Autonomous Machines Research Articles

Masters or Slaves? AI and the Future of Humanity

Masters or Slaves? AI and the Future of Humanity

The Role of Compute in Autonomous Micro Aerial Vehicles: Optimizing for Mission Time and Energy Efficiency

Autonomous and mobile cyber-physical machines are becoming an inevitable part of our future. In particular, Micro Aerial Vehicles (MAVs) have seen a resurgence in activity. With multiple use cases, such as surveillance, search and rescue, package delivery, and more, these unmanned aerial systems are on the cusp of demonstrating their full potential. Despite such promises, these systems face many challenges, one of the most prominent of which is their low endurance caused by their limited onboard energy. Since the success of a mission depends on whether the drone can finish it within such duration and before it runs out of battery, improving both the time and energy associated with the mission are of high importance. Such improvements have traditionally been arrived at through the use of better algorithms. But our premise is that more powerful and efficient onboard compute can also address the problem. In this article, we investigate how the compute subsystem, in a cyber-physical mobile machine such as a Micro Aerial Vehicle, can impact mission time (time to complete a mission) and energy. Specifically, we pose the question as what is the role of computing for cyber-physical mobile robots? We show that compute and motion are tightly intertwined, and as such a close examination of cyber and physical processes and their impact on one another is necessary. We show different “impact paths” through which compute impacts mission metrics and examine them using a combination of analytical models, simulation, and micro and end-to-end benchmarking. To enable similar studies, we open sourced MAVBench , our tool-set, which consists of (1) a closed-loop real-time feedback simulator and (2) an end-to-end benchmark suite composed of state-of-the-art kernels. By combining MAVBench, analytical modeling, and an understanding of various compute impacts, we show up to 2X and 1.8X improvements for mission time and mission energy for two optimization case studies, respectively. Our investigations, as well as our optimizations, show that cyber-physical co-design, a methodology with which both the cyber and physical processes/quantities of the robot are developed with consideration of one another, similar to hardware-software co-design, is necessary for arriving at the design of the optimal robot.

Augmented Workforce: contextual, cross-hierarchical enquiries on human-technology integration in industry

Although shop floors become more automated, manual labor is more than the sum of recurring tasks which can simply be executed by autonomous machines. Where total automation is ineffective, operator assistance systems (OAS) could increase productivity and empower the workforce. Operator Assistance Systems (OAS) are systems that interact with operators to modify their cognitive or physical capabilities whilst performing industrial tasks. Given the important role of humans in future manufacturing environments that cannot be automated, production organizations in industry and Human-Technology Integration (HTI) researchers need to understand where OAS can be deployed and what human factors and other human implications arise from their deployment. In short, capturing views from stakeholders who are both affected by and affect the successful implementation of new technologies are essential to align technological innovations with a human-centric perspective. However, based on our literature review of OAS, we find that there are few technology-neutral enquiries on the industrial applicability of OAS. In particular, we note a lack of considerations of the different requirements for OAS resulting from diverse stakeholders in industry, which is expected to be of importance when designing effective HTI. To address this gap, we explore the industrial context of OAS and the perspectives of stakeholder groups across organizations on the applicability of OAS using a multi-method research approach encompassing 27 qualitative expert interviews and ethnographic observations of three industrial contexts. A key finding of our contextual enquiry is that participants expect OAS to be beneficial on shop floors if designed to improve cognitive abilities, such as inductive reasoning. Further, in the case a company seeks to introduce an OAS to augment physical capabilities of operators whilst attached to their bodies, the data indicate a cautious approach is sensible as many operators reject such a form of augmentation. We highlight what our findings mean for HTI research, especially as it relates to consideration of the highly contextual user requirements when developing and integrating human-technology systems for industry.

