3D-Odometry

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.

Multi-degree-of-freedom (MDOF) vehicles have many potential advantages over conventional (i.e., 2-DOF) vehicles. For example, MDOF vehicles can travel sideways and they can negotiate tight turns more easily. In addition, some MDOF designs provide better payload capability, better traction, and improved static and dynamic stability. However, MDOF vehicles with more than three degrees-of-freedom are difficult to control because of their overconstrained nature. These difficulties translate into severe wheel slippage or jerky motion under certain driving conditions. In the past, these problems limited the use of MDOF vehicles to applications where the vehicle would follow a guide-wire, which would correct wheel slippage and control errors. By contrast, autonomous or semi-autonomous mobile robots usually rely on dead-reckoning between periodic absolute position updates and their performance is diminished by excessive wheel slippage. This paper introduces a new concept in the kinematic design of MDOF vehicles. This concept is based on the provision of a compliant linkage between drive wheels or drive axles. Simulation results indicate that compliant linkage allows to overcome the control problems found in conventional MDOF vehicles and reduces the amount of wheel slippage to the same level (or less) than the amount of slippage found on a comparable 2-DOF vehicle.

PurposeMyopia is associated with increased near-work, time spent indoors, and urban environments. This may in part stem from the spatial frequency (SF) composition of the visual environment in such scenarios compared to nature. We investigated the SF content of natural and man-made environments and how the relative contrast experienced may be affected by viewing distance.DesignExperimental study of environmental contrast.Subjects, Participants, and ControlsDigital images (n = 594) from natural, mixed-urban, urban, and indoor environments across Singapore.MethodsThe fast Fourier transform was computed and radially averaged, and the slope of the amplitude spectra with SF was determined. The total contrast energy within each SF octave (f–2f) was measured to determine exposure deficits between environments and whether environmental contrast was scale invariant (unaffected by changes in viewing distance).Main Outcome MeasuresEnvironment differences in SF gradient, total contrast, and scale invariance.ResultsAs expected, indoor environments displayed the steepest SF gradients at –1.36 ± 0.1, more than urban (–1.22 ± 0.1, P < 0.01), mixed-urban (–1.09 ± 0.1, P < 0.01), and natural (–1.00 ± 0.1, P < 0.01) environments. Specifically, mixed-urban, urban, and indoor environments all lacked contrast at middle and higher SFs compared with natural scenes (P < 0.01 each). Contrast energy/octave was approximately equal for natural environments, signifying the relative SF composition was scale invariant. This was not true for man-made environments. Contrast energy/octave decreased as a function of SF in mixed-urban, urban, and most rapidly in indoor environments (P < 0.001 each), meaning the total contrast experienced in such environments is directly dependent on viewing distance. Consequently, halving viewing distance when indoors would reduce total perceived middle SF contrast by 35%, despite indoor environments already being deficient compared to nature.ConclusionsThe SF content of natural environments is consistent regardless of viewing distance, signifying scale invariance. This does not apply in man-made environments where contrast at all SFs directly depends on viewing distance. This implies that shorter viewing distances in man-made environments further exacerbate inherent deficits in middle and higher SF contrast, and thus these environments may fail to stimulate the eye with sufficient contrast compared to natural environments, possibly explaining why such environments induce myopia.Financial Disclosure(s)The authors have no proprietary or commercial interest in any materials discussed in this article.

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. >

Robotic technologies are overgrowing with an improvement in their capabilities, such as “autonomy” and “mobility”. The two main forces driving these advancements are economics and safety. Often referred to as the "three D's": Dirty, Dangerous and Dull, many tasks performed by humans are either dangerous, such as tactical reconnaissance, or highly repetitive, such as patrolling in an industrial factory. Autonomous Mobile Robots are often well suited to these tasks because they can be more consistent and relatively expendable. These robots have historically been designed to replace humans in these dangerous and dull tasks, which means they are designed with human-like capabilities. There is a growth in the development of intelligent systems based on mobile sensors due to increased demand for automated surveillance of indoor and outdoor environments, such as production plants, airports, warehouses, military etc. The fundamental optimization problems related to environmental map representation, localization, navigation, and surveillance tasks have been addressed entirely in most robotic surveillance schemes.

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 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.

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.

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.

