检索结果-内蒙古大学图书馆

IEEE international conference on robotics and automation (ICRA)

作者： Preiss, James A. Millard, David Yao, Tao Sukhatme, Gaurav S. Univ Southern Calif Los Angeles CA 90007 USA

ISBN: (纸本)9781728196817

We propose a method for robotic control of deformable objects using a learned nonlinear dynamics model. After collecting a dataset of trajectories from the real system, we train a recurrent neural network (RNN) to approximate its input-output behavior with a latent state-space model. The RNN internal state is low-dimensional enough to enable realtime nonlinear control methods. We demonstrate a closed-loop control scheme with the RNN model using a standard nonlinear state observer and model-predictive controller. We apply our method to track a highly dynamic trajectory with a point on the deformable object, in real time and on real hardware. Our experiments show that the RNN model captures the true system's frequency response and can be used to track trajectories outside the training distribution. In an ablation study, we find that the full method improves tracking accuracy compared to an open-loop version without the state observer.

关键词： Deformable models Training Tracking loops Recurrent neural networks Tracking Observers Hardware

来源：评论

学校读者我要写书评

暂无评论

Narrowing the coordinate-frame gap in behavior prediction models: Distillation for efficient and accurate scene-centric motion forecasting 39

Narrowing the coordinate-frame gap in behavior prediction mo...

引用

IEEE international conference on robotics and automation (ICRA)

作者： Su, DiJia (Andy) Douillard, Bertrand Al-Rfou, Rami Park, Cheol Sapp, Benjamin Princeton Univ Princeton NJ 08544 USA Waymo LLC Mountain View CA USA

ISBN: (纸本)9781728196817

Behavior prediction models have proliferated in recent years, especially in the popular real-world robotics application of autonomous driving, where representing the distribution over possible futures of moving agents is essential for safe and comfortable motion planning. In these models, the choice of coordinate frames to represent inputs and outputs has crucial trade offs which broadly fall into one of two categories. Agent-centric models transform inputs and perform inference in agent-centric coordinates. These models are intrinsically invariant to translation and rotation between scene elements, are best-performing on public leaderboards, but scale quadratically with the number of agents and scene elements. Scene-centric models use a fixed coordinate system to process all agents. This gives them the advantage of sharing representations among all agents, offering efficient amortized inference computation which scales linearly with the number of agents. However, these models have to learn invariance to translation and rotation between scene elements, and typically underperform agent-centric models. In this work, we develop knowledge distillation techniques between probabilistic motion forecasting models, and apply these techniques to close the gap in performance between agent-centric and scene-centric models. This improves scenecentric model performance by 13.2% on the public Argoverse benchmark, 7.8% on Waymo Open Dataset and up to 9.4% on a large In-House dataset. These improved scene-centric models rank highly in public leaderboards and are up to 15 times more efficient than their agent-centric teacher counterparts in busy scenes.

关键词： Computational modeling Robot kinematics Transforms Predictive models Benchmark testing Probabilistic logic Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

Simulation models verification and validation: Recent development and challenges: A review

引用

international JOURNAL OF MODELING SIMULATION AND SCIENTIFIC COMPUTING 2025年第1期16卷

作者： Biazen, Melkamu Ambelu Woldeyohannes, Abraham Debebe Gebeyehu, Sisay Geremew Bahir Dar Univ Bahir Dar Inst Technol Fac Mech & Ind Engn Ind Engn Bahir Dar 26 Ethiopia Addis Ababa Sci & Technol Univ Coll Elect & Mech Engn Mech Engn Addis Ababa Ethiopia

