Attentional Mechanism for Sensory-motor Coordination in Behavior-based Robotic Systems

To be counted as operationally autonomous relative to the execution of some given task, a robotic system must be capable of performing that task without any human intervention after its activation. Recent progress in the fields of robotics and AI has paved the way to robots autonomously performing tasks that may signif-icantly affect individual and collective interests, which are deemed as worthy of pro-tection from both ethical and legal perspectives. The present contribution provides an overview of ensuing normative problems and identifies some ethically and legal-ly grounded solutions to them. To this end, three case studies will be more closely scrutinized, i.e. increasingly autonomous weapons systems, vehicles, and surgical robots. These case studies are used to illustrate, respectively, the preliminary prob-lem of whether we want to grant certain forms of autonomy to robotic systems, the problem of selecting appropriate ethical policies to control the behavior of autono-mous robotic systems, and the problem of how to retain responsibility for mis-doings of autonomous robotic systems. The analysis of these case studies brings out the key role played by human control in ethical and legal problem-solving strat-egies concerning the operational autonomy of robotic and AI systems.

We describe a new method for adaptive model-based control of robotic dynamic systems using a new hybrid neuro-fuzzy-fractal approach. Intelligent control of robotic systems is a difficult problem because the dynamics of these systems is highly nonlinear. Optimal control of many robotic systems also requires methods which make use of predictions of future behavior. We describe an intelligent system for controlling robot manipulators to illustrate our neuro-fuzzy-fractal hybrid approach for adaptive control. We use a new fuzzy inference system for reasoning with multiple differential equations for model selection based on the relevant selection parameters for the problem. We use neural networks for identification and control of robotic dynamic systems.

The demand for 3D models that represent real-world objects such as structures and buildings has increased in recent years. It is becoming increasingly important that the reconstructions are not only visually convincing but also feature high geometric accuracy. This includes, for example, the fields of civil engineering, terrestrial surveying and archeology, where precise measurements are made in the models for documentation and analysis purposes. There are different approaches to create such a reconstruction. The photogrammetric method Structure from Motion and laser scanning are among the most widely used methods here, as they do not require a complicated setup and can be used for scenarios at small to large scale. Recent developments are enabling unmanned robotic systems, especially sensor mounted UAVs, to assist in the recording of areas which are otherwise difficult to observe. The demand for a high geometric accuracy, however, comes at the expense of high computational complexity of up to several days. Hence, especially real-time reconstructions are unfeasible, such that recording and reconstruction procedure must be executed consecutively. The resulting model quality, i.e. completeness and accuracy, is only assessable afterwards. Since it is often difficult or even impossible to improve these models with additional measurements afterwards, methods that ensure a reliable acquisition of sufficient data is required.
\n
\nIn this thesis we develop new methods and theory that address this problem for the mentioned sensor types. For both, a probabilistic description of the expected surface reconstruction error is maintained cost-efficiently as an estimate for the model quality during the recording procedure. For image sensors this is realized by incrementally constructing confidence ellipsoids that describe the information obtained from all views. With depth sensors the surface quality is described by the variance of a Gaussian process implicit surface regression fit to point cloud data using polyharmonic kernel functions. Sensor poses are then assessed by the information they add to the subsequent reconstruction up to a desired geometric accuracy using a formulation that is motivated from Optimal Experimental Design. This quantity is further used in an iterative next-best-view selection framework as a subproblem of a coverage path planning problem.
\n
\nThe general formulations presented in this thesis enables a wide range of applications, such as offline and online view planning or various autonomous robot systems under consideration of dynamic and geometric constraints. We present the first multi-view coverage path planning approach, specifically targeted at autonomous Structure from Motion data acquisition. Its correctness is validated in simulation using the physics simulator Gazebo. Furthermore, we lay a foundation for similar applications with depth sensors. All presented algorithms were developed with scalability in mind and show promising results regarding real-time usability.

