Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
9,799
result(s) for
"Interactive control"
Sort by:
This book is out of control!
Ben wants to show Bella how his remote-controlled fire engine works, but the buttons aren't working properly and strange things are happening to Bella's dog.
Book
A Lower Limb Exoskeleton Adaptive Control Method Based on Model-free Reinforcement Learning and Improved Dynamic Movement Primitives
Recent advancements in lower limb exoskeleton control have predominantly focused on enhancing walking capabilities across diverse terrains, such as level ground, stairs, and ramps. However, achieving seamless transitions between these terrains remains a significant challenge due to the unpredictability of the environment, which hampers adaptive control. In this paper, we propose a Hierarchical Interactive Learning (HIL) control method based on gait phase and locomotion pattern recognition. The method comprises two layers: high-level learning and low-level control. The high-level learning is based on gait phase and locomotion pattern recognition, utilizing the Dynamic Movement Primitives (DMP) to piecewise learn the desired joint torque curves. The low-level control utilizes the learned DMP to output torque based on the gait phase and locomotion pattern, while reinforcement learning is employed to dynamically adjust the control parameters of DMP in real-time with the goal of minimizing human-exoskeleton interaction forces. The experiments collected gait data of lower limb movement from active exoskeletons. The results show that our method significantly reduces human-exoskeleton interaction forces across diverse terrains. In order to verify the feasibility and effectiveness of the proposed method, 15 healthy subjects were tested with the lower limb exoskeleton of these 3 generations. The experimental results show that the proposed HIL control method gives a valuable tool for smooth transitions among different terrains, reduces the reliance on accurate dynamic models and the average oxygen consumption decreased by about 12%, underscoring its potential to improve exoskeleton-assisted mobility.
Journal Article
Interactive Force Control Based on Multimodal Robot Skin for Physical Human−Robot Collaboration
This work proposes and realizes a control architecture that can support the deployment of a large‐scale robot skin in a Human‐Robot Collaboration scenario. It is shown, how whole‐body tactile feedback can extend the capabilities of robots during dynamic interactions by providing information about multiple contacts across the robot's surface. Specifically, an uncalibrated skin system is used to implement stable force control while simultaneously handling the multi‐contact interactions of a user. The system formulates control tasks for force control, tactile guidance, collision avoidance, and compliance, and fuses them with a multi‐priority redundancy resolution strategy. The approach is evaluated on an omnidirectional mobile‐manipulator with dual arms covered with robot skin. Results are assessed under dynamic conditions, showing that multi‐modal tactile information enables robust force control while at the same time remaining responsive to a user's interactions. The sense of touch is an important aspect of natural collaboration between humans and robots. This work extends the capabilities of robots during dynamic interactions with humans by using the tactile feedback of a large‐area skin system. The implemented control architecture is validated on a mobile manipulator and enables stable force control while performing a collaborative task with a human.
Journal Article
Human-in-the-loop machine learning: a state of the art
Researchers are defining new types of interactions between humans and machine learning algorithms generically called human-in-the-loop machine learning. Depending on who is in control of the learning process, we can identify: active learning, in which the system remains in control; interactive machine learning, in which there is a closer interaction between users and learning systems; and machine teaching, where human domain experts have control over the learning process. Aside from control, humans can also be involved in the learning process in other ways. In curriculum learning human domain experts try to impose some structure on the examples presented to improve the learning; in explainable AI the focus is on the ability of the model to explain to humans why a given solution was chosen. This collaboration between AI models and humans should not be limited only to the learning process; if we go further, we can see other terms that arise such as Usable and Useful AI. In this paper we review the state of the art of the techniques involved in the new forms of relationship between humans and ML algorithms. Our contribution is not merely listing the different approaches, but to provide definitions clarifying confusing, varied and sometimes contradictory terms; to elucidate and determine the boundaries between the different methods; and to correlate all the techniques searching for the connections and influences between them.
Journal Article
Agency plus automation
Much contemporary rhetoric regards the prospects and pitfalls of using artificial intelligence techniques to automate an increasing range of tasks, especially those once considered the purview of people alone. These accounts are often wildly optimistic, understating outstanding challenges while turning a blind eye to the human labor that undergirds and sustains ostensibly “automated” services. This long-standing focus on purely automated methods unnecessarily cedes a promising design space: one in which computational assistance augments and enriches, rather than replaces, people’s intellectual work. This tension between human agency and machine automation poses vital challenges for design and engineering. In this work, we consider the design of systems that enable rich, adaptive interaction between people and algorithms. We seek to balance the often-complementary strengths and weaknesses of each, while promoting human control and skillful action. We share case studies of interactive systems we have developed in three arenas—data wrangling, exploratory analysis, and natural language translation—that integrate proactive computational support into interactive systems. To improve outcomes and support learning by both people and machines, we describe the use of shared representations of tasks augmented with predictive models of human capabilities and actions. We conclude with a discussion of future prospects and scientific frontiers for intelligence augmentation research.
Journal Article
Research on Application Scenarios of Artificial Intelligence in New Power System
Building a New Power System with new energy as the main body is the main theme of modern energy system construction and energy for a period of time in the future. It is an inevitable choice to promote the clean and low-carbon development of electric power. Through artificial intelligence technology, we can solve the problems of strong volatility and difficult regulation caused by the diversity of new energy sources, and promote the establishment of a green, efficient, flexible, interactive, safe and controllable New Power System. This paper sorts out the challenges and deficiencies faced by New Power System, summarizes the application characteristics of artificial intelligence in various industries, analyzes the development and characteristics of artificial intelligence applications, combines the application hotspots of artificial intelligence New Power System, studies the application scenarios of artificial intelligence in the construction, operation and maintenance of New Power System, and puts forward suggestions on the research direction.
