Development Of Autonomous System Research Articles

ScribbleNet: Efficient interactive annotation of urban city scenes for semantic segmentation

Annotation is a crucial first step in the semantic segmentation of urban images that facilitates the development of autonomous navigation systems. However, annotating complex urban images is time-consuming and challenging. It requires significant human effort making it expensive and error-prone. To reduce human effort during annotation, multiple images need to be annotated in a short time-span. In this paper, we introduce ScribbleNet, an interactive image segmentation algorithm to address this issue. Our approach provides users with a pre-segmented image that iteratively improves the segmentation using scribble as an annotation input. This method is based on conditional inference and exploits the learnt correlations in a deep neural network (DNN). ScribbleNet can: (1) work with urban city scenes captured in unseen environments, (2) annotate new classes not present in the training set, and (3) correct several labels at once. We compare this method with other interactive segmentation approaches on multiple datasets such as CityScapes, BDD, Mapillary Vistas, KITTI, and IDD. ScribbleNet reduces the annotation time of an image by up to 14.7 × over manual annotation and up to 5.4× over the current approaches. The algorithm is integrated into the publicly available LabelMe image annotation tool and will be released as an open-source software.

Artificial intelligence and responsibility gaps: what is the problem?

Recent decades have witnessed tremendous progress in artificial intelligence and in the development of autonomous systems that rely on artificial intelligence. Critics, however, have pointed to the difficulty of allocating responsibility for the actions of an autonomous system, especially when the autonomous system causes harm or damage. The highly autonomous behavior of such systems, for which neither the programmer, the manufacturer, nor the operator seems to be responsible, has been suspected to generate responsibility gaps. This has been the cause of much concern. In this article, I propose a more optimistic view on artificial intelligence, raising two challenges for responsibility gap pessimists. First, proponents of responsibility gaps must say more about when responsibility gaps occur. Once we accept a difficult-to-reject plausibility constraint on the emergence of such gaps, it becomes apparent that the situations in which responsibility gaps occur are unclear. Second, assuming that responsibility gaps occur, more must be said about why we should be concerned about such gaps in the first place. I proceed by defusing what I take to be the two most important concerns about responsibility gaps, one relating to the consequences of responsibility gaps and the other relating to violations of jus in bello.

Associations between maternal prenatal depression and neonatal behavior and brain function – Evidence from the functional near-infrared spectroscopy

BackgroundMaternal prenatal depression is a significant public health issue associated with mental disorders of offspring. This study aimed to determine if maternal prenatal depressive symptoms are associated with changes in neonatal behaviors and brain function at the resting state. MethodsA total of 204 pregnant women were recruited during the third trimester and were evaluated by Edinburgh Postpartum Depression Scale (EPDS). The mother-infant pairs were divided into the depressed group (n = 75) and control group (n = 129) based on the EPDS, using a cut-off value of 10. Cortisol levels in the cord blood and maternal blood collected on admission for delivery were measured. On day three of life, all study newborns were evaluated by the Neonatal Behavior Assessment Scale (NBAS) and 165 infants were evaluated by resting-state functional near-infrared spectroscopy (rs-fNIRS). To minimize the influences of potential bias on the rs-fNIRS results, we used a binary logistic regression model to carry out propensity score matching between the depressed group and the control group. Rs-fNIRS data from 21 pairs of propensity score-matched newborns were used for analysis. The associations between maternal EPDS scores, neonatal NBAS scores, and cortisol levels were analyzed using linear regressions and the mediation analysis models. ResultsCompared to the control group, the newborns in the depressed group had lower scores in the social-interaction and autonomic system dimensions of NBAS (P < 0.01). Maternal and umbilical cord plasma cortisol levels in the depressed group were higher (P < 0.01) than in the control group. However, only umbilical cord plasma cortisol played a negative mediating role in the relationship between maternal EPDS and NBAS in the social-interaction and autonomic system (β med = −0.054 [−0.115,−0.018] and −0.052 [−0.105,−0.019]. Proportional mediation was 13.57 % and 12.33 for social-interaction and autonomic systems, respectively. The newborns in the depressed group showed decreases in the strength of rs-fNIRS functional connections, primarily the connectivity of the left frontal-parietal and temporal-parietal regions. However, infants in the depressed and control groups showed no differences in topological characteristics of the brain network, including standardized clustering coefficient, characteristic path length, small-world property, global efficiency, and local efficiency (P > 0.05). The social-interaction Z-scores had positive correlations with functional connectivity strength of left prefrontal cortex-left parietal lobe (r = 0.57, p < 0.01)，prefrontal cortex-left parietal lobe - left temporal lobe (r = 0.593, p < 0.01) and left parietal lobe - left temporal lobe (r = 0.498, p < 0.01). Autonomic system Z-scores were also significantly positive correlation with prefrontal cortex-left parietal lobe (r = 0.509, p < 0.01)，prefrontal cortex-left parietal lobe - left temporal lobe (r = 0.464, p < 0.01), left parietal lobe - left temporal lobe (r = 0.381, p < 0.05), and right temporal lobe and left temporal lobe (r = 0.310, p < 0.05). ConclusionThis study shows that maternal prenatal depression may affect the development of neonatal social-interaction and autonomic system and the strength of neonatal brain functional connectivity. The fetal cortisol may play a role in behavioral development in infants exposed to maternal prenatal depression. Our findings highlight the importance of prenatal screening for maternal depression and early postnatal behavioral evaluation that provide the opportunity for early diagnosis and intervention to improve neurodevelopmental outcomes.