We here propose a new evolutionary approach with learning to create a variety of behavioral patterns in autonomous robots. The conventional evolution or learning is to optimize a cost function such as fitness function and error function. In practice, the robot encounters situations where exist multiple solutions having quite similar fitness or error values. The optimum solution is generally selected, while others are eliminated, even if the difference in the fitness or error is very little between the solutions. This causes an essential problem for behavior-based robots. Ideally, the robot should be able to select one of the behaviors by perceiving a slight difference in the sensory information, but the ability is lost. To overcome this problem, we introduced a structural learning during the evolution of neural network ensemble (NNE). Motor outputs were generated by summing outputs of component neural networks of an NNE, and they were trained to segregate each other by negative correlation learning between generations. In experiment, each component network exhibited different functionality, producing a variety of behaviors as a whole. The proposed evolution of NNE with negative-correlation learning thus can be a practical solution for the plasticity-stability problem in robotics.

Some important conclusions for achieving an energy supply system which satisfies the concept of sustainable development are that: The use of limited stocks of energy is compatible with the concept of sustainability provided that we can guarantee future generations a technically and economically viable energy base which is at least of the same size. The use of scarce resources, including the environment as a resource, is decisive when assessing the sustainability of energy systems. The full costs (generation costs plus external costs) should be considered as a helpful indicator for assessing the contribution of power generation technologies to a sustainable energy system. The technical progress made possible by increasing knowledge, which contributes to expanding the technically and economically exploitable raw materials and energy resources and allows a further uncoupling of economic development and the use of resources, will play a key role in achieving sustainable development. A life-cycle-based evaluation employing a variety of sustainability criteria clearly shows that nuclear energy is an attractive source of low-cost electricity that can foster economic development and reduce greenhouse gas emissions cost effectively while broadening the available energy resource base for future generations. Low total material requirements and the total energy requirements of nuclear electricity production are indications of the rational use of scarce resources in comparison with other electricity technologies. Estimates of health risks including those of severe accidents indicate that nuclear power, when constructed and operated according to present safety standards, is associated with health impacts that are in the lower range of all electricity systems. Nuclear energy combines economic, resource, climatological and environmental attractiveness making a sustainable electricity supply system a practically feasible and economically affordable target for many countries.

Robotic systems have significantly transformed the landscape of minimally invasive surgery, offering enhanced precision, reduced recovery times, and improved patient outcomes. These systems have evolved from simple mechanical tools to sophisticated platforms integrating advanced control algorithms and real-time feedback mechanisms. This paper provides a comprehensive overview of the role of robotic systems in minimally invasive surgery, exploring the various benefits, inherent risks, and the challenges associated with their adoption and development. We examine the technical aspects of robotic control systems, such as kinematics, force control, and haptic feedback, which enable greater surgical accuracy. Despite these advantages, challenges such as system complexity, high costs, and ethical concerns remain significant barriers to widespread adoption. The future of robotic surgery lies in overcoming these obstacles, with advancements in system miniaturization and further refinement of control systems poised to enhance the efficacy and accessibility of robotic platforms. This paper explores the role of robotic systems in minimally invasive surgery, focusing on three key areas: bronchoscopy and ureteroscopy. By reviewing the benefits, risks, case studies, and future directions of these technologies, the paper seeks to provide an in-depth understanding of how robotic systems are shaping the future of surgery. Key words: Robotic Surgery, Minimally Invasive Surgery, Robotic Control Systems, Surgical Precision, PID Control, Kinematics, Inverse Kinematics, Forward Kinematics, Dynamic Control, Force Control, Impedance Control, Surgical Robotics, Haptic Feedback, Robotic Arm, Robotic Surgery Benefits, Robotic Surgery Risks, Robot-Assisted Surgery, Surgeon Console, Real-Time Feedback, Surgical Training, Robotic System Development, System Testing, Clinical Trials, Surgical Robot Performance, Robotics in Urology, Telepresence Surgery, Robotic Surgery Cost, Robotic Surgery Future Directions.

We describe in this paper a new method for adaptive model-based control of robotic dynamic systems using a new hybrid approach combining neural networks, fuzzy logic, and genetic algorithms. Intelligent control of robotic systems is a difficult problem because the dynamics of these systems is highly non-linear. We describe an intelligent system for controlling robotic systems to illustrate our new hybrid approach for adaptive control. We use a new fuzzy inference system for reasoning with multiple differential equations for model selection based on the relevant parameters for the problem. In this case, the genetic algorithm is used to optimize the fuzzy system. We also use neural networks for identification and control of robotic systems.

