查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Research findings on Machine Learning are discussed in a new report. According to news reporting from Campinas, Brazil , by NewsRx journalists, research stated, "This study presents a hybrid modeling approach that combines a simplified phenomenological model with machine learnin g techniques for predicting variables in the microalgae biomass gasification pro cess in supercritical water (SCWG). The simplified phenomenological model, based on the Gibbs energy minimization methodology (minG) associated with the ideal g as model, exhibits significant deviations when compared to the actual behavior o f the process." Financial support for this research came from Fundacao de Amparo a Pesquisa do E stado de Sao Paulo (FAPESP).
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Robotics have been published. According to news originating from Zurich, Switzerland, by News Rx correspondents, research stated, "Forests provide vital resources and service s for humanity, but preserving and restoring them is challenging due to the diff iculty of obtaining actionable data, especially in inaccessible areas, such as f orest canopies. To address this, we follow the lead of arboreal animals that exp loit multiple modes of locomotion." Financial support for this research came from Schweizerischer Nationalfonds zur Frderung der Wissenschaftlichen Forschung. Our news journalists obtained a quote from the research from the Swiss Federal I nstitute of Technology, "We combine aerial and tethered movements to enable AVOC ADO to navigate within a tree canopy. Starting from the top of a tree, it can de scend with the tether and maneuver around obstacles with thrusters. We extend ou r previous work with a new mechanical design with a protective shell, increased computational power and cameras for state estimation. We introduce a dynamic mod el and simulation, and perform a quasistatic and dynamic validation. For autonom y, we derive a control framework in simulation to regulate tether length, tilt, and heading, before transfer to the robot. We evaluate the controllers for traje ctory tracking through experiments. AVOCADO can follow trajectories around obsta cles and reject disturbances on the tether."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on Robotics is now availab le. According to news reporting originating in Beijing, People's Republic of Chi na, by NewsRx journalists, research stated, "Wearable robotic devices interact w ith humans by applying the assistive force in parallel with muscle-tendon system s. Designing actuations in mimicking the natural activation patterns of human mu scles is a promising way to optimize the performance of wearable robots." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). The news reporters obtained a quote from the research from Peking University, "I n this article, we propose a bioinspired cable-driven actuation system capable o f providing anisometric contractions (including concentric and eccentric contrac tion) assistance or nearly acting as a transparent device in an efficient manner . A novel clutch-spring mechanism is employed to accomplish switches between ass istive modes and the transparent mode. Corresponding control strategies coordina ting with the mechanical design were presented and described in detail. Multiple evaluations were conducted on a test bench to characterize the system's perform ance. The closed-loop bandwidth of the system running concentric assistance cont rol was 18.2 Hz. The R-squared values of linear fitting under eccentric assistan ce control were above 0.99. The engagement time of the proposed clutch was about 90 ms. Applying the actuation to an ankle exoskeleton, multiple walking experim ents with electromyography measurements were performed on five subjects to show its application potential in existing wearable robots. Experimental results reve aled that the proposed design could reduce soleus muscle activity by 27.32% compared with normal walking."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on robotics is now availab le. According to news reporting originating from Wuhan, People's Republic of Chi na, by NewsRx correspondents, research stated, "Simultaneously guaranteeing mate rial removal accuracy and surface quality of robotic grinding is crucial." The news reporters obtained a quote from the research from Huazhong University o f Science and Technology: "However, existing studies of robotic grinding process optimization have mainly focused on a single indicator that solely considers co ntour error or surface roughness, while studies that simultaneously investigate the impact of contact force, spindle speed, feed rate, inclination angle, and pa th space on the material removal profile (MRP) and the surface roughness are lac king. This paper proposes a hybrid optimization method that considers dimensiona l accuracy and surface quality constraints. First, an MRP model that considers t he coupling influence of the contact force, spindle speed, feed rate, and inclin ation angle is presented. Then, a surface roughness model that considers the inc lination angle is established. Finally, the contact force, feed rate, inclinatio n angle, and path space are simultaneously optimized to satisfy the hybrid const raints of MRP accuracy and surface roughness. The proposed method ensures maximu m grinding efficiency while satisfying dimensional accuracy and surface quality constraints."