Electrification of Rural Remote Areas Using Renewable Energy Sources: Literature Review

The current stage of development of autonomous energy systems is characterized by a rapid increase in renewable energy sources’ installed capacity. Such growth is observed both in centralized and isolated energy systems. Renewable energy sources show high efficiency in the electrification of rural remote settlements around the world. The power of such power complexes varies from several kilowatts to tens of megawatts. When solving the problems of rural remote settlements electrification, the main issues of optimizing the composition of equipment and the structure of the energy systems play an extremely important role. Moreover, depending on the specifications of the problem being solved, criteria for evaluating efficiency are used, which are different. For example, the following are used as objective functions: minimization of the levelized cost of energy and fossil fuel consumption; maximizing the standard of people living and reliability indicators; the payback period of the project and other indicators. Various combinations of objective functions and the solution to the multi-criteria optimization problem are possible. Moreover, an important stage in the development of renewable energy in remote rural areas is the availability of new mechanisms to support an environmentally friendly generation. These mechanisms can be used in solving problems of optimizing the structure and composition of energy equipment in remote power systems. The main purpose of this article is to demonstrate the world practices of optimal design of isolated energy systems. The review includes both the main questions that arise when solving such problems, and specific problems that require a more detailed analysis of the object of study.

Dynamic speed trajectory generation and tracking control for autonomous driving of intelligent high-speed trains combining with deep learning and backstepping control methods

The development of autonomous transportation systems has received increasing attention over the last decades. Different from existing automatic train control systems, the decision-making capability in the autonomous driving system enables a train to adapt to the complicated and dynamic circumstances. This paper in particular focuses on the decision-making problem for the autonomous driving of intelligent high-speed trains, and proposes a novel decision-making framework by combining the deep learning and backstepping control methods. By exploiting the deep learning methods, a speed trajectory generator is trained with the actual driving data, and dynamically calculates the reference speed trajectory according to the real-time driving condition. Then, a backstepping controller is designed to track the reference speed trajectory such that the separation, cohesion and alignment requirements for the autonomous driving of high-speed trains are achieved. Simulation experiments are implemented to illustrate the effectiveness of our methods.

Design and development of orchard autonomous navigation spray system.

