检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Scholten, Jan Wout, Daan Celemin, Carlos Kober, Jens Cognitive Robotics Department Faculty of Mechanical Maritime and Materials Engineering Delft University of Technology Netherlands

Deep Reinforcement Learning has enabled the control of increasingly complex and high-dimensional problems. However, the need of vast amounts of data before reasonable performance is attained prevents its widespread application. We employ binary corrective feedback as a general and intuitive manner to incorporate human intuition and domain knowledge in model-free machine learning. The uncertainty in the policy and the corrective feedback is combined directly in the action space as probabilistic conditional exploration. As a result, the greatest part of the otherwise ignorant learning process can be avoided. We demonstrate the proposed method, Predictive Probabilistic Merging of Policies (PPMP), in combination with DDPG. In experiments on continuous control problems of the OpenAI Gym, we achieve drastic improvements in sample efficiency, final performance, and robustness to erroneous feedback, both for human and synthetic feedback. Additionally, we show solutions beyond the demonstrated knowledge. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Accelerating surgical robotics research: A review of 10 years with the da Vinci research kit

arXiv

引用

arXiv 2021年

作者： D’Ettorre, Claudia Mariani, Andrea Stilli, Agostino Rodriguez y Baena, Ferdinando Valdastri, Pietro Deguet, Anton Kazanzides, Peter Taylor, Russell H. Fischer, Gregory S. DiMaio, Simon P. Menciassi, Arianna Stoyanov, Danail University College London LondonW1W 7EJ United Kingdom Pisa Italy Mechanical Engineering Department Imperial College London United Kingdom STORM Lab Institute of Robotics Autonomous Systems and Sensing School of Electronic and Electrical Engineering University of Leeds Leeds United Kingdom Johns Hopkins University Baltimore United States Automation and Interventional Medicine Laboratory Worcester Polytechnic Institute WorcesterMA United States Intuitive Surgical Inc SunnyvaleCA United States

Robotic-assisted surgery is now well-established in clinical practice and has become the gold standard clinical treatment option for several clinical indications. The field of robotic-assisted surgery is expected to grow substantially in the next decade with a range of new robotic devices emerging to address unmet clinical needs across different specialties. A vibrant surgical robotics research community is pivotal for conceptualizing such new systems as well as for developing and training the engineers and scientists to translate them into practice. The da Vinci Research Kit (dVRK), an academic and industry collaborative effort to re-purpose decommissioned da Vinci surgical systems (Intuitive Surgical Inc, CA, USA) as a research platform for surgical robotics research, has been a key initiative for addressing a barrier to entry for new research groups in surgical robotics. In this paper, we present an extensive review of the publications that have been facilitated by the dVRK over the past decade. We classify research efforts into different categories and outline some of the major challenges and needs for the robotics community to maintain this initiative and build upon it. © 2021, CC BY.

关键词： Robotic surgery

来源：评论

学校读者我要写书评

暂无评论

A Multi-Sensor Fusion Based 2D-Driven 3D Object Detection Approach for Large Scene Applications ∗

A Multi-Sensor Fusion Based 2D-Driven 3D Object Detection Ap...

引用

IEEE International Conference on robotics and Biomimetics

作者： Yingtian Liu Chuanzhe Suo Zhe Liu Yun-Hui Liu School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen T Stone Robotics Institute and Department of Mechanical and Automation Engineering The Chinese University of Hong Kong

In this paper, we propose a 3D object detection approach for large-scale environments by considering the 2D visual information and 3D lidar data simultaneously. In the proposed multi-sensor fusion framework, first of all, a large-scene application oriented data alignment method is presented, which utilizes the EPnP based joint calibration method in order to achieve an improved data-association performance. Based on which, the 2D bounding box of each object is generated by using the visual detection and the 3D point cloud contained in the corresponding 3D frustum can be obtained. Then, after the ground fitting and point cloud clustering operations, an innovative scoring mechanism is proposed to evaluate each point cloud cluster and find out the cluster belonging to the detected object. Finally, the accurate lidar point cloud segment in the 3D frustum can be generated. Comparing with existing 3D object detection approaches, we propose a more general framework in this paper, which does not require a large number of 3D point cloud detection datasets to train the network and can be used on the 3D lidar with any number of lines, thus a real-time 3D detection system can be achieved. Experiments in large-scale airport environments validate the advanced performance of the proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tag-like cyclic peptides: Modular affinity elements for protein integration and bioengineering applications

