feasibility of removing supervision from lethal engagements. The subject’s importance is that several well-tried concepts that have long comprised battlecraft may no longer be fit for purpose. In particular, legal and other obstacles challenge such weapons remaining compliant under Laws of Armed Conflict. Technical challenges, moreover, include the setting of weapon values and goals, the anchoring of the weapon’s internal representations as well as management of its utility functions, its learning functions and other key operational routines. While the recent development pace in these technologies may appear extraordinary, fundamental fault lines endure. The thesis also notes the inter-dependent and highly coupled nature of the routines that are envisaged for AWS operation, in particular ramifications arising from its machine learning spine, in order to demonstrate how detrimental are these compromises to AWS deployment models. In highlighting AWS deployment challenges, the analysis draws on broad primary and secondary sources to conclude that Meaningful Human Control (MHC) should be a statutory requirement in all violent engagements.

We present our recent work on the electrical and hardware design of the mobile robot platform ReMoRo that is based on distributed input/output modules. We have designed three generation of this platform with different specifications, which it help us to design more compatible and applied mobile robot. Nevertheless, the goal of this project was to develop a low-cost and robust but extensible modular robot platform for research and educational purposes. In this paper we describe a new affordable robot structure that enables large-scale innovative, new curriculum, multi robot research and multi-robotics outreach to computer and artificial intelligent students. We introduce the ReMoRo platform, which offers a balance between capabilities, accessibility, cost and an opendesign. All of electrical devices like sensors module, motor drivers and device communication manager are designed based on ARM Cortex M3 microcontrollers that runs under Real-Time Operating System (freeRTOS) for manages each modules internal scheduling and activation control in communication bus. With a range of different sensors, cylindrical manipulator and omnidirectional locomotion system, RoMeRo can interact with environment in multiple ways, handle common objects and therefore be used in various service robot scenarios like warehouse robots or multi agent mobile robots. We demonstrate the usability of our concept by quantifying the object-handling task and also briefly describe the software design based on ROS framework for educational usage.

In this paper, we present the modeling and validation of a new family of climbing robots that are capable of adhering to vertical surfaces through permanent magnetic elements. The robotic system is composed of two modules, the master and the follower carts, which are arranged in a sandwich configuration, with the surface to climb interposed between them. Thanks to this configuration, the mobile robot can climb even nonferromagnetic and curved surfaces; moreover, the master cart is capable of freely moving on the floor by detaching from the follower. In this paper, we propose the mathematical modeling, simulation, and experimental validation of this kind of robots, with particular focus on the transitions between floor and climbing motion.

The textbook is available in hard-copy version (in Serbian language) primary for our MSc and PhD students to learn and investigate modern scientific disciplines in domain of intelligent manufacturing systems and processes development. They will learn new concepts within Industry 4.0 development considering a lot of our courses like: Intelligent manufacturing systems (MSc), Industrial robots (MSc), Robotics and AI (MSc), Machine learning of intelligent robotic systems (MSc), Decision-making methods (MSc), Scheduling of manufacturing systems and processes (MSc), Autonomous systems and machine learning (PhD), Biologically inspired optimization algorithms (PhD), Systems of ANN (PhD), Cognitive robotics (PhD).

In this study, the method of direct-motion diagonal and perpendicular parking is introduced both in theo-ry and in simulations for the vehicle with and without a trailer. The results show that not only a vehicle with a trailer park in diagonal or perpendicular using direct motion, but also a vehicle with a trailer park in diagonal and perpendicular in direct motion after the final value of the orientation angle is satisfied. Simulation results are given to verify the effec-tiveness of the proposed method. Keywords: diagonal, perpendicular, direct motion, parking, trailer, car-like vehicle Paper videos can be reached from this URL: http://www.youtube.com/playlist?list=PLENSkat0854vGceT1fX4Yr6Yw0UqqW_vl

This article presents a summary of applications of chaos and fractals in robotics. Firstly, basic concepts of determin‐ istic chaos and fractals are discussed. Then, fundamental tools of chaos theory used for identifying and quantifying chaotic dynamics will be shared. Principal applications of chaos and fractal structures in robotics research, such as chaotic mobile robots, chaotic behaviour exhibited by mobile robots interacting with the environment, chaotic optimization algorithms, chaotic dynamics in bipedal locomotion and fractal mechanisms in modular robots will be presented. A brief survey is reported and an analysis of the reviewed publications is also presented.

Este artículo describe el seguimiento de trayectoria y respuesta ante perturbaciones mediante el control monoarticular y multiarticular de un Robot Esférico de tres grados de libertad, así como el cálculo de su cinemática y dinámica. Se usa la herramientas de Simulink y MatLab como software de simulación del motor, el robot y el controlador.

Italy has been one of the first countries in the world to enact ad hoc regulations on drones. Therefore, the Italian approach may constitute a model for many regulations to come; nonetheless, the legal literature seems to overlook the phenomenon. In this article, I place the discourse on drones in the context of some more general considerations on the main legal issues related to the deployment of machines, including robots, in our everyday life. Indeed, most considerations apply equally to robots and drones, moving from the unrefined, albeit practical, observation that the latter are robots equipped with wings. An analysis of the intellectual property, data protection, privacy, and liability issues is carried out bearing in mind the complexity arising from the increasing implementation of cloud computing and artificial intelligence technologies. The article claims that autonomous machines will outclass human beings in all their tasks, but the horror vacui ought to be avoided: a new unforeseeable society will come. Therein, human beings – granted that a distinction between them and machines will still make sense – will not have to work in order to be able to live.
PLEASE CITE AS: G. NOTO LA DIEGA, Machine rules. Of drones, robots and the info-capitalist society, in Italian Law Journal, 2016, II, 367-404

The increasing need for food in recent years means that environmental protection and sustainable agriculture are necessary. For this, smart agricultural systems and autonomous robots have become widespread. One of the most significant and persistent problems related to robots is 3D path planning, which is an NP-hard problem, for mobile robots. In this paper, efficient methods are proposed by two metaheuristic algorithms (Incremental Gray Wolf Optimization (I-GWO) and Expanded Gray Wolf Optimization (Ex-GWO)). The proposed methods try to find collision-free optimal paths between two points for robots without human intervention in an acceptable time with the lowest process costs and efficient use of resources in large-scale and crowded farmlands. Thanks to the methods proposed in this study, various tasks such as tracking crops can be performed efficiently by autonomous robots. The simulations are carried out using three methods, and the obtained results are compared with each other and analyzed. The relevant results show that in the proposed methods, the mobile robots avoid the obstacles successfully and obtain the optimal path cost from source to destination. According to the simulation results, the proposed method based on the Ex-GWO algorithm has a better success rate of 55.56% in optimal path cost.