Nowadays, verification and validation activities have become the prominent parameters to check the acceptability of a simulation model by the users for the intended purpose. This review paper aims to identify and analyze the recent development and challenges of simulation model verification and validation. To achieve this objective, a systematic review of the literature was carried out which mainly consisted of the methodological development of verification and validation process paralleled with simulation model development. Initially, a cumulative total of 980 records was found sourced from Google Scholar via an advanced search method, Science Direct, Web of science and from Scopus. Through a rigorous screening process about 72 sources or publications were included for analysis. The verification and validation techniques that have been developed so far were classified into five categories methodologically. From intensive analysis, it is found that researchers extensively scrutinize the traditional methods and graphical/ statistical tools, escalating interest in data-driven and automation techniques, and limited focus on agent-based and hybrid models. Though agent-based and hybrid models are increasingly vital in the realm of complex system simulations, their verification and validation processes remain relatively under-explored. Though reasonable efforts have been exerted on the verification and validation methods development, still academicians and researchers agreed on the lack of verification and validation methodology for the recently developed simulation model paradigms such as agent-based and hybrid models, autonomous robotics models, high fidelity and data-driven models, and real-time prediction models such as digital twins. As a challenge of verification and validation processes, lack of universal methodologies, lack of reliable real-world data for validation, inaccuracy of real-world data for the intended purpose, different world views by different individ

关键词： Challenges recent development simulation modeling verification validation

来源：评论

学校读者我要写书评

暂无评论

Decentralized Ride-sharing of Shared Autonomous Vehicles Using Graph Neural Network-Based Reinforcement Learning 39

Decentralized Ride-sharing of Shared Autonomous Vehicles Usi...

引用

IEEE international conference on robotics and automation (ICRA)

作者： Li, Boqi Ammar, Nejib Tiwari, Prashant Peng, Huei Univ Michigan Mech Engn Dept Ann Arbor MI 48105 USA Toyota Motor North Amer Plano TX USA

ISBN: (纸本)9781728196817

Ride-sharing has important implications for improving the efficiency of mobility-on-demand systems. However, it remains a challenge due to the complex dynamics between vehicles and requests. This paper presents a decentralized ride-sharing algorithm suitable for shared autonomous vehicles (SAVs) deployment. The ride-sharing problem is formulated as a multi-agent reinforcement learning problem. We explore state representation with the request-vehicle graph to encode shareability and potential coordination information. We use a graph attention network to build a hierarchical structure that unifies ride-sharing assignments with rebalancing and handles real-world scenarios where hundreds of user requests can be associated with vehicles. We show results in both generic gridworld and SUMO simulation with real-world data from the Manhattan area. We empirically demonstrate that our proposed approach can achieve similar performance compared with a state-of-the-art centralized optimization method and higher computation efficiency.

关键词： automation Heuristic algorithms Computational modeling Optimization methods Reinforcement learning Data models Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Preferred Jacobian Differentiation and Direct Collocation methods for an Efficient and Accurate Walker Gait Optimization

引用

international JOURNAL OF CONTROL automation AND SYSTEMS 2025年第5期23卷 1551-1562页

作者： Knisley, Veronica Cho, Kwonseung Lee, Kang-Woo Hur, Pilwon Southwest Res Inst San Antonio TX 78238 USA Gwangju Inst Sci & Technol Dept Mech & Robot Engn Gwangju 61005 South Korea

Devices based on walker robotics research sometimes require a reference trajectory for the control systems of the devices to track. One valuable class of methods used to find an optimal reference trajectory is direct collocation, but even after selecting a method like direct collocation, several optimization design decisions remain. In order to determine the most desirable optimization settings, 600 optimizations were performed for the trajectory of a two degree-of-freedom (DOF) compass gait walker, and 200 optimizations were performed for a five-DOF link walker. These runs evaluated various combinations of optimization settings, including: numerical vs. symbolic vs. automatic differentiation;trapezoidal vs. Hermite Simpson collocation;numerical vs. symbolic calculation of joint accelerations;and inclusion or exclusion of joint accelerations in the decision variables. The different generated gaits were then compared in terms of computational efficiency and accuracy. The results showed that including joint accelerations as decision variables eliminated alternative gaits but increased computational complexity and variability. Symbolic acceleration evaluation was preferable when automatic differentiation was excluded. Automatic differentiation was shown to be significantly faster than the other two differentiation methods for both walking models. In addition, Hermite-Simpson collocation, although slower than trapezoidal, was the more accurate of the two approaches. These results can be applied to the derivation of optimal reference joint trajectories in future robotics applications.