Driven by the demand for efficient plant protection in orchards, the autonomous navigation system for orchards is hereby designed and developed in this study. According to the three modules of unmanned system “perception-decision-control,” the environment perception and map construction strategy based on 3D lidar is constructed for the complex environment in orchards. At the same time, millimeter-wave radar is further selected for multi-source information fusion for the perception of obstacles. The extraction of orchard navigation lines is achieved by formulating a four-step extraction strategy according to the obtained lidar data. Finally, aiming at the control problem of plant protection machine, the ADRC control strategy is adopted to enhance the noise immunity of the system. Different working conditions are designed in the experimental section for testing the obstacle avoidance performance and navigation accuracy of the autonomous navigation sprayer. The experimental results show that the unmanned vehicle can identify the obstacle quickly and make an emergency stop and find a rather narrow feasible area when a moving person or a different thin column is used as an obstacle. Many experiments have shown a safe distance for obstacle avoidance about 0.5 m, which meets the obstacle avoidance requirements. In the navigation accuracy experiment, the average navigation error in both experiments is within 15 cm, satisfying the requirements for orchard spray operation. A set of spray test experiments are designed in the final experimental part to further verify the feasibility of the system developed by the institute, and the coverage rate of the leaves of the canopy is about 50%.

Real-Time Free Space Semantic Segmentation for Detection of Traversable Space for an Intelligent Wheelchair.

The last decades saw a great innovation in computer vision. Recently, the field has been fundamental in the development of autonomous navigation systems. Modern assistive technologies, like smart wheelchairs, could employ autonomous navigation to assist users during operation. A prerequisite for such systems is to recognise the navigable space in real-time. The current research features an off-the-shelf powered wheelchair customised into an intelligent robot, which perceives the environment using Point Cloud Semantic Segmentation (PCSS). The implemented algorithm is used to distinguish between two conditions, traversable and non-traversable space, in real-time, using the aforementioned conditions as the two labelled classes. The accuracy of traversable space detection resulted as 99.64% while the accuracy of non-traversable space detection was 91.79%. The performance of the suggested method was invariant to changes in wheelchair velocity indicating that the latency of the suggested algorithm is within the tolerable limits for real-time operation.

Deep understanding of big geospatial data for self-driving: Data, technologies, and systems

With the continued development of Autonomous Vehicle System (AVS), self-driving related technologies have attracted much attention over the past decade. In this light, we survey existing literature regarding self-driving related data, technologies, and systems. We present details of representative studies regarding collision avoidance, automatic lane-changing maneuver, object detection (including pedestrian detection and obstacle detection), and vehicle trajectory prediction, respectively. This survey summarizes the findings of existing self-driving studies, thus uncovering new insights that may guide researchers and software engineers in fields of self-driving data management systems and autonomous vehicle systems.

Development and testing of an image transformer for explainable autonomous driving systems

Purpose Perception has been identified as the main cause underlying most autonomous vehicle related accidents. As the key technology in perception, deep learning (DL) based computer vision models are generally considered to be black boxes due to poor interpretability. These have exacerbated user distrust and further forestalled their widespread deployment in practical usage. This paper aims to develop explainable DL models for autonomous driving by jointly predicting potential driving actions with corresponding explanations. The explainable DL models can not only boost user trust in autonomy but also serve as a diagnostic approach to identify any model deficiencies or limitations during the system development phase. Design/methodology/approach This paper proposes an explainable end-to-end autonomous driving system based on “Transformer,” a state-of-the-art self-attention (SA) based model. The model maps visual features from images collected by onboard cameras to guide potential driving actions with corresponding explanations, and aims to achieve soft attention over the image’s global features. Findings The results demonstrate the efficacy of the proposed model as it exhibits superior performance (in terms of correct prediction of actions and explanations) compared to the benchmark model by a significant margin with much lower computational cost on a public data set (BDD-OIA). From the ablation studies, the proposed SA module also outperforms other attention mechanisms in feature fusion and can generate meaningful representations for downstream prediction. Originality/value In the contexts of situational awareness and driver assistance, the proposed model can perform as a driving alarm system for both human-driven vehicles and autonomous vehicles because it is capable of quickly understanding/characterizing the environment and identifying any infeasible driving actions. In addition, the extra explanation head of the proposed model provides an extra channel for sanity checks to guarantee that the model learns the ideal causal relationships. This provision is critical in the development of autonomous systems.

