This paper advances the previous theoretical work of authors by conducting experiments on a generalized coverage optimization algorithm using a team of heterogeneous mobile robots. A scalar measure ...(herein called the density) of the environment defines a nonuniform coverage metric of the area. Mobile robots are spatially configured such that their asymptotic placements in an area maximize the nonuniform coverage metric. Over the last fifteen years, a large body of research work has been conducted in solving the area coverage optimization problem where the focus was mainly on theoretical results followed by mostly numerical simulations. In some cases, the coverage optimization algorithms were validated with experimental results, but the implementation platforms were suitable to specific homogeneous robot platforms. Here, the emphasis is on the real-time implementation of the authors' previously published theoretical results on area coverage optimization problems using a team of heterogeneous mobile robots. The robots are heterogeneous in the sense that they have different actuator limits, physical dimensions, and processing capabilities. The modularity of the algorithm stems from the fact that the additional hardware/software architecture is open-source and can be applied to different robots regardless of their internal electromechanical system architectures. The algorithm is implemented using the emerging robot operating system in a multithreaded manner. A commercial robot simulator was used to validate the coverage performance followed by a set of experiments conducted in an indoor environment.
In a Robot Operating System (ROS) application, robot software is often distributed across multiple networked components, forming the ROS network, where every component acts as server and/or a client, ...and publishing and/or receiving robot data simultaneously. For indoor robots, a local ROS network, through a Wi-Fi hotspot, is sufficient. But for outdoor robots, a remote ROS network is needed to connect the ROS application to the cloud. Although a number of cloud-based solutions support this, implementing them is challenging, as they need to be configured to facilitate ROS's unique, multidirectional, and simultaneous flow of robot data. This article presents Port Forwarding as an alternative approach, which offers a private, secured, and a direct ROS-to-ROS, eliminating the need for a dedicated middleware and its configuration and setup complexities. But Port Forwarding has its own challenges; chiefly, the beforehand knowledge of Internet addresses of all networked components and the need to update port forwarding settings when these addresses change, which they often do. This article addresses this issue (and others) and presents a detailed procedure for setting Port Forwarding for ROS applications, highlighting configuration, and troubleshooting steps. Also, the article compares between Port Forwarding and cloud-based solutions, in terms of setup, performance, and others. Results show that robot performance under Port Forwarding is on par with cloud-based solutions, but it required a fraction of setup time. The authors developed a set of shell scripts that monitor the Internet addresses of all networked components and auto-update Port Forwarding settings when they change, solving this issue. With this, Port Forwarding could be considered a viable option for ROS system networks, on par with cloud-based solutions.
Achieving polite service with a public service robot requires it to proactively ascertain who will interact with it in human-populated environments. Enlightened by interactive inference of intentions ...among humans, we investigate a novel and practical interactive intention-predicting method for people using bimodal information analysis for a public service robot. Different from the traditional research, only the visual cues are used to analyze the user's attention, this method combines the RGB-D camera and laser information to perceive the user, which realizes the 360-degree range perception, and compensates for the lack of perspective using the RGB-D camera. In addition, seven kinds of interactive intent features were extracted, and a random forest regression model was trained to score the interaction intentions of the people in the field of view. Considering the inference order of two different sensors, a priority rule for intention inference is also designed. The algorithm is implemented into a robot operation system (ROS) and evaluated on our public service robot. Extensive experimental results illustrate that the proposed method enables public service robots to achieve a higher level of politeness than the traditional, passive interactivity approach in which robots wait for commands from users.
Navigation, which is defined as determining the most convenient way to go from one point to another and make the journey on the planned path, is indispensable for developing a fully autonomous ...system. The navigation stack and its components are a widely studied area in the literature. However, in most of the studies, the developed approaches are tested in laboratory or office environments. Suppose such an approach is intended to be used in a real-world large-scale industrial application. In that case, it must operate to industry standards in a highly dynamic and ever-changing environment and show similar performance on every run or repetitive duty. In this study, for prototypes of industrial autonomous mobile robots (AMRs) equipped with encoders, inertial measurement unit (IMU) and laser rangefinders in order to navigate, an Extended Kalman Filter-based localization approach is implemented using the well-known packages available in the robot operating system (ROS) environment as a part of the navigation stack. Some enhancements are made by showing what kind of challenges may occur in a real factory environment. All developed and/or improved approaches have been tested and validated on the real automotive production lines of the Ford Otosan Kocaeli Plant, considering real working conditions such as real noises, disturbances and obstacles. This is the most important difference that distinguishes this study from similar publications in the literature.
Humanitarian Crisis scenarios typically require immediate rescue intervention. In many cases, the conditions at a scene may be prohibitive for human rescuers to provide instant aid, because of ...hazardous, unexpected, and human threatening situations. These scenarios are ideal for autonomous mobile robot systems to assist in searching and even rescuing individuals. In this study, we present a synchronous ground-aerial robot collaboration approach, under which an Unmanned Aerial Vehicle (UAV) and a humanoid robot solve a Search and Rescue scenario locally, without the aid of a commonly used Global Navigation Satellite System (GNSS). Specifically, the UAV uses a combination of Simultaneous Localization and Mapping and OctoMap approaches to extract a 2.5D occupancy grid map of the unknown area in relation to the humanoid robot. The humanoid robot receives a goal position in the created map and executes a path planning algorithm in order to estimate the FootStep navigation trajectory for reaching the goal. As the humanoid robot navigates, it localizes itself in the map while using an adaptive Monte-Carlo Localization algorithm by combining local odometry data with sensor observations from the UAV. Finally, the humanoid robot performs visual human body detection while using camera data through a Darknet pre-trained neural network. The proposed robot collaboration scheme has been tested under a proof of concept setting in an exterior GNSS-denied environment.