Promising SLAM Methods for Automated Guided Vehicles and Autonomous Mobile Robots

Fuzzy drive control of an autonomous mobile robot

To support delivery tasks using autonomous mobile robots (AMRs), an AMR tracks target-of-interest (ToI) objects, such as workers. ToI objects that are tracked using AMRs are specified in advance or through the robot’s settings. It is difficult for an object to be directly set as a ToI object. By making an AMR follow a ToI object wearing a specific vest, the object can be set easily. As such, it is essential to develop a ToI object tracking system that can follow a ToI object wearing a specific vest with AMR. This paper proposes a ToI object tracking system using a specific vest to track changeable ToI objects. The proposed system comprises a recognition unit to recognize a ToI object wearing a specific vest and a control unit to control the AMR. The recognition unit tracks the ToI object and estimates its position while the control unit controls the AMR based on the ToI object’s position. The contributions of this paper are as follows. 1) A system that can follow a changeable ToI object is proposed. 2) This tracking system can easily designate and change ToI objects. In the experiment, the proposed system enabled the AMR to track a changeable ToI object. The recognition unit then calculated the position of the ToI object wearing a specific vest, and the control unit calculated a control signal for the AMR to track the ToI object based on its position.

[EMBARGOED UNTIL 8/1/2024] Order picking, which involves retrieving items from storage locations for an internal or external customer, is a core function in warehouses and accounts for up to 65 percent of the total operating cost. It is considered as a crucial driver for supply chain performance as improper planning of picking operations leads to inefficient asset utilization and delayed deliveries, which, in turn, adversely affects customer satisfaction, operating cost, and competitiveness. A majority of warehouses adopt a picker-to-parts system (workers travel through a warehouse to retrieve and transport items from storage to packing station), and the fulfillment speed of such order picking system (OPS) depends on the following key decisions - (i) set of orders to be picked in a tour (order batching decision), (ii) assignment of a batch to a picker and order in which their a processed (batch assignment and sequencing decisions), and (iii) route followed x by the picker to collect the orders in each batch (picker routing decision). However, with the growing customer demand and global labor shortage, warehouses are seeking efficient and less labor-intensive order picking systems. Autonomous mobile robots (AMRs) or collaborative robots (cobots) have the potential to alleviate the strain on human workers and expedite order picking operations. However, there are several key operational challenges to address for ensuring an effective collaborative human-robot order-picking system (CHR-OPS), where humans perform item retrieval tasks, and AMRs handle item transportation to the depot. This research aims to improve the fulfillment efficiency of a picker-to-parts CHROPS by optimizing key decisions associated with two warehouse picking strategies, namely, static picking and dynamic picking. In the case of static picking, the items to be retrieved from storage for a given day are known as apriority. On the other hand, the dynamic picking strategy allows for orders to arrive over time (e.g., e-commerce warehouses), and the pick cycle (or picking plan) can be updated in real time. First, we address the problem of optimizing the following key subproblems of a CHR-OPS with a static picking strategy: (i) order batching (how many items should be collected in each AMR tour?), (ii) batch assignment and sequencing (how to assign batches to AMRs, and in what order should they be processed?), and (iii) picker-robot routing (how should the AMR and picker be routed to coordinate the picking process?). Existing literature has not dealt with the three subproblems, and this work is the first to address them for a picker-to-parts CHR-OPS system employing multiple pickers and AMRs. A mixed integer linear programming model is developed to jointly optimize the three subproblems with the objective of minimizing the total tardiness of all orders. The MILP model is validated and solved to optimality for small instances. However, since the problem under consideration is NP-hard, it is computationally intractable for larger instances. To efficiently handle large instances, we proposed deterministic and stochastic local search algorithms, namely variable neighborhood descent and a new variant of simulated annealing. The numerical experiments demonstrate the superior performance of the proposed solution approach compared to existing methods. Besides, our results also show that the picking efficiency is impacted by human{robot team composition, AMR speed, AMR capacity and warehouse layout. Subsequently, we address the CHR-OPS with dynamic picking and developing interventionist picking algorithms for a multi-robot multi-human setting. Specifically, we propose two interventionist policies for dynamic collaborative order picking, namely, the collaborative human-robot interventionist picking algorithm (CHRIPA) and the collaborative human-robot rule-based interventionist picking algorithm (CHR-RIPA). The evaluation of the policies demonstrates that the proposed rules can improve the overall performance of the system compared to benchmark approaches (human-only dynamic picking and collaborative picking with no intervention). In addition, results indicate CHR-IPA outperforms CHR-RIPA in terms of average tar diness and order completion time, albeit with a slightly higher travel distance for human workers. The results have led to several managerial implications for a collaborative order picking system. Further, the proposed models and algorithms are modular and can be adapted to any warehouse setting by accounting for the relevant parameters such as warehouse layout, AMR capacity and human-robot composition. Finally, the directions for future research have been identified and summarized.