Single photon imaging and sensing of highly obscured objects around the corner

Non-line-of-sight (NLOS) optical imaging and sensing of objects imply new capabilities valuable to autonomous technology, machine vision, and other applications, in which case very few informative photons are buried in strong background counts. Here, we introduce a new approach to NLOS imaging and sensing using the picosecond-gated single photon detection generated by nonlinear frequency conversion. With exceptional signal isolation, this approach can reliably achieve imaging and position retrieval of obscured objects around the corner, in which case only 4 × 10−3 photons are needed to be detected per pulse for each pixel with high temporal resolution. Furthermore, the vibration frequencies of different objects can be resolved by analyzing the photon number fluctuation received within a ten-picosecond window, allowing NLOS acoustic sensing. Our results highlight the prospect of photon efficient NLOS imaging and sensing for real-world applications.

Eden Library: A long-term database for storing agricultural multi-sensor datasets from UAV and proximal platforms

In modern agriculture, visual recognition systems based on deep learning are arising to allow autonomous machines to execute field operations in crops. However, for obtaining high performances, these methods need high amounts of data, which are usually scarce in agriculture. The main reason is that building an agricultural dataset covering exhaustively a specific problem is challenging, as visual characteristics of the symptoms may change, and there is a high dependency on environmental factors, such as temperature, humidity and light conditions. Therefore, an efficient methodology is necessary to consistently cover the entire workflow for creating an agricultural dataset, from the image acquisition to its online publication. This paper presents the Eden Library, a platform for contributing to this existing gap in open access crop/plant databases covering proximal and aerial images. The complete workflow on the design and deployment of the platform is also explained and discussed. This workflow is relevant because the provided datasets are thought to be maintained and enriched along the time, and they do not just remain as a static research output covering only specific species, growth stages, and conditions. The image annotations of plants and symptoms are provided, saving users from manually annotating images. Currently, the Eden Library covers 15 different crops, 9 weeds and 30 disorders (pests, diseases and nutrient deficiencies). Eden Library aspires to close this gap by providing a large and diversified image collection of plants, organized in a consistent manner, in order to boost further vision-based and AI-enabled field applications.

Rapid SARS-CoV-2 Inactivation in a Simulated Hospital Room Using a Mobile and Autonomous Robot Emitting Ultraviolet-C Light.

The spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) since 2019 has made mask-wearing, physical distancing, hygiene, and disinfection complementary measures to control virus transmission. Especially for health facilities, we evaluated the efficacy of an UV-C autonomous robot to inactivate SARS-CoV-2 desiccated on potentially contaminated surfaces. ASSUM (autonomous sanitary sterilization ultraviolet machine) robot was used in an experimental box simulating a hospital intensive care unit room. Desiccated SARS-CoV-2 samples were exposed to UV-C in 2 independent runs of 5, 12, and 20 minutes. Residual virus was eluted from surfaces and viral titration was carried out in Vero E6 cells. ASSUM inactivated SARS-CoV-2 by ≥ 99.91% to ≥ 99.99% titer reduction with 12 minutes or longer of UV-C exposure and onwards and a minimum distance of 100cm between the device and the SARS-CoV-2 desiccated samples. This study demonstrates that ASSUM UV-C device is able to inactivate SARS-CoV-2 within a few minutes.

Avoiding adverse autonomous agent actions

Few today would dispute that the age of autonomous machines is nearly upon us (cf., Kurzweil, 2005; Moravec, 1988), if it is not already. While it is doubtful that one can identify any fully autono...

Intelligent vision based wear forecasting on surfaces of machine tool elements

To realize autonomous production machines it is necessary that machines are able to automatically and autonomously predict their condition. Although many classical as well as Deep Learning based approaches have shown the ability to classify faults, so far there are no approaches that go beyond the basic detection of faults. A complete, image based predictive maintenance approach for machine tool components has to the best of our knowledge not been investigated so far. In this paper it is shown how defects on a Ball Screw Drive (BSD) can be automatically detected by using a machine learning based detection module, quantified by using an intelligent defect quantification module and finally forecasted by a prognosis module in a combined approach. To optimize the presented method, it is shown how existing domain knowledge can be formalized in an expert system and combined with the predictions of the machine learning model to aid quality of the prediction system. This enables the practitioner to forecast the severity of failures on BSD and prevent machine breakdowns. The work is intended to set new accents for the development of practical predictive maintenance systems and bridging the fields of machine learning and production engineering. The code is available under: https://github.com/2Obe/Pitting_Pred_Maintenance.

