检索结果-内蒙古大学图书馆

IEEE Conference on Decision and Control

作者： Skyler Hughes Rebecca Martin Micah Corah Sebastian Scherer NSF REU program Robotics Institute Summer Scholars (RISS) program Carnegie Mellon University Airlab Robotics Institute Carnegie Mellon University Department of Computer Science Colorado School of Mines

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

Observing and filming a group of moving actors with a team of aerial robots is a challenging problem that combines elements of multi-robot coordination, coverage, and view planning. A single camera may observe multiple actors at once, and a robot team may observe individual actors from multiple views. As actors move about, groups may split, merge, and reform, and robots filming these actors should be able to adapt smoothly to such changes in actor formations. Rather than adopt an approach based on explicit formations or assignments, we propose an approach based on optimizing views directly. We model actors as moving polyhedra and compute approximate pixel densities for each face and camera view. Then, we propose an objective that exhibits diminishing returns as pixel densities increase from repeated observation. This gives rise to a multi-robot perception planning problem that we solve via a combination of value iteration and greedy submodular maximization. We evaluate our approach on challenging scenarios modeled after various social behaviors and featuring different numbers of robots and actors and observe that robot assignments and formations arise implicitly given the movements of groups of actors. Simulation results demonstrate that our approach consistently outperforms baselines, and in addition to performing well with the planner’s approximation of pixel densities our approach also performs comparably for evaluation based on rendered views. Overall, the multi-round variant of the sequential planner we propose meets (within 1%) or exceeds formation and assignment baselines in all scenarios.

关键词： Robot kinematics Simulation Robot vision systems Cameras Motion pictures Planning Trajectory Multi-robot systems Optimization Sports

来源：评论

学校读者我要写书评

暂无评论

Neural Network Model of Continuum Soft Robots Based on WaveNets Equipped with Adaptive IIR 21

Neural Network Model of Continuum Soft Robots Based on WaveN...

引用

21st International Conference on Electrical Engineering, Computing Science and Automatic Control, CCE 2024

作者： Garcia-Castro, Oscar Federico Ramos-Velasco, Luis Enrique Parra-Vega, Vicente Garcia-Rodriguez, Rodolfo Vazquez-Garcia, Carlos Ernesto CINVESTAV-IPN Robotics and Advanced Manufacturing Coahuila Ramos Arizpe Mexico Universidad Politecnica Metropolitana Posgraduate Program of Aeroespace Engineering de Hidalgo Mexico CINVESTAV-IPN Robotics and Advanced Manufacturing Coahuila Mexico Universidad Autónoma de Coahuila Facultad de Ciencias de la Administración de Coahuila Mexico

ISBN: (纸本)9798350377545

Soft robots have attracted attention from many areas, such as robotics, materials, automatic control, and artificial intelligence. The particular class of continuum soft robot (cSR) is the most challenging given its highly nonlinear dynamics from the hyperviscoelasticity and varying stiffness, which arise from the modeling of an infinite conglomerate of particles enclosed in a deformable finite-dimensional body based on the lumped parameters assumption and the D' Alambert principle. The cSR is a complex model that presents a significant challenge in the field. Its nonintuitive structure, variable natural frequency, and parametric uncertainties, including its input matrix and lack of reliable velocity measurements, make it difficult to approximate its dynamics using only input and partial output data. This paper proposes a wavelet-based neural network (WaveNet) with an adaptive infinite impulse response (IIR) output filter. The WaveNet sweeps over modal frequencies, while the IIR enforces feedback and forward loops to propagate current and past neural outputs. The input shapes a controllable canonical output form. Simulations for a 2-degree-of-freedom CSR show that a bounded approximate modeling error is guaranteed at a low computational cost. © 2024 IEEE.

关键词： Impulse response

来源：评论

学校读者我要写书评

暂无评论

Development of Automatic Detection and Monitoring Application System for Peristaltic Condition based on Machine Learning and Internet of Thing (IoT) System 7

Development of Automatic Detection and Monitoring Applicatio...