关键词： Computational efficiency direct collocation Jacobian trajectory optimization

来源：评论

学校读者我要写书评

暂无评论

Integrating Deep Reinforcement and Supervised Learning to Expedite Indoor Mapping 39

Integrating Deep Reinforcement and Supervised Learning to Ex...

引用

IEEE international conference on robotics and automation (ICRA)

作者： Zwecher, Elchanan Iceland, Eran Levy, Sean R. Hayoun, Shmuel Y. Gal, Oren Barel, Ariel Hebrew Univ Jerusalem Comp Sci Dept Jerusalem Israel Technion Israel Inst Technol Fac Aerosp Engn Haifa Israel Technion Israel Inst Technol Geoinformat Dept Haifa Israel Technion Israel Inst Technol Comp Sci Dept Haifa Israel

ISBN: (纸本)9781728196817

The challenge of mapping indoor environments is addressed. Typical heuristic algorithms for solving the motion planning problem are frontier-based methods, that are especially effective when the environment is completely unknown. However, in cases where prior statistical data on the environment's architectonic features is available, such algorithms can be far from optimal. Furthermore, their calculation time may increase substantially as more areas are exposed. In this paper we propose two means by which to overcome these shortcomings. One is the use of deep reinforcement learning to train the motion planner. The second is the inclusion of a pre-trained generative deep neural network, acting as a map predictor. Each one helps to improve the decision making through use of the learned structural statistics of the environment, and both, being realized as neural networks, ensure a constant calculation time. We show that combining the two methods can shorten the duration of the mapping process by up to 4 times, compared to frontier-based motion planning.

关键词： Training Neural networks Decision making Supervised learning Reinforcement learning System recovery Predictive models

来源：评论

学校读者我要写书评

暂无评论

EAI-SIM: An Open-source Embodied AI Simulation Framework with Large Language models 18

EAI-SIM: An Open-source Embodied AI Simulation Framework wit...

引用

IEEE 18th international conference on Control and automation (ICCA)

作者： Liu, Guocai Sun, Tao Li, Weihua Li, Xiaohui Liu, Xin Cui, Jinqiang Peng Cheng Lab Shenzhen 518055 Guangdong Peoples R China Shenzhen Inst Artificial Intelligence & Robot Soc Shenzhen Guangdong Peoples R China Beihang Univ Beijing Peoples R China

ISBN: (纸本)9798350354416;9798350354409

In the era of embodied intelligence, developing and testing various intelligent algorithms for robots, including unmanned aerial vehicles (UAVs) and manipulators, poses significant challenges. Researchers are increasingly depends on simulation technologies to evaluate the performance of new algorithms across various conditions and applications. The advent of large language model (LLM) technology creates new demand for simulations of robotics tasks with the help LLMs. This study introduces EAI SIM, a simulation system capable of controlling unmanned aerial vehicles (UAVs) and manipulators based on user prompts. The modular framework acts as an extension of NVIDIA Isaac Sim, facilitating real-time simulation of UAVs and manipulators in photo-realistic environments. Thanks to the modular implementation and user-friendly Graphical User Interface (GUI), it can be seamlessly integrated with the widely used PX4-Autopilot and ROS2 system. To showcase its performance, a variety of control Application Programming Interfaces (APIs) are implemented within EAI SIM. A range of tasks can be achieved by combining different APIs. Supplementary material, including code and documentation for this framework, is provided to benefit the community. The source code can be found at https://***/PengICS/eai sim, and a demo video can be found at https://***/YcNkwo_PNnQ.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Tutorial: Evolutionary Design methods in Electronic Design automation 42

Tutorial: Evolutionary Design Methods in Electronic Design A...