Predictive Quality of Service: The Next Frontier for Fully Autonomous Systems

Recent advances in software, hardware, computing, and control have fueled significant prog-ress in the field of autonomous systems. Notably, autonomous machines should continuously estimate how the scenario in which they move and operate will evolve within a predefined timeframe, and foresee whether or not the network will be able to fulfill the agreed quality of service (QoS). If not, appropriate countermea-sures should be taken to satisfy the application requirements. Along these lines, in this article we present possible methods to enable predictive QoS (PQoS) in autonomous systems, and discuss which use cases will particularly benefit from network prediction. Then we shed light on the challenges in the field that are still open for future research. As a case study, we demonstrate whether machine learning can facilitate PQoS in a teleoperated-driving-like use case as a function of different measurement signals.

The Role of Muscle Spindle Feedback in the Guidance of Hindlimb Movement by the Ipsilateral Forelimb during Locomotion in Mice.

Safe and efficient locomotion relies on placing the foot on a reliable surface at the end of each leg swing movement. Visual information has been shown to be important for determining the location of foot placement in humans during walking when precision is required. Yet in quadrupedal animals where the hindlimbs are outside of the visual field, such as in mice, the mechanisms by which precise foot placement is achieved remain unclear. Here we show that the placement of the hindlimb paw is determined by the position of the forelimb paw during normal locomotion and in the presence of perturbations. When a perturbation elicits a stumbling corrective reaction, we found that the forelimb paw shifts posteriorly relative to body at the end of stance, and this spatial shift is echoed in hindlimb paw placement at the end of the swing movement. Using a mutant mouse line in which muscle spindle feedback is selectively removed, we show that this posterior shift of paw placement is dependent on muscle spindle feedback in the hindlimb but not in the forelimb. These findings uncover a neuronal mechanism that is independent of vision to ensure safe locomotion during perturbation. This mechanism adds to our general knowledge of how the nervous system controls targeted limb movements and could inform the development of autonomous walking machines.

Early detection algorithm for alzheimer’s disease using autonomous learning

The current document describes the approach to a research problem that aims to generate an algorithm that allows detecting the probable appearance of Alzheimer’s disease in its first phase, using autonomous learning techniques or Machine Learning, more specifically KNN (K- nearest Neighbor) with which the best result was obtained. This development will be based on a complete information bank taken from ADNI (Alz- heimer’s Disease NeuroImaging Initiative), with all the necessary parameters to direct the inves- tigation to an algorithm that is as efficient as pos- sible, since it has biological, sociodemographic and medical history data, biological specimens, neural images, etc., and in this way the early de- tection of the aforementioned disease was con- figured. A complete guide to the process will be carried out to finally obtain the KNN algorithm whose efficiency is 99%, and then discuss the obtained results.

DIGITALIZATION OF THE WORLD ECONOMY: THEORETICAL AND POLITICAL ASPECTS

The purpose of this article is to explore the theoretical background of the digitalization of the world economy, focusing on the channels of influence of digitalization on economic growth. There is also a discussion of policy priorities to enhance the positive effects and limit the negative effects of digitalization. Systematic and comparative analysis methods were used. The main conclusions are that early research on the impact of digital technology on economic growth has failed to fully explain the sustained correlation between digitalization and productivity, mainly because of the limitations of available statistics in the past. Recent studies largely suggest that digital technology can have a positive impact on productivity through channels such as robotics that increase productivity on assembly lines, autonomous machines and intelligent systems that increase data analysis and operations productivity, automated maintenance scheduling that increases productivity by reducing downtime due to breakdowns, 3-D printing technology that increases productivity through rapid production of parts, reducing the supply chain, innovative materials that reduce costs and processing time, informatics that reduce costs and reanalysis time. It is argued that, in reality, these channels may have much less impact on productivity than their potential, due to a number of market characteristics and policy constraints. The phenomenon of the digital divide includes unequal income distribution, unequal access to technology, and risks of increased unemployment, etc. Thus, effective, comprehensive policies to promote digitalization at various levels can have an important impact on the economic and social goals of the nation. Recommendations are given to solve the problem of the "digital divide" as follows: improving skills and technical knowledge, providing high-speed Internet in rural and remote areas, redistribution of labor and capital, competition policy tools in case of a large influence of platform business on markets, reducing financial constraints for young innovative firms and start-ups, transition to public digital services, digital-friendly policy for the elderly population.