引用

Bioorganic & Medicinal Chemistry 2025年

作者： Zirui Zhu Andrew Poweleit Louisa Girard Wenjun Sun Haowei Ma Edouard Nice Department of Chemistry and Biochemistry The Ohio State University Columbus OH 43210 United States of America Chemistry Graduate Program The Ohio State University Columbus OH 43210 United States of America Ohio State Biochemistry Program The Ohio State University Columbus OH 43210 United States of America Department of Mechanical and Aerospace Engineering Case Western Reserve University Cleveland OH 44106 United States of America Department of Biochemistry and Molecular Biology Monash University Clayton VIC 3800 Australia

Cyclic peptides have emerged as highly versatile compounds in drug development and bioengineering, offering unique structural stability, binding specificity, and reduced susceptibility to proteolysis compared to their linear counterparts. These properties make cyclic peptides valuable in a range of therapeutic applications, from antimicrobial and anticancer agents to affinity tags in protein engineering. This review provides a comprehensive overview of cyclic peptide types, synthesis methods, and the latest advances in cyclic peptide-based therapeutics. Particular emphasis has been placed on “tag-like” cyclic peptides, which can function as affinity tags for enhancing the bioactivity and targeting capabilities of larger proteins. We explore various cyclization techniques, including disulfide bridging, metal-mediated linkers, and organic reagents, that facilitate the production of both monocyclic and bicyclic peptides with optimized pharmacokinetic and stability profiles. Recent advancements in display technologies, such as phage and mRNA display, further underscore the therapeutic potential of cyclic peptides, enabling rapid identification of candidates with high affinity and selectivity for a range of targets. This review discusses the potential of cyclic peptides as affinity tags that can be engineered onto proteins of interest, bridging the gap between small molecules and larger biologics, and explores future directions for their use in enhancing protein purification, detection, and interaction studies in protein engineering projects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Osteocyte dysfunction promotes osteoarthritis through MMP13-dependent suppression of subchondral bone homeostasis

引用

Bone Research 2019年第4期7卷 354-370页

作者： Courtney MMazur Jonathon JWoo Cristal SYee Aaron JFields Claire Acevedo Karsyn NBailey Serra Kaya Tristan WFowler Jeffrey CLotz Alexis Dang Alfred CKuo Thomas PVail Tamara Alliston Department of Orthopaedic Surgery University of CaliforniaSan FranciscoCA 94143USA UC Berkeley-UCSF Graduate Program in Bioengineering San FranciscoCA 94143USA Department of Mechanical Engineering University of UtahSalt Lake CityUT 84112USA San Francisco Veterans Affairs Medical Center San FranciscoCA 94121USA

Osteoarthritis(OA),long considered a primary disorder of articular cartilage,is commonly associated with subchondral bone ***,the cellular mechanisms responsible for changes to subchondral bone in OA,and the extent to which these changes are drivers of or a secondary reaction to cartilage degeneration,remain *** knee joints from human patients with end-stage OA,we found evidence of profound defects in osteocyte *** of osteocyte perilacunar/canalicular remodeling(PLR)was most severe in the medial compartment of OA subchondral bone,with lower protease expression,diminished canalicular networks,and disorganized and hypermineralized extracellular *** a step toward evaluating the causality of PLR suppression in OA,we ablated the PLR enzyme MMP13 in osteocytes while leaving chondrocytic MMP13 intact,using Cre recombinase driven by the 9.6-kb DMP1 *** only did osteocytic MMP13 deficiency suppress PLR in cortical and subchondral bone,but it also compromised *** in the absence of injury,osteocytic MMP13 deficiency was sufficient to reduce cartilage proteoglycan content,change chondrocyte production of collagen II,aggrecan,and MMP13,and increase the incidence of cartilage lesions,consistent with early ***,in humans and mice,defects in PLR coincide with cartilage ***-derived MMP13 emerges as a critical regulator of cartilage homeostasis,likely via its effects on ***,these findings implicate osteocytes in bone-cartilage crosstalk in the joint and suggest a causal role for suppressed perilacunar/canalicular remodeling in osteoarthritis.