引用

42nd international conference on Computer Design

作者： Sekanina, Lukas Brno Univ Technol Fac Informat Technol Brno Czech Republic

ISBN: (纸本)9798350380415;9798350380408

The use of evolutionary algorithms (EAs) for the automated design of programs, electronic circuits, neural networks, and other computational structures has become a fruitful approach in the last two decades. The advantage of EAs is that they can handle the design process in a holistic, multi-objective way and create solutions with unique properties. This tutorial surveys the key ingredients of EAs and focuses mainly on genetic programming. It presents several techniques (such as incorporating formal verification methods and surrogate models) to improve the scalability of the method. Examples of evolved solutions (approximate arithmetic circuits, neural network architectures, and image filters) that show unique properties compared to conventional designs are presented and discussed.

关键词： accelerator approximate circuit electronic design automation genetic programming machine learning

来源：评论

学校读者我要写书评

暂无评论

Textile Anomaly Detection: Evaluation of the State-of-the-Art for Automated Quality Inspection of Carpet

Textile Anomaly Detection: Evaluation of the State-of-the-Ar...

引用

2023 Australasian conference on robotics and automation, ACRA 2023

作者： Forsberg, Briony Williams, Henry MacDonald, Bruce Chen, Tracy Hulse, Kirstine Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand Bremworth Ltd Auckland New Zealand

In this study, state-of-the-art unsupervised detection models were evaluated for the purpose of automated anomaly inspection of wool carpets. A custom dataset of four unique types of carpet textures was created to thoroughly test the models and their robustness in detecting subtle anomalies in complex textures. Due to the requirements of an inline inspection system in a manufacturing use case, the metrics of importance in this study were accuracy in detecting anomalous areas, the number of false detections, and the inference times of each model for real-time performance. Of the evaluated models, the student-teacher network based methods were found on average to yield the highest detection accuracy and lowest false detection rates. When trained on a multi-class dataset the models were found to yield comparable if not better results than single-class training. Finally, in terms of detection speed, with exception to the generative model, all other evaluated models were found to have comparable inference times on a GPU, with an average of 0.16s per image. On a CPU, most of these models typically produced results between 1.5 to 2 times the respective GPU inference times. © 2023 Australasian robotics and automation Association. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Applications Of Wireless Sensor Networks in Biomedical Research and Healthcare

Applications Of Wireless Sensor Networks in Biomedical Resea...

引用

2024 international conference on Control and automation, Electronics, robotics, Internet of Things, and Artificial Intelligence, CERIA 2024

作者： Dhanraj, Abhilasha Attar, Bilal Ahmad Sharma, Soumil Kshirsagar, Ujwala Symbiosis Institute of Technology Symbiosis International Pune India

ISBN: (纸本)9798331511166

The introduction of Wireless Sensor Networks (WSNs) has sparked a transformative shift in healthcare, offering answers for real-time affected person monitoring, chronic disorder management, and emergency response. By utilising a community of small, low-electricity sensors, WSNs can reveal physiological parameters and provide continuous remarks, enabling early interventions and improving the high-quality of existence for patients. This paper delves into the applications of WSNs in healthcare, that specialize in Body Area Networks (BANs) and electricity-conscious routing, which decorate the performance of WSN structures. We advocate a methodology for integrating WSNs into current healthcare frameworks, supported via power-green routing algorithms. Through simulations, we reveal the impact of WSNs on patient results, underscoring the capacity of those technology to revolutionize healthcare transport. The paper additionally addresses demanding situations which in- cludes records security, community reliability, and power intake, supplying solutions for his or her mitigation. Our consequences imply great enhancements in information accuracy and gadget performance, laying the basis for destiny studies in power-efficient healthcare technologies. © 2024 IEEE.

关键词： Physiological models

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：