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on robotics is the subjec t of a new report. According to news originating from Shanghai, People's Republi c of China, by NewsRx editors, the research stated, "The inferior sample efficie ncy of reinforcement learning (RL) and the requirement for high-quality demonstr ations in imitation learning (IL) will hinder their application in real-world ro bots." Financial supporters for this research include National Natural Science Foundati on of China; Shanghai Crossdisciplinary Research Fund. Our news correspondents obtained a quote from the research from Shanghai Jiao To ng University: "To address this challenge, a novel self-evolution framework, nam ed task-oriented self-imitation learning (TOSIL), is proposed. To circumvent ext ernal demonstrations, the top-K self-generated trajectories are chosen as expert data from both per-episode exploration and long-term return perspectives. Each transition is assigned a guide reward, which is formulated by these trajectories . The guide rewards update as the agent evolves, encouraging good exploration be haviors. This methodology guarantees that the agent explores in the direction re levant to the task, improving sample efficiency and asymptotic performance. The experimental results on locomotion and manipulation tasks indicate that the prop osed framework outperforms other state-of-the-art RL methods."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in Machine Learning. According to news reporting out of Xi'an, People's Republic of China, by NewsRx editors, research stated, "The utilization of molten salts in heat tr ansfer applications, specifically within shell-and-tube heat exchangers, has gar nered significant attention for its potential in sustainable energy solutions. t his study employs advanced machine learning algorithms, including decision tree regressor, support vector regressor, extreme gradient boosting, and random fores t, to not only predict the heat transfer behavior of molten salts but also unrav el the complex mechanisms underlying this process. Achieving a remarkable accura cy score of 0.985, the Support Vector Regressor leads the predictive models, clo sely followed by random forest (0.982), Decision Tree Regressor (0.974), and Ext reme Gradient Boosting (0.965)." Our news journalists obtained a quote from the research from Xi'an Jiaotong Univ ersity, "The incorporation of Shapley Additive exPlanations values accentuates t he Reynolds number's pivotal role, elucidating a robust correlation with the Nus selt value. These insights transcend mere prediction, offering a profound unders tanding that can significantly impact the design and optimization of molten salt heat exchangers." According to the news editors, the research concluded: "The applications of molt en salts extend across various sectors, including concentrated solar energy and thermal storage, solidifying their position as a versatile and effective solutio n in the pursuit of sustainable and efficient energy systems."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Robotics is the subjec t of a report. According to news reporting out of Mexico City, Mexico, by NewsRx editors, the research stated, "Adaptive control is one of the most employed tec hniques to achieve trajectory tracking of robot manipulators. Although it is des irable to obtain exact parameter estimation, most adaptive schemes need the pers istency of excitation (PE) condition on the regressor to be satisfied." Financial support for this research came from DGAPA#x2013;UNAM. Our news journalists obtained a quote from the research from the National Autono mous University of Mexico (UNAM), "In the recent years, the so-called dynamic re gressor extension and mixing (DREM) procedure was developed to provide an altern ative in the design of adaptive laws with conditions different from PE. When met , the improvement in parameter estimation is remarkable, but when not, adaptatio n can simply stop, which might be unacceptable for control purposes. This articl e proposes for the first time a composite scheme, which combines the standard gr adient adaptive law with a DREM-based additional term with the following propert ies: 1) Trajectory tracking for joint desired positions and velocities is guaran teed; 2) in the absence of PE, if a new condition that can partially be verified online for the additional DREM-based term is matched, then exact parameter esti mation takes place in finite time."