Simplifying the design of multilevel thermal machines using virtual qubits

Quantum thermodynamics often deals with the dynamics of small quantum machines interfacing with a large and complex environment. Virtual qubits, collisional models and reset master equations have become highly useful tools for predicting the qualitative behaviour of two-dimensional target systems coupled to few-qubit machines and a thermal environment. While few successes in matching the simplified model parameters for all possible physical systems are known, the qualitative predictions still allow for a general design of quantum machines irrespective of the implementation. We generalise these tools by introducing multiple competing virtual qubits for modelling multi-dimensional systems coupled to larger and more complex machines. By simulating the full physical dynamics for targets with three dimensions, we uncover general properties of reset models that can be used as `dials' to correctly predict the qualitative features of physical changes in a realistic setup and thus design autonomous quantum machines beyond a few qubits. We then present a general analytic solution of the reset model for arbitrary-dimensional systems coupled to multi-qubit machines. Finally, we showcase an improved three-level laser as an exemplary application of our results.

AN OVERVIEW ON ROBOTICS AND CONTROL SYSTEMS

A robot is a virtual or mechanical agent. In practice, it is often an electro-mechanical system, which looks and speeds as if it were one of its own. The intent and its own agency. The term robot refers to both physical robots and virtual software agents, but often virtual software agents are called bots. There has been no consensus that machines are qualified as robots, but there is a consensus among experts and the public that some or all of the following can be done such as: walking, operating a device or a component of the environment, the environment Understanding and manipulating it and imparting intelligent behavior that mimics human and animal behaveor. The stories of artificial assistants and companions and and the effort to create them have a long history, but fully autonomous machines were the only programmed first robot to run in the digital system since the 20th century, Unimate, In 1971, hot pieces of metal were picked up from the stamp making machine and made to make their stack. Today, commercial and industrial robots are widely used inexpensively and with greater accuracy and greater reliability than humans. They are also employed for tasks which are very dangerous in human terms. , Messy and boring tasks. Robots are being widely used for manufacturing, assembly and bundling, transportation, earth and space exploration, surgery, weapons manufacturing, laboratory research and consumer and industrial production. Domestic robots are generally common around homes for cleaning and maintenance work. Concerns about the economic impact of robotic weapons and automation are generally common. Remains, a concern that is not resolved by the villainous, intelligent, acrobatic robots described in popular entertainment. Real robots are still benign, retarded, and gross compared to their imaginary counterparts.

The social turn of artificial intelligence

Social machines are systems formed by material and human elements interacting in a structured way. The use of digital platforms as mediators allows large numbers of humans to participate in such machines, which have interconnected AI and human components operating as a single system capable of highly sophisticated behaviour. Under certain conditions, such systems can be understood as autonomous goal-driven agents. Many popular online platforms can be regarded as instances of this class of agent. We argue that autonomous social machines provide a new paradigm for the design of intelligent systems, marking a new phase in AI. After describing the characteristics of goal-driven social machines, we discuss the consequences of their adoption, for the practice of artificial intelligence as well as for its regulation.