引用

7th International Conference of Computer and Informatics Engineering, IC2IE 2024

作者： Astuti, Winda Giovanni Benedict Davin, K. Nurul Puji, Muhammad Kunaifi, Matthew Andriatin, Yuli Astuti Bina Nusantara University Binus Aso School of Engineering Automotive and Robotics Program Computer Engineering Department Jakarta Indonesia Cilacap Regional General Hospital Gatot Subroto No.28 Cilacap Indonesia

ISBN: (纸本)9798331505530

Poor sanitation and limited access to clean water are the main causes of increased risk of gastrointestinal diseases. In Indonesia, environmental hygiene problems are the main cause of digestive tract disorders, which contribute to more than 25% of deaths each year according to data from the Ministry of Health. Digestive disease is one of the diseases that often appears due to Poor sanitation and limited access to clean water. The development of a digital stethoscope for early detection of problems in the digestive tract would be useful, especially in remote areas. The sound was recorded from a Mel Frequency Cepstral Coefficient (MFCC) technique. The resulting features extracted from the stethoscope sound signal, are used as the inputs for the machine learning which applied three types of method, they are Logistic Regression (LR), combination of Logistic Regression (LR) and K-Nearest Neighbors (KNN), combination of Logistic Regression (LR) and Support Vector Machine (SVM). The experiment of MFCC with three types of machine learning methods above, based the sound from a stethoscope. Experimental results show the combination of Logistic Regression (LR) and K-Nearest Neighbors (KNN) has exceeded results among other methods, with the training and testing accuracy of 90 % and 88 % respectively. They confirm the effectiveness of the proposed intelligent automatic stethoscope sound identification based on Mel-Frequency Cepstral Coefficient (MFCC) and Linear Regression. Furthermore, the system continuously saves and monitors the result of the patient. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Inpatient Monitoring System: Temperature, Oxygen Saturation, Blood Pressure, Heart Rate, and Infusion Automation Based on ESP 32, IoT, and Mobile Application 7

Inpatient Monitoring System: Temperature, Oxygen Saturation,...

引用

7th International Conference of Computer and Informatics Engineering, IC2IE 2024

作者： Joseph, Irvanda Anthony, Patrick Astuti, Winda Lie, Zener Sukra Iwan Solihin, Mahmud Bina Nusantara University Binus Aso School of Engineering Automotive and Robotics Program Computer Engineering Department Jakarta11480 Indonesia Ucsi University Department of Mechanical and Mechatronics Engineering Kuala Lumpur Malaysia

ISBN: (纸本)9798331505530

The implementation of a patient monitoring system and infusion automation which aims to ensure regular and periodic monitoring of inpatient conditions are applied in this system. This embedded system is applied in hospitals and addresses the uneven distribution of healthcare workers in Indonesia, particularly in remote areas. Currently, manual checks by nurses can lead to errors and reduced patient comfort. The improvement supervision is developed in this work. The system monitored body temperature, oxygen saturation, blood pressure, heart rate, and automated infusions. All the embedded systems are connected to Internet of Things (IoT) and a real-time database accessible through an application and web. This system allows doctors and hospital authorities to make decisions based on patient condition history. The testing phase of the system shows four data acquisition devices (temperature, oxygen saturation, blood pressure, and heart rate), an ESP 32, and Firebase as a database, have ability to capture and send real-time data every five seconds and can be accessed by doctors, patients, and hospital authorities. © 2024 IEEE.

关键词： Remote patient monitoring

来源：评论

学校读者我要写书评

暂无评论

A Real-time Affordance-based Object Pose Estimation Approach for Robotic Grasp Pose Estimation

A Real-time Affordance-based Object Pose Estimation Approach...