关键词： MMP13 homeostasis likely

来源：评论

学校读者我要写书评

暂无评论

Design and energy assessment of a new hybrid solar drying dome - Enabling Low-Cost, Independent and Smart Solar Dryer for Indonesia Agriculture 4.0

引用

IOP Conference Series: Earth and Environmental Science 2022年第1期998卷

作者： F E Gunawan A S Budiman B Pardamean E Djuana S Romeli N Hananda C Harito D P B Aji D N N Putri Stevanus Industrial Engineering Department BINUS Graduate Program - Master of Industrial Engineering Bina Nusantara University Jakarta Indonesia 11480 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Electrical Engineering Department Faculty of Industrial Technology Universitas Trisakti Jakarta 11440 Indonesia PT. Impack Pratama Industri Jakarta Indonesia Industrial Engineering Department Faculty of Engineering Bina Nusantara University Jakarta 11480 Indonesia. Mechanical Engineering Department. Faculty of Industrial Technology Universitas Trisakti Jakarta 11440 Indonesia

Solar dryer is typically used for agricultural purposes in Indonesia. There are many economically important crops requiring storage or drying under particular environmental conditions such as temperature and humidity. High temperatures inside solar dryer prevents the growth of microorganism, and quickly reduce moisture content from the substance. A hybrid solar dryer is generally considered to provide the most optimum solution, however solar panels may be expensive and they still only provide heat or energy in the daytime. Hence, we propose here a new kind of hybrid solar dryer for 24/7 optimum conditions for crops - enabled by recent advances in energy technologies as well as Industry 4.0. This study aims to create an efficient, affordable and a self-sufficient intelligent energy system that will be applied to agriculture for storage or drying purposes by measuring the energy needs for the optimal drying system. Therefore, it is crucial to estimate and assess the critical energy needs for such new systems in order to optimize and design such smart solar dryer (SSD) system especially for Indonesia's agricultural needs. We use design experience of our industry partner (PT Impack Pratama Industri, Indonesia) who has been working extensively on such solar dryer dome (SDD) based on polycarbonate material (only solar irradiation, no other technologies) and theoretical framework based on first principles in thermodynamics to estimate and assess critical energy needs for such dome with all the smart technologies. The calculation was performed based on Mollier diagram and the result still a rough estimation of energy required.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reachability-based Trajectory Safeguard (RTS): A safe and fast reinforcement learning safety layer for continuous control

arXiv

引用

arXiv 2020年

作者： Shao, Yifei Simon Chen, Chao Kousik, Shreyas Vasudevan, Ram The School of Mechanical Engineering University of Michigan Ann ArborMI United States The Robotics Institute University of Michigan Ann ArborMI United States The Department of Aeronautics and Astronautics Stanford University StanfordCA United States

Reinforcement Learning (RL) algorithms have achieved remarkable performance in decision making and control tasks by reasoning about long-term, cumulative reward using trial and error. However, during RL training, applying this trial- and-error approach to real-world robots operating in safety critical environment may lead to collisions. To address this challenge, this paper proposes a Reachability-based Trajectory Safeguard (RTS), which leverages reachability analysis to ensure safety during training and operation. Given a known (but uncertain) model of a robot, RTS precomputes a Forward Reachable Set of the robot tracking a continuum of parameterized trajectories. At runtime, the RL agent selects from this continuum in a receding-horizon way to control the robot;the FRS is used to identify if the agent’s choice is safe or not, and to adjust unsafe choices. The efficacy of this method is illustrated in static environments on three nonlinear robot models, including a 12-D quadrotor drone, in simulation and in comparison with state-of-the-art safe motion planning methods. © 2020, CC BY-NC-ND.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of a Workload-Adaptive Haptic Shared Control Framework for Semi-Autonomous Driving

Design and Evaluation of a Workload-Adaptive Haptic Shared C...

引用

American Control Conference

作者： Yifan Weng Ruikun Luo Paramsothy Jayakumar Mark J. Brudnak Victor Paul Vishnu R. Desaraju Jeffrey L. Stein X. Jessie Yang Tulga Ersal Department of Mechanical Engineering University of Michigan Ann Arbor MI Robotics Institute University of Michigan Ann Arbor MI U.S. Army Ground Vehicles System Center Warren MI Toyota Research Institute Ann Arbor MI Department of Industrial and Operations Engineering University of Michigan Ann Arbor MI