Обоснован перечень задач самообучения интеллектуальных систем управления автономными роботами и мультиагентными робототехническими группировками. Обсуждаются основные проблемы создания интеллектуальных самообучающихся систем управления. Показано, что один из наиболее перспективных подходов к реализации процессов самообучения в интеллектуальных системах управления автономными роботами и многоагентными робототехническими группировками связан с использованием метода автоматического построения деревьев классификации. Приводятся результаты комплексного моделирования.

A way to improve the performance in autonomous robots is adding intelligence to control systems avoiding hardware redundancy and inopportune mission abortion. In this paper, we present a distributed architecture supporting diagnosis and control of autonomous robots with the purpose of assisting the operator or piloting system in managing fault detection, risk assessment, and recovery plans under uncertainty. The architecture is generic, open and modular consisting of a decision module, intelligent modules, and robot piloting modules. The decision module is the architecture core requesting intelligent modules for diagnosis and recovery action based on data obtained from robot piloting modules

Evolution of behaviors in autonomous robot using artificial neural network and genetic algorithm

The research theme of this investigation is driven by a strong clinical need for new and improved technology to help the modern surgeon. Since the beginning of the 21st century, the emergence of innovative technologies made further advances in minimal access surgery possible. Surgical techniques have evolved rapidly, for example the introduction of minimally invasive surgery (MIS) and robotically-assisted MIS which have improved outcomes for patients with faster recovery, reduced post-operative pain and fewer scars. For such a reason, there is an increasing need to develop innovative en- gineering solutions to some of the challenges being faced as surgery evolves to help surgeons to achieve the best possible clinical outcome and also to develop solutions helping to reduce costs and improve quality. As a matter of fact, robotic surgery and medical simulator addressed the limitations of medical procedures, thus revolutionizing minimal access surgery. First of all, with the introduction of robotics in the operating room, an evolutionary stage in the development of surgical technique was achieved to enhance the control and the visual field of the surgeon. It can be stated that this new approach was patient oriented as it brings several critical advantages for him: damage to healthy tissue is minimal; patients hospitalization is reduced to an average of 1.2 days; psychological impact of the procedure upon the patient is significantly lower; the risk of an unwanted infection is almost zero; using robotic systems the precision of the intervention is below one hundred of a millimetre; the risk of unwanted cuts (vessel sectioning, nerve damage, etc.) is minimal; the number of assistants in the operation room is reduced; 3D visual feedback. Second, training with a surgical simulator offers several advantages. It is similar to a wet laboratory, human cost in the form of adverse outcomes for patients is minimized, and residents can practice in a relaxed learning environment at their own pace. Additionally, training on surgical simulators can be incorporated into a curriculum that is available to residents at any time. Furthermore, the development of physical and cognitive surgical simulators offers an approach for learning which is different from the traditional apprenticeship model. Simulators cannot replace experienced surgical preceptors, but they are fast becoming an attractive and acceptable adjunct in surgical curricula. As the technology improves, the simulations will become more realistic, and the experience will become more valuable. Simulation programs will play a greater role in future surgical education. For what concerns improving patient care and providing technology for healthcare professionals, there are many limitations and obstacles to overcome, before robotic surgery systems and medical simulators being able to be integrated into the medical field. Motivated by the above observations, the goal of this research is to develop a new manipulator in order to improve such electromecanical limitation of the current surgery robotic systems and also to build a new surgery simulator to address some obstacles when doing some open surgery performances.

Fast adaptability and high flexibility have made use of autonomous robots (ARs) a popular choice for different material transfer activities in the flexible manufacturing systems (FMSs). The ARs are observed to be highly capable and flexible for integration with computer-controlled machine tools, producing different types of jobs in the FMS. The integrated scheduling of production operations on the machine tools and material transfer operations of ARs in the FMS can offer high productivity in the FMS. The present study proposes a procedure for integrated scheduling between jobs under production in the FMS and the ARs in the FMS by using the differential evolution algorithm. The proposed procedure is used for integrated scheduling between the jobs and the ARs so as to minimize the idle time of the machining centers and also minimizing the cost due to the delay in the production simultaneously. It is observed that the proposed scheduling procedure yields efficient results.