引用

2023 International Conference on System Science and Engineering, ICSSE 2023

作者： Wong, Shang-Wen Chiu, Yu-Chen Tsai, Chi-Yi Tamkang University Doctoral Program in Robotics College of Engineering New Taipei City Taiwan Tamkang University Department of Electrical and Computer Engineering New Taipei City Taiwan

ISBN: (纸本)9798350322941

This paper proposes a pose estimation system for robot grasping based on a novel Object Affordance Detection and Segmentation (OADS) network. The proposed system consists of four modules: (1) OADS network;(2) point cloud extraction;(3) object pose estimation;(4) grasp pose estimation. Based on the OADS network, the proposed system achieves affordance-based object pose estimation results. The proposed grasp pose estimation system is evaluated on a laboratory-made dual-arm robot. Experimental results show that the proposed system achieves high detection rate and high accuracy in affordance detection and segmentation tasks, leading to a high success rate in object grasping tasks with lab-made dual-arm robot. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Reward Generation via Large Vision-Language Model in Offline Reinforcement Learning

Reward Generation via Large Vision-Language Model in Offline...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Younghwan Lee Tung M. Luu Donghoon Lee Chang D. Yoo Electrical Engineering KAIST Daejeon South Korea Robotics Program KAIST Daejeon South Korea

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In offline reinforcement learning (RL), learning from fixed datasets presents a promising solution for domains where real-time interaction with the environment is expensive or risky. However, designing dense reward signals for offline dataset requires significant human effort and domain expertise. Reinforcement learning with human feedback (RLHF) has emerged as an alternative, but it remains costly due to the human-in-the-loop process, prompting interest in automated reward generation models. To address this, we propose Reward Generation via Large Vision-Language Models (RG-VLM), which leverages the reasoning capabilities of LVLMs to generate rewards from offline data without human involvement. RG-VLM improves generalization in long-horizon tasks and can be seamlessly integrated with the sparse reward signals to enhance task performance, demonstrating its potential as an auxiliary reward signal.

关键词： Reinforcement learning Signal processing Real-time systems Human in the loop Data models Cognition Acoustics Labeling Speech processing

来源：评论

学校读者我要写书评

暂无评论

Sample Efficient Reinforcement Learning via Large Vision Language Model Distillation

Sample Efficient Reinforcement Learning via Large Vision Lan...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Donghoon Lee Tung M. Luu Younghwan Lee Chang D. Yoo Robotics Program KAIST Daejeon South Korea Electrical Engineering KAIST Daejeon South Korea

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recent research highlights the potential of multi-modal foundation models in tackling complex decision-making challenges. However, their large parameters make real-world deployment resource-intensive and often impractical for constrained systems. Reinforcement learning (RL) shows promise for task-specific agents but suffers from high sample complexity, limiting practical applications. To address these challenges, we introduce LVLM to Policy (LVLM2P), a novel framework that distills knowledge from large vision-language models (LVLM) into more efficient RL agents. Our approach leverages the LVLM as a teacher, providing instructional actions based on trajectories collected by the RL agent, which helps reduce less meaningful exploration in the early stages of learning, thereby significantly accelerating the agent’s learning progress. Additionally, by leveraging the LVLM to suggest actions directly from visual observations, we eliminate the need for manual textual descriptors of the environment, enhancing applicability across diverse tasks. Experiments show that LVLM2P significantly enhances the sample efficiency of baseline RL algorithms. The code is available at https://***/i22024/LVLM2P

关键词： Visualization Limiting Foundation models Decision making Signal processing algorithms Reinforcement learning Cognition Trajectory Complexity theory Speech processing

来源：评论

学校读者我要写书评

暂无评论

Vehicle Speed Control in the Dilemma Zone Using Deep Learning

引用

Journal of Institute of Control, robotics and Systems 2022年第3期28卷 209-217页

作者： Lee, Jaewook Kim, Bongsang Sim, Hongseok Choi, Hyohyuk Moon, Heechang Industrial Convergence Interdepartmental Program Autonomous Vehicle･Intelligent Robotics The Graduate School of Hongik University Korea Republic of Mechanical and System Design Engineering Hongik University Korea Republic of