Teleoperation virtual platforms allow people to send their skills and capacities into machines located in either relative close (few meters away) or far (different continents) locations. With the use ...of lightweight protocols, people can remotely control the actions and movements of robots so they can avoid physical interaction with dangerous or risky places. Oil and gas well-pads stations are working zones considered hazardous due to the various chemical substances used in their daily processes. This characteristic makes these places the perfect candidates for the implementation of teleoperation solutions in order to reduce the direct interaction of humans with different chemicals and risky situations. The following investigation focuses on the development of a base teleoperation scheme to perform inspection and maintenance tasks in the inside one of these hydrocarbon facilities. The proposed system aims to generate an easily scalable teleoperation solution using distributed control schemes and a lightweight communication protocol to remotely manipulate a KUKA mobile manipulator. As the first stage of this investigation, the main result focuses on the development of the generic control and communication functions that allow the physical testing of the system using a KUKA YouBOT mobile manipulator and the help of a qualified operator of the station.
Computer science; Electrical engineering; Systems engineering; Automation; Computer engineering; Robotics; Electromechanics; Petroleum industry; IEC-61499; MQTT protocol; Robot operating system (ROS); Teleoperation; Oil & Gas process
Safe and secure operations of robotic systems are of paramount importance. Aiming for achieving the trusted operations of a military robotic vehicle under contested environments, we introduce a new ...cyber-physical system based on the concepts of deep learning Convolutional Neural Network (CNN). The proposed algorithm is specifically designed to reduce the cyber vulnerability of the Robot Operating System (ROS), a well-known middleware platform, widely used in both civilian and military domains. To demonstrate the efficacy of the proposed algorithm, we conduct penetration testing (real-time man-in-the-middle cyberattacks) on the GVR-BOT ground vehicle, a replicate of a military ground robot, developed by the United States Army Combat Capabilities Development Command (CCDC), Ground Vehicle Systems Center. The cyberattacks also exploit the vulnerability of the Robot Operating System employed on its onboard computer. We collect experimental data and train our CNN based on two different operating conditions, namely, legitimate and malicious. We normalize and convert the network traffic data in the form of RGB or grayscale images. We introduce two different types of windowing techniques, namely, the independent and overlapping sliding epochs to efficiently feed the network traffic data to our CNN system. Our research indicates the efficacy of the proposed algorithm as our proposed cyber intrusion detection system can achieve reasonably high accuracies <inline-formula><tex-math notation="LaTeX">\geq</tex-math> <mml:math><mml:mo>≥</mml:mo></mml:math><inline-graphic xlink:href="santoso-ieq1-3302807.gif"/> </inline-formula>99% and substantially small false-positive rates <inline-formula><tex-math notation="LaTeX">\leq</tex-math> <mml:math><mml:mo>≤</mml:mo></mml:math><inline-graphic xlink:href="santoso-ieq2-3302807.gif"/> </inline-formula>2% supported with minimum detection times. In addition, we also compare and demonstrate the relative merits of our proposed algorithm with respect to the performance of some well-known techniques, namely, 'bag-of-features' (BoFs) and Support Vector Machine (SVM) algorithms.
Testing and debugging have become major obstacles for robot software development, because of high system complexity and dynamic environments. Standard, middleware-based data recording does not ...provide sufficient information on internal computation and performance bottlenecks. Other existing methods also target very specific problems and thus cannot be used for multipurpose analysis. Moreover, they are not suitable for real-time applications. In this letter, we present ros2_tracing , a collection of flexible tracing tools and multipurpose instrumentation for ROS 2. It allows collecting runtime execution information on real-time distributed systems, using the low-overhead LTTng tracer. Tools also integrate tracing into the invaluable ROS 2 orchestration system and other usability tools. A message latency experiment shows that the end-to-end message latency overhead, when enabling all ROS 2 instrumentation, is on average 0.0033 ms, which we believe is suitable for production real-time systems. ROS 2 execution information obtained using ros2_tracing can be combined with trace data from the operating system, enabling a wider range of precise analyses, that help understand an application execution, to find the cause of performance bottlenecks and other issues.
This article presents a comprehensive method for radar-camera calibration with a primary focus on real-time projection, addressing the critical need for precise spatial and temporal alignment between ...radar and camera sensor modalities. The research introduces a novel methodology for calibration utilizing geometrical transformation, incorporating radar corner reflectors to establish correspondences. This methodology applies to post-automotive manufacturing for integration into radar-camera applications such as advanced driver-assistance systems (ADASs), adaptive cruise control (ACC), collision warning, and mitigation systems. It also serves post-production for sensor installation and algorithm development. The proposed approach employs an advanced algorithm to optimize spatial and temporal synchronization and radar and camera data alignment, ensuring accuracy in multimodal sensor fusion. Rigorous validation through extensive testing demonstrates the efficiency and reliability of the proposed system. The results show that the calibration method is highly accurate compared to the existing state-of-the-art methods, with minimal errors, an average Euclidean distance (AED) of 1.447, and a root-mean-square reprojection error (RMSRE) of (0.1720, 0.5965), indicating a highly efficient spatial synchronization method. During real-time projection, the proposed algorithm for temporal synchronization achieves an average latency of 35 ms between frames.