ISBN: (数字)9781538682661

ISBN: (纸本)9781538682678

Haptic shared control of an autonomy-enabled vehicle is used to manage the control authority allocation between a human and autonomy smoothly. Existing haptic shared control schemes, however, do not take the workload condition of human into account. To fill this research gap, this study develops a novel haptic shared control scheme that adapts to a human operator's workload in a semi-autonomous driving scenario. Human-in-the-loop experiments with 8 participants are reported to evaluate the new scheme. In the experiment, a human operator and an autonomous navigation module shared the steering control of a simulated teleoperated vehicle in a path tracking task while the speed of the vehicle is controlled by autonomy. High and low screen refresh rates were used to create moderate and high workload cases, respectively. Results indicate that adaptive haptic control leads to less driver control effort without sacrificing the path tracking performance when compared with the non-adaptive case.

关键词： Vehicle speed steering control Human vehicle Standing Orders Workload tracking Autonomy driver control

来源：评论

学校读者我要写书评

暂无评论

Active Upper Arm Exoskeleton – Design and Kinematic Analysis

Active Upper Arm Exoskeleton – Design and Kinematic Analysi...

引用

IEEE Region 10 Symposium

作者： Paulami Santra Arani Mukhopadhyay Bishan Debnath Mervin A. Herbert Subhasis Bhaumik Department of Mechanical Engineering National Institute of Technology Karnataka Surathkal India Department of Mechanical Engineering Indian Institute of Engineering Science and Technology Howrah India School of Mechatronics and Robotics Indian Institute of Engineering Science and Technology Howrah India

The authors present a design of an exoskeleton with 6 active degrees of freedom (DOF) and 5 passive DOFs for rehabilitation of stroke survivors. Emphasis has been laid on making the model light weight and more ergonomic. Thus, concentration is mainly on 3D modeling of that device so that the mechatronic approach is compatible with human hand. The main choice of material for fabrication has been Nylon 6/10, owing to its lightweight and durable properties. The model was developed completely by the use of Computer Aided Design (CAD) and Computer Aided engineering (CAE). Our model focuses on proposing a new actuation principle for better development of ergonomic shoulder design by incorporation of compliant passive springs and one passive revolute joint. Joints of the exoskeleton have been taken as simple revolute, possessing desired motion limits. Also forward kinematics has been established and the general workspace of the model has been developed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Safer Motion Planning of Steerable Needles via a Shaft-to-Tissue Force Model

arXiv

引用

arXiv 2021年

作者： Bentley, Michael Rucker, Caleb Reddy, Chakravarthy Salzman, Oren Kuntz, Alan Robotics Center Kahlert School of Computing University of Utah Salt Lake CityUT84112 United States The Department of Mechanical Aerospace and Biomedical Engineering University of Tennessee KnoxvilleTN37996 United States Huntsman Cancer Institute and School of Medicine University of Utah Salt Lake CityUT84112 United States Department of Computer Science Technion - Israel Institute of Technology Technion City Haifa3200003 Israel

Steerable needles are capable of accurately targeting difficult-to-reach clinical sites in the body. By bending around sensitive anatomical structures, steerable needles have the potential to reduce the invasiveness of many medical procedures. However, inserting these needles with curved trajectories increases the risk of tissue damage due to perpendicular forces exerted on the surrounding tissue by the needle's shaft, potentially resulting in lateral shearing through tissue. Such forces can cause significant damage to surrounding tissue, negatively affecting patient outcomes. In this work, we derive a tissue and needle force model based on a Cosserat string formulation, which describes the normal forces and frictional forces along the shaft as a function of the planned needle path, friction model and parameters, and tip piercing force. We propose this new force model and associated cost function as a safer and more clinically relevant metric than those currently used in motion planning for steerable needles. We fit and validate our model through physical needle robot experiments in a gel phantom. We use this force model to define a bottleneck cost function for motion planning and evaluate it against the commonly used path-length cost function in hundreds of randomly generated 3-D environments. Plans generated with our force-based cost show a 62% reduction in the peak modeled tissue force with only a 0.07% increase in length on average compared to using the path-length cost in planning. Additionally, we demonstrate the ability to plan motions with our force-based cost function in a lung tumor biopsy scenario from a segmented computed tomography (CT) scan. By planning motions for the needle that aim to minimize the modeled needle-to-tissue force explicitly, our method plans needle paths that may reduce the risk of significant tissue damage while still reaching desired targets in the body. © 2021, CC BY.

关键词： Needles

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：