The dilemma zone refers to the area where a vehicle approaching an intersection as the light turns yellow must decide whether to stop or not. Often, the vehicle’s speed is too fast for it to stop at the stop line before the light turns red, but the vehicle cannot completely clear the intersection before the three-second yellow signal ends. This can lead to a major accident as the departing vehicle has not cleared the intersection before the opposite light changes to a green signal and cars on the other side of the intersection start to move. To prepare for this situation, traffic light patterns were modified using pre-trained data sets, then the traffic patterns at these lights were recorded using cameras. Autonomous vehicles were introduced into these areas and their speed was controlled based on the recognized traffic light patterns. This paper explores whether deep learning algorithms can effectively control vehicle speed when autonomous vehicles face the dilemma zone. © ICROS 2022.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

ASTM: Autonomous Smart Traffic Management System Using Artificial Intelligence CNN and LSTM

arXiv

引用

arXiv 2024年

作者： Goenawan, Christofel Rio Robotics Master Program Korea Advanced Institute of Science and Technology Daejeon Korea Republic of

In the modern world, the development of Artificial Intelligence (AI) has contributed to improvements in various areas, including automation, computer vision, fraud detection, and more. AI can be leveraged to enhance the efficiency of Autonomous Smart Traffic Management (ASTM) systems and reduce traffic congestion rates. This paper presents an Autonomous Smart Traffic Management (STM) system that uses AI to improve traffic flow rates. The system employs the YOLO V5 Convolutional Neural Network to detect vehicles in traffic management images. Additionally, it predicts the number of vehicles for the next 12 hours using a Recurrent Neural Network with Long Short-Term Memory (RNN-LSTM). The Smart Traffic Management Cycle Length Analysis manages the traffic cycle length based on these vehicle predictions, aided by AI. From the results of the RNN-LSTM model for predicting vehicle numbers over the next 12 hours, we observe that the model predicts traffic with a Mean Squared Error (MSE) of 4.521 vehicles and a Root Mean Squared Error (RMSE) of 2.232 vehicles. After simulating the STM system in the CARLA simulation environment, we found that the Traffic Management Congestion Flow Rate with ASTM (21 vehicles per minute) is 50% higher than the rate without STM (around 15 vehicles per minute). Additionally, the Traffic Management Vehicle Pass Delay with STM (5 seconds per vehicle) is 70% lower than without ASTM (around 12 seconds per vehicle). These results demonstrate that the ASTM system using AI can increase traffic flow by 50% and reduce vehicle pass delays by 70%. © 2024, CC BY.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Real-time Path Planning Algorithm based on Ridge Detection for Solid-State LiDAR-based Autonomous Agricultural Robot

引用

Journal of Institute of Control, robotics and Systems 2022年第2期28卷 146-152页

作者： Baek, Seungbeom Kim, Bongsang Lee, Jaewook Moon, Heechang Industrial Convergence Interdepartmental Program Autonomous Vehicle·Intelligent Robotics The Graduate School of Hongik University Korea Republic of Mechanical & System Design Engineering Hongik University Korea Republic of

Autonomous robots driving in agricultural environments need to create accurate routes to prevent damaging farmland. Herein, a real-time path planning algorithm based on ridge detection using the Livox Mid70 LiDAR is proposed. The field has a steep slope between the furrow and the ridge, and we find data corresponding to this slope from the lidar data. Using two Mid70 LiDARs, we collect the left and right slope data and linearly fit the slope data using the RANSAC algorithm. Finally, the driving route is obtained from the average of the two straight lines. To verify the algorithm, the steering angle needed to follow the driving path was calculated, and an autonomous driving test was conducted in the actual field environment: it was observed that the robot drove stably. Additional tests will be conducted in more rugged terrain. © ICROS 2022.

关键词： Optical radar

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：