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on artificial intelligenc e is the subject of a new report. According to news originating from Corvinus Un iversity by NewsRx correspondents, research stated, "Artificial intelligence (AI ) can support the company's internal audit function (IAF) by delivering substant ial strategic oversight, minimizing manual procedures, and making possible addit ional value-added auditing service. Currently, there are research gaps in the li terature, such as limited studies on the topic, low AI adoption rates in the IAF across different countries and regions, and a shortage of comprehensive framewo rks for effectively using AI in the IAF." The news reporters obtained a quote from the research from Corvinus University: "Hence, this review work aims to fill the research gap by offering an outline of research avenues on the topic in the literature and suggesting a new compressiv e framework for the effective use of AI in the IAF. This paper undertakes a syst ematic literature review (SLR) approach and aspires to highlight the state of re search on the use of AI in the IAF, to deliver insight for scholars and industry experts on the issue, and to reveal the implications for IAF of the new AI tech nology. Moreover, to quickly make artificial intelligence work in internal audit functions, the CACS framework was recommended with attributes such as commitmen t, access, capability, and skills development (CACS). This work provides signifi cant contributions for guiding future research directions and the development of theoretical foundations for the IAF field. On a practical level, the work will help internal auditors to assess and understand the potential advantages and ris ks of implementing AI in their organization's IAF. For regulators, this review s hould prove useful for updating regulations on internal auditing in the context of using advanced technology such as AI and for ensuring the compliance of inter nal auditing practices to the evolving technology."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Fresh data on Robotics are presented i n a new report. According to news reporting out of Bristol, United Kingdom, by N ewsRx editors, research stated, "Grasp planning for irregularly shaped objects u sing multifingered robotic hands is challenging due to the high dimensionality o f the search space and a lack of proper modeling methods for object geometry. To address these issues, we propose a grasp planning approach based on Gaussian pr ocess implicit surfaces (GPIS)." Our news journalists obtained a quote from the research from the University of t he West of England, "To explore the object geometry and identify feasible contac t positions and normals, our method introduces several moving points called attr actors along with a dynamical system. The dynamical system constrains and guides the attractors with the partial differentials of the GPIS, which can be conveni ently obtained through the linear expression of a GP. The hand motion is also gu ided by the dynamical system. In addition, an inverse kinematics method, which c onsiders finger joint limits, is developed to simultaneously adjust the palm pos e and finger joint angles for a feasible grasp. The performance of our method is demonstrated using various robotic hands and objects, and real robot experiment s are conducted to validate the planned grasp's effectiveness in reality."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ro botics. According to news reporting out of Macau, People's Republic of China, by NewsRx editors, research stated, "This paper proposes a new teleoperated telepr esence robot system with high-fidelity haptic feedback for interaction work, suc h as pre-operation of explosive ordnance disposal (EOD). The system includes a m aster device and a slave collaborative robot." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). Our news journalists obtained a quote from the research from the University of M acau, "The master device enables the human operator to feel the operation proced ure when performing the environmental interaction task. The system's kinematics and dynamics models are derived, laying the foundation for the control scheme de sign. To meet the requirements of EOD missions, a hybrid motion mapping method i ncluding position-velocity (PV) and position-position (PP) mapping modes is pres ented to achieve a balance between working efficiency and manipulation accuracy. A hybrid haptic force rendering method is introduced to facilitate the human's feeling of the interacting force and control the slave robot in PP and PV mappin g modes, respectively. Experimental results reveal that the developed system exh ibits good position and velocity tracking performance with root-mean-square (RMS ) errors of 0.004 m and 0.007 m/s, respectively. The haptic tracking is realized with an RMS force error of 0.14 N. Moreover, the developed system can improve t he EOD working efficiency by 10.7% with accurate operation while e nsuring the fidelity of the haptic feedback to feel the contact process. The rep orted telepresence robot system provides a promising solution to delicate remote interaction operations. Note to Practitioners-Teleoperated robotic systems are commonly utilized to perform hazardous tasks such as EOD tasks. However, the exi sting EOD robots controlled by the joystick have limited dexterity. Moreover, vi sual feedback alone cannot provide enough telepresence for an operator, which le ads to low efficiency. This paper proposes a new teleoperated robot system with high-fidelity haptic feedback assistance intended for EOD tasks. The system inte grates the motion mapping method that combines PP and PV modes to improve the wo rking efficiency while maintaining manipulation accuracy. The haptic sensations feedback can switch the rendering mode according to different control modes. The haptic feedback mechanism enables the operators to feel reliable contact under PP mapping mode and ensures safety and stability under PV mapping mode."
NETL
NSTL