The development of robotics and autonomous systems in Australia: key issues, actors, and discourses

ABSTRACT Robotics and autonomous systems (RAS) are amongst a plethora of new and emerging technologies states are seeking to develop and use to gain military advantage in an environment of intensifying strategic competition. Australia is a key player when it comes to autonomous systems, with trusted autonomous systems (TAS) being earmarked as a priority area. RAS have taken an increasingly prevalent place in Australian research, discourse, military thinking, and defence industry. How Australia thinks about these technologies reveals important insights into their broader defence and strategic outlook, including their understanding of how the character of warfare is changing, and their approach to alliances and partnerships. In this article, I will trace how TAS became a priority area for defence in Australia, and provide a stocktake of the key developments in RAS which have taken place since 2016. This will include key actors, funding, discourses, and technologies. Taking stock of RAS in Australia reveals several key themes which stand out: the centrality of the concept of control, trust, ethics, interoperability, keeping ahead of adversaries, reducing danger to defence personnel, and developing systems which are cheap, small, and single-use.

User-Centered Approaches in Conventional and Autonomous Truck Design and Future Effects on Environmental Design

Meeting the world’s increasing need for transportation today soon requires the development of autonomous vehicle systems. User-centered approaches in industrial design are crucial to advance technological, mechanical, and equipment specifications and provide effective driving experiences. This study analyzes conventional and new generation autonomous vehicles through user-centered design (UCD) and drivers’ experiences. Turkish company BMC and the new truck series “Tuğra” are selected. Participants are truck drivers, designers, engineers, and specialists. Observations and face-to-face interviews investigated comfort, usefulness, usability, desirability, accessibility, credibility, findability, and value from the elements of user experience design within the truck, as well as users’ awareness of UCD. Credibility and usability were among the highest-ranked principles. The participants provided valuable information for the design development of trucks, and ideas for future problems and solutions. Further multidisciplinary research that focuses on technical, as well as social and ethical issues is essential in this new and emerging area.

Explorative Experiments: A Paradigm Shift to Deal with Severe Uncertainty in Autonomous Robotics

AbstractThis paper presents a case of severe uncertainty in the development of autonomous and intelligent systems in Artificial Intelligence and autonomous robotics. After discussing how uncertainty emerges from the complexity of the systems and their interaction with unknown environments, the paper describes the novel framework of explorative experiments. This framework presents a suitable context in which many of the issues relative to uncertainty, both at the epistemological level and at the ethical one, in this field should be reframed. The case of autonomous robot systems for search and rescue is used to make the discussion more concrete.

Development and Implementation of Autonomous Quality Management System (AQMS) in an Automotive Manufacturing using Quality 4.0 Concept– A Case Study

PurposeThe goal of this research is to use the Quality 4.0 (Q4.0) concept to digitalize the traditional Quality Management System (QMS) and demonstrate the efficiency of the Autonomous Quality Management System (AQMS) in the case organization. Design/Methodology/ApproachThe Internet of Things (IoT) concept was used to develop AQMS. The Q4.0 technique was used to digitalize the developed system. Gage repeatability and reproducibility (gage R&R) of traditional and autonomous QMS systems have been evaluated. Both the QMS systems were examined using six-sigma quality indicators, as well as machining and inspection cost analysis. FindingsIn traditional and autonomous QMS, the gage R&R was found to be 91.60 percent and 0.67 percent, respectively. The special purpose machine (SPM), computer numerical control (CNC), and hydraulic machine production rates were increased by 44.42 percent, 65.60 percent, and 65.76 percent, respectively. The effective deployment of AQMS has reduced the production and inspection costs by 52.16 percent and 78.35 percent. The AQMS process yield has increased from 86.80 percent to 99.99 percent, and the component rejection rate has decreased by 93.70 percent. Overall machining process improved significantly as the sigma level increased from 1.5 to 5.5. Research Limitation/ImplicationThe current study's findings are limited to hub bolt products only. In future investigations, the application of AQMS to other types of products will be considered. Originality/ValuesThis study was carried out practically to reflect the effectiveness of the implemented Q4.0 concept in the actual industry scenario.