Journal Article
Hybrid electromagnetic and moisture energy harvesting enabled by ionic diode films
Wireless energy-responsive systems provide a foundational platform for powering and operating intelligent devices. However, current electronic systems relying on complex components limit their effective deployment in ambient environment and seamless integration of energy harvesting, storage, sensing, and communication. Here, we disclose a coupling effect of electromagnetic wave absorption and moist-enabled generation on carrier transportation and energy interaction regulated by ionic diode effect. As demonstration, a wireless energy interactive system is established for electromagnetic-moist coupled energy harvesting and signal transmission through highly integrated polyelectrolyte/conjugated conductive polymer bilayer ionic diode films as dynamic energy-switching carriers. The gradient distribution of ions within the films, excited by moist energy, enables the ionic rectification and further endows the films with electromagnetic energy harvesting capability. In turn, the absorbed electromagnetic energy drives the directional migration of charge carriers and internal ionic current. By rationally regulating the electrolyte and dielectric properties of ionic diodes, it becomes feasible to control targeted electric signals and energy outputs under coupled electromagnetic-moist environment. This work is a step towards enabling enhanced smart interactivities for wirelessly driven flexible electronics.
Wireless energy-responsive systems are essential for intelligent devices. This study demonstrates an electromagnetic-moist coupling effect for energy harvesting and signal transmission using fabricated ionic diode films, showing improved performance and potential for practical applications.
Journal Article
Ranking the risk of animal-to-human spillover for newly discovered viruses
The death toll and economic loss resulting from the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic are stark reminders that we are vulnerable to zoonotic viral threats. Strategies are needed to identify and characterize animal viruses that pose the greatest risk of spillover and spread in humans and inform public health interventions. Using expert opinion and scientific evidence, we identified host, viral, and environmental risk factors contributing to zoonotic virus spillover and spread in humans. We then developed a risk ranking framework and interactive web tool, SpillOver, that estimates a risk score for wildlife-origin viruses, creating a comparative risk assessment of viruses with uncharacterized zoonotic spillover potential alongside those already known to be zoonotic. Using data from testing 509,721 samples from 74,635 animals as part of a virus discovery project and public records of virus detections around the world, we ranked the spillover potential of 887 wildlife viruses. Validating the risk assessment, the top 12 were known zoonotic viruses, including SARS-CoV-2. Several newly detected wildlife viruses ranked higher than known zoonotic viruses. Using a scientifically informed process, we capitalized on the recent wealth of virus discovery data to systematically identify and prioritize targets for investigation. The publicly accessible SpillOver platform can be used by policy makers and health scientists to inform research and public health interventions for prevention and rapid control of disease outbreaks. SpillOver is a living, interactive database that can be refined over time to continue to improve the quality and public availability of information on viral threats to human health.
Journal Article
Interactive control of combustion stability and operating limits in a biogas-fueled spark ignition engine with high compression ratio
The use of high compression ratios on spark ignition engines enables the increase of thermal efficiency, but also contributes to the reduction of high load limit because of the higher auto-ignition tendency in the end-gas. Gaseous fuels provide a good option to expand the high load limits because of their high octane ratings, mostly in small engines. Biogas is a renewable fuel, mainly composed by
CH
4
and
CO
2
that exhibits high auto-ignition temperature and slow laminar flame speed. When biogas is burned in spark ignition engines partial and total misfire at low loads counteract the benefits achieved at high loads in which knocking combustion is reduced, hence the design of an effective control of the operating range based on the real-time observation of combustion instabilities is desirable. This paper presents an interactive control of the safe operating range through the modification of the spark time, equivalent ratio and throttle valve opening, taking as feedback the combustion instabilities, which are calculated from the in-cylinder pressure evolution for a biogas-fueled high compression ratio spark ignition engine. The interactive control was tested on a modified diesel engine converted to spark-ignition, original compression ratio of 15.5:1 and fueled with biogas. Control was able to keep a safe operating range with a maximum throttle valve opening of 39%, equivalence ratios within 0.6 and 1, and spark advances in the range of 329–358 crank angle degree. The coefficient of variation of IMEP was lower than 8%, whereas the maximum average knocking intensity was close to 2.5.
Journal Article
Feedback-controlled hydrogels with homeostatic oscillations and dissipative signal transduction
Driving systems out of equilibrium under feedback control is characteristic for living systems, where homeostasis and dissipative signal transduction facilitate complex responses. This feature not only inspires dissipative dynamic functionalities in synthetic systems but also poses great challenges in designing novel pathways. Here we report feedback-controlled systems comprising two coupled hydrogels driven by constant light, where the system can be tuned to undergo stable homeostatic self-oscillations or damped steady states of temperature. We demonstrate that stable temperature oscillations can be utilized for dynamic colours and cargo transport, whereas damped steady states enable signal transduction pathways. Here mechanical triggers cause temperature changes that lead to responses such as bending motions inspired by the single-touch mechanoresponse in Mimosa pudica and the frequency-gated snapping motion inspired by the plant arithmetic in the Venus flytrap. The proposed concepts suggest generalizable feedback pathways for dissipative dynamic materials and interactive soft robotics.An optical signal transduction pathway through feedback-controlled homeostatic temperature oscillations and mechanoresponse enables dynamic functionalities in a hydrogel.
Journal Article