Measurement of latency during real-time wireless video transmission for remote supervision of autonomous agricultural machines

As the prominence of autonomous vehicles continues to rise within agriculture, remote surveillance of the equipment is likely to become a key aspect of operation. Transmission latency during the relay of video from vehicle to viewer is not well explored and is an important part of communications which should be assessed. A riding mower was equipped with a Raspberry Pi using GStreamer and an open-source latency measurement library to assemble a real-time streaming system to evaluate transmission latency in different environments using cellular and radio transmission. In most locations, measured latencies were under 200–300 ms. In areas where cellular connection quality was adequate, cellular latency and variance were reduced compared to that of radio transmission for higher qualities of video. In areas of poor cellular network coverage, cellular transmission latency increased while radio transmission latencies remained constant. Overall, latency tends to increase with video quality to a statistically significant degree. It is recommended that real-time video can be transmitted over short distances for edge-of-field surveillance of autonomous agricultural machines using existing cellular networks in areas where adequate cellular signal strength is available. If adequate cellular signal strength is not available in a specific field location, it is recommended that video should be transmitted using radio transmission.

Classification of Lathe’s Cutting Tool Wear Based on an Autonomous Machine Learning Model

Classification of Lathe’s Cutting Tool Wear Based on an Autonomous Machine Learning Model

RAI: Rapid, Autonomous and Intelligent machine learning approach to identify fire-vulnerable bridges

Recent surveys have noted that the majority of bridges continue to serve for a prolonged period of time (+40 years) that far exceeds its intended operational lifespan. Given our limited resources to maintain and upkeep bridges, these structures become notoriously vulnerable to extreme events. Building upon the fact that bridges continue not to be specifically designed to withstand the adverse effects of fire, this study presents the development of a rapid, automated, and intelligent (RAI) approach that leverages machine learning to identify vulnerable bridges to fire hazard. This work also presents details on a comprehensive database comprising actual observations collected from 135 notable and international bridge fire incidents. This database was developed to train two machine learning techniques, deep learning and genetic algorithms, to quantify hidden patterns that govern the propensity of existing/new/historical bridges to undergo fire damage and/or fire-induced collapse via a multi-classification analysis. The proposed RAI approach also has the capability to pinpoint fire-vulnerable bridge components and to display its level of confidence in its predictions. As such, our approach can be of aid to bridge engineers and government officials (who may not be well-versed in fire design) with accuracy reaching 89.6%. This approach is implemented into a software (App) with optimized architecture and reduced computational complexity and hence is easily scalable and integratable into a user-friendly framework and handheld devices. The outcome of this study shows that the RAI approach can be deployed to arrive at an instantaneous assessment of fire vulnerable bridges.

Sensing and Biosensing in the World of Autonomous Machines and Intelligent Systems

In this paper we discuss how nanotech-based sensors and biosensors are providing the data for autonomous machines and intelligent systems, using two metaphors to exemplify the convergence between nanotechnology and artificial intelligence (AI). These are related to sensors to mimic the five human senses, and integration of data from varied sources and natures into an intelligent system to manage autonomous services, as in a train station.

Artificial Intelligence Marketing (AIM) for Enhancing Customer Relationships

Based on the literature, we present an artificial intelligence marketing (AIM) framework that enables autonomous machines to receive big data and information, use artificial intelligence (AI) to create knowledge, and then disseminate and apply the knowledge to enhance customer relationships in a knowledge-based environment. To develop the AIM framework, we bring together and curate a wide range of relevant literatures including real-life examples and cases, and then understand how these literatures contribute to the framework in this research topic. We explain the AIM framework from the interdisciplinary perspective, which is an important role of both the artificial intelligence and marketing academia. The AIM framework includes three main components, including the pre-processor, the main processor, and the memory storage. The main processor, which is the key component, uses AI to process structured data processed by pre-processor in order to make real-time decisions and reasonings. The AI approach is characterized by its hypothetical abilities, learning paradigms, and operation modes with human. The strategic use of the developed AIM framework based on the literature to enhance customer relationships, including customer trust, satisfaction, commitment, engagement, and loyalty, is presented. Finally, future potential investigations are presented to drive forward this interdisciplinary research topic.