Expertise, playfulness and analogical reasoning: three strategies to train Artificial Intelligence for design applications

This paper presents a theoretical framework for the implementation of Artificial Intelligence (AI) in architectural and structural design processes, and it is complemented by some practical applications. The aim is to demonstrate that AI can be used to simulate certain aspects of human cognition and can therefore be integrated into CAD software to support conceptual design and idea generation in a number of different ways. The aim of this study is also to investigate to what extent AI models can interact with a designer to explore future forms of human–machine interaction, including autonomous and participative design. This study identifies and applies AI models to simulate three distinct learning mechanisms: design expertise, playfulness and analogical reasoning. Each strategy has been applied to train different AI models, including generative models and reinforcement learning agents. In the first application, the AI model extracts visual features from a dataset of shell and spatial structures, and then recombines such features to generate new design propositions. In the second application, an AI agent learns a design strategy to solve a toy-design problem with no prior knowledge of precedents. The third application illustrates that AI can be trained to discover meaningful features from biological forms and generate simple design objects through the visual abstraction of such forms. The applications demonstrate the ability of AI to synthesise design options and interact with a designer through visual data formats, such as 2D images and 3D models. This work does not focus on assessing the usefulness of AI models in a real-world design scenario, or on comparing AI with current computational design tools and approaches. It instead investigates different forms of design exploration for computational design purposes, thus paving the way for the development of future autonomous and participative design systems.

A Review on Software/Systems Architecture Description for Autonomous Systems

Background: The design of Autonomous Systems must consider multiple elements of the system, such as agents, physical objects and their software counterparts, control mechanisms, sensors, actuators, and other components. All these distributed elements in the environment make the necessity of creating multiple views for design, including system coordination, development, structural, and behavior views. Therefore, Software/Systems Architectures have been recognized as an important element in process development to manage the systems' complexity. Objective: The objective of this article is to describe a review of architecture characteristics, approaches, styles, and standards that are commonly considered for the development of autonomous systems. Method: First, we describe important elements of software architecture, as well as the standards used in this field. Then, we describe the types of approaches for architecture design. In addition, we provide a classification of software/systems architectures for autonomous systems. Results: As a result, we present a review on the Software/Systems Architecture description for Autonomous Systems. We also find that formal architecture standards are rarely considered in practice, and a large variety of nonfunctional requirements is mentioned. Conclusion: As autonomous systems deal with many components interacting with the real world, under certain quality constraints, considering trade-offs and decisions, software/system architectures are highly relevant for managing all this complexity. A list of main challenges for autonomous systems is described and then discussed according to a review of the literature. This review can be useful for professionals and researchers in identifying software/systems architecture as an important technical element for developing autonomous systems.

Evaluating feature combination strategies for hate-speech detection in Spanish using linguistic features and transformers

The rise of social networks has allowed misogynistic, xenophobic, and homophobic people to spread their hate-speech to intimidate individuals or groups because of their gender, ethnicity or sexual orientation. The consequences of hate-speech are devastating, causing severe depression and even leading people to commit suicide. Hate-speech identification is challenging as the large amount of daily publications makes it impossible to review every comment by hand. Moreover, hate-speech is also spread by hoaxes that requires language and context understanding. With the aim of reducing the number of comments that should be reviewed by experts, or even for the development of autonomous systems, the automatic identification of hate-speech has gained academic relevance. However, the reliability of automatic approaches is still limited specifically in languages other than English, in which some of the state-of-the-art techniques have not been analyzed in detail. In this work, we examine which features are most effective in identifying hate-speech in Spanish and how these features can be combined to develop more accurate systems. In addition, we characterize the language present in each type of hate-speech by means of explainable linguistic features and compare our results with state-of-the-art approaches. Our research indicates that combining linguistic features and transformers by means of knowledge integration outperforms current solutions regarding hate-speech identification in Spanish.

An Autonomous Task Assignment Paradigm for Autonomous Robotic In-Space Assembly.