The financial and economic mechanism of balanced use of natural resources includes a wide specification of environmental, organizational, economic and financial instruments. The author's vision of the multi-vector nature of the ecological and economic assessment of water resources is outlined, which is a comprehensive approach to the analysis of the use and management of water resources for making informed decisions with the determination of priorities for Ukraine. It is substantiated that formation of fundamental scientific bases for the evaluation of water resources of Ukraine should be based on the use of ecological and economic approaches, in particular: ecological dimension, economic analysis, social dimension, technical analysis, legal and regulatory context, risk analysis, climate change analysis, water infrastructure projects, water conflict management, environmental impact monitoring and assessment, alternative scenarios. A study of publicly available data on the assessment of the use of water resources of Ukraine was conducted. Based on the results of the study, we proposed the structure of a multi-vector model of the tools of the ecological and economic mechanism of water resources assessment, which is systematized according to interrelated instrumental blocks: ecological dimension — assessment of the impact of any water projects or activities on natural ecosystems, aquatic biological resources, and water quality; economic analysis — consideration of economic indicators; social dimension — assessment of the impact of projects on society; technical analysis — analysis of technical solutions, engineering aspects and technological parameters of water projects; legal and regulatory context — consideration of relevant legislative and regulatory requirements; analysis — risk assessment of possible risks and development of strategies for their management. The ecological and economic approach helps ensure balanced use of water resources, taking into account the needs of humanity and the requirements of the environment. On the basis of the multi-vector nature of the ecological and economic assessment of water resources, recommendations on environmental protection, optimal use of resources, social impact of projects, risk management strategies and other important aspects can be provided. The author's approach to theoretical-methodological approaches and methodological provisions regarding the formation of a model of tools for the ecological-economic mechanism of water resources assessment, the effective influence of which is aimed at balancing the ecological, economic and social components of the use of water resources of Ukraine, is proposed. It is substantiated that the functioning of multi-directional tools of the ecological and economic mechanism will ensure both greening and increasing the economic and social effectiveness of the use of water resources, the consolidation of management aspects around strategic tasks and priorities determined by the Basic principles of the state environmental policy of Ukraine for the period up to 2030.

The same coordination aspects are the key-points of the last proposed method about comunication: now, the robotic device have to cooperate in order to manage the object in the desired way with a good sensitivity and this can be done exploiting the torque end force sensor of the new system. A general introduction underlining the need to make a robot autonomous or at least able to operate in unstructured scenarios to cope with human end other robotic device. Project of ultralight robot arm for aerial manipulation whit simulations and experiments. Proposed robot manipulator framework in order to exploit the interaction robot-robot, redundancy management for dexterity scopes. Simulations are presented to validate the proposed hardware. And exploit the problematic of the comunication and control of the multiple platform. Simulations are presented to validate the proposed approach.

Control systems for autonomous robots are concurrent, distributed, embedded, real-time and data intensive software systems. A real-world robot control system is composed of tens of software components. For each component providing robotic functionality, tens of different implementations may be available. The difficult challenge in robotic system engineering consists in selecting a coherent set of components, which provide the functionality required by the application requirements, taking into account their mutual dependencies. This challenge is exacerbated by the fact that robotics system integrators and application developers are usually not specifically trained in software engineering. In various application domains, software product line (SPL) development has proven to be the most effective approach to face this kind of challenges. In a previous paper [D. Brugali and N. Hochgeschwender, Managing the functional variability of robotic perception systems, in First IEEE Int. Conf. Robotic Computing, 2017, pp. 277–283.] we have presented a model-based approach to the development of SPL for robotic perception systems, which integrates two modeling technologies developed by the authors: The HyperFlex toolkit [L. Gherardi and D. Brugali, Modeling and reusing robotic software architectures: The HyperFlex toolchain, in IEEE Int. Conf. Robotics and Automation, 2014, pp. 6414–6420.] and the Robot Perception Specification Language (RPSL) [N. Hochgeschwender, S. Schneider, H. Voos and G. K. Kraetzschmar, Declarative specification of robot perception architectures, in 4th Int. Conf. Simulation, Modeling, and Programming for Autonomous Robots, 2014, pp. 291–302.]. This paper extends our previous work by illustrating the entire development process of an SPL for robot perception systems with a real case study.