The development of autonomous robotic systems is a key component in the expansion of space exploration and the development of infrastructures for in-space applications. An important capability for these robotic systems is the ability to maintain and repair structures in the absence of human input by autonomously generating valid task sequences and task to robot allocations. To this end, a novel stochastic problem formulation paired with a mixed integer programming assembly schedule generator has been developed to articulate the elements, constraints, and state of an assembly project and solve for an optimal assembly schedule. The developed formulations were tested with a set of hardware experiments that included generating an optimal schedule for an assembly and rescheduling during an assembly to plan a repair. This formulation and validation work provides a path forward for future research in the development of an autonomous system capable of building and maintaining in-space infrastructures.

Smart automotive technology adherence to the law: (de)constructing road rules for autonomous system development, verification and safety

Abstract Driving is an intuitive task that requires skill, constant alertness and vigilance for unexpected events. The driving task also requires long concentration spans, focusing on the entire task for prolonged periods, and sophisticated negotiation skills with other road users including wild animals. Modern motor vehicles include an array of smart assistive and autonomous driving systems capable of subsuming some, most, or in limited cases, all of the driving task. Building these smart automotive systems requires software developers with highly technical software engineering skills, and now a lawyer’s in-depth knowledge of traffic legislation as well. This article presents an approach for deconstructing the complicated legalese of traffic law and representing its requirements and flow. Our approach (de)constructs road rules in legal terminology and specifies them in ‘structured English logic’ that is expressed as ‘Boolean logic’ for automation and ‘Lawmaps’ for visualization. We demonstrate an example using these tools leading to the construction and validation of a ‘Bayesian Network model’. We strongly believe these tools to be approachable by programmers and the general public, useful in development of Artificial Intelligence to underpin motor vehicle smart systems, and in validation to ensure these systems are considerate of the law when making decisions.

An End-to-End UAV Simulation Platform for Visual SLAM and Navigation

Visual simultaneous localization and mapping (v-SLAM) and navigation of unmanned aerial vehicles (UAVs) are receiving increasing attention in both research and education. However, extensive physical testing can be expensive and time-consuming due to safety precautions, battery constraints, and the complexity of hardware setups. For the efficient development of navigation algorithms and autonomous systems, as well as for education purposes, the ROS-Gazebo-PX4 simulator was customized in-depth, integrated into our previous released research works, and provided as an end-to-end simulation (E2ES) solution for UAV, v-SLAM, and navigation applications. Unlike most other similar works, which can only stimulate certain parts of the navigation algorithms, the E2ES platform simulates all of the localization, mapping, and path-planning kits in one simulator. The navigation stack performs well in the E2ES test bench with the absolute pose errors of 0.3 m (translation) and 0.9 degree (rotation), respectively, for an 83 m length trajectory. Moreover, the E2ES provides an out-of-box, click-and-fly autonomy in UAV navigation. The project source code is opened for the benefit of the research community.

Research on the future of combat robotics on the example of Ukraine

The object of research is the architecture of any combat ground robot in the context of its individual systems and subsystems. The conducted research forms a transparent and clear understanding of the main logical links of a combat robot, individual technologies, and components used in the development and serial production. The paper summarizes the global experience and achievements of combat robotics and provides examples of the example of the development of teams from Ukraine. The mentioned are the main system players in this sector of defense technologies, long-term and productive activity of which resulted in the appearance of the first combat robot units in the armies of the leading countries of the world. The author studied and presented the structural structure of any ground combat robot by the method of deduction and reproduction of functional capabilities. In the context of separate systems or subsystems of a ground combat robot recommendations on the equipment of those or other components, sensors, technologies, or their analogs and other equipment are given. The work summarizes the experience of the head of Robotics Design Bureau LLC (Kyiv, Ukraine), associated with the attention of representatives of foreign companies and government agencies to the Ukrainian developments in this area. The leading idea of the research is the priority development of functions and algorithms of combat robots, associated with the development of vision and autonomous movement systems. Realization of these functions sharply increases the advantages of own combat robots, increases their survivability and combat efficiency, reduces dangers for operators of the equipment. Factors related to the package of impact module subsystems directly affecting the combat effectiveness of a ground robot are presented. Compared to similar known studies on this topic, the research conducted immediately immerses the reader into the practical plane of developing a ground combat robot from the perspective of the engineer-creator, which provides quick basic knowledge and insights and inspires further exploration in this direction.