检索结果-内蒙古大学图书馆

21st International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2022

作者： Aswale, Ashay López, Antonio Ammartayakun, Aukkawut Pinciroli, Carlo Department of Robotics Engineering Worcester Polytechnic Institute WorcesterMA United States

ISBN: (纸本)9781713854333

Ants have evolved to seek and retrieve food by leaving trails of pheromones. This mechanism has inspired several approaches to decentralized multi-robot coordination. However, in this paper, we show that pheromone trails are a fragile mechanism for coordination, and can be sabotaged to starve the colony. We introduce detractors: malicious agents that leave a misleading, but indistinguishable, trail of food pheromone to distract and trap cooperator ants in the nest. We analyze the effectiveness of detractors with respect to parameters such as evaporation rate of misleading pheromone and fraction of detractors in the colony. In addition, we propose a countermeasure to this attack by introducing a new type of pheromone: the cautionary pheromone. Cooperator ants secrete this type of pheromone atop existing food trails as a warning. When the cautionary pheromone intensity exceeds the food pheromone intensity, cooperator ants ignore overlapping food pheromone. We show that, despite its simplicity, this defense mechanism can limit, but not nullify, the effect of detractors. Ultimately, our work shows that pheromone-based coordination, while effective, is also fragile. © 2022 International Foundation for Autonomous Agents and Multiagent Systems (***). All rights reserved

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

A System for Watering and Autonomously Monitoring Plants

A System for Watering and Autonomously Monitoring Plants

引用

IEEE Symposium on Systems and Information engineering Design, SIEDS

作者： E. Gutman L. Harrison J. Hart I. Lucas C. Mullane G. C. Lewin Department of Mechanical Engineering Worcester Polytechnic Institute Worcester Massachusetts Department of Robotics Engineering Worcester Polytechnic Institute Worcester Massachusetts

ISBN: (数字)9798331535759

ISBN: (纸本)9798331535766

To alleviate the challenges of plant care, the Great Roboticz Ladiez’ Plant Watering Robot (GRL PWR) team developed SWAMP, a mobile robotic System for Watering and Autonomously Monitoring Plants. SWAMP replicates the plant care a human provides with minimal user input and allows plant owners the freedom to keep their plants anywhere in their homes. From stakeholder analysis, the team categorized the main functionalities required to meet user needs into Customizing Plant Care, Accessing Plants, Assessing Plant Condition, Providing Water, and System Monitoring. The user can input unique watering instructions and plant characteristics. The robot uses a differential drive to autonomously navigate and localize within its environment while safely avoiding obstacles. The robot has an articulated arm to reach plants up to 24 -inches off the ground and set back no more than 2.5 -inches from the edge of the surface. These design choices allow SWAMP to accurately meet the watering needs of each plant, reducing the time commitment required from plant owners. GRL PWR will demonstrate the system in the WPI Gordon Library, providing a real-world environment to assess SWAMP’s ability to map its surroundings, navigate around obstacles, and accurately deliver water to plants.

关键词： Water Visualization Navigation Storage management Robot vision systems User interfaces Stakeholders Robots Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

Run-Time Task Composition with Safety Semantics 41

Run-Time Task Composition with Safety Semantics

引用

41st International Conference on Machine Learning, ICML 2024

作者： Leahy, Kevin Mann, Makai Serlin, Zachary Department of Robotics Engineering Worcester Polytechnic Institute LexingtonMA United States MIT Lincoln Laboratory LexingtonMA United States

Compositionality is a critical aspect of scalable system design. Here, we focus on Boolean composition of learned tasks as opposed to functional or sequential composition. Existing Boolean composition for Reinforcement Learning focuses on reaching a satisfying absorbing state in environments with discrete action spaces, but does not support composable safety (i.e., avoidance) constraints. We provide three contributions: i) introduce two distinct notions of compositional safety semantics;ii) show how to enforce either safety semantics, prove correctness, and analyze the trade-offs between the two safety notions;and iii) extend Boolean composition from discrete action spaces to continuous action spaces. We demonstrate these techniques using modified versions of value iteration in a grid world, Deep Q-Network (DQN) in a grid world with image observations, and Twin Delayed DDPG (TD3) in a continuous-observation and continuous-action Bullet physics environment. Copyright 2024 by the author(s)

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging Dexterous Picking Skills for Complex Multi-Object Scenes

Leveraging Dexterous Picking Skills for Complex Multi-Object...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Anagha Rajendra Dangle Mihir Pradeep Deshmukh Denny Boby Berk Calli Robotics Engineering Department of Worcester Polytechnic Institute

ISBN: (数字)9798350373578

ISBN: (纸本)9798350373585

This work focuses on the problem of robotic picking in challenging multi-object scenarios. These scenarios include difficult-to-pick objects (e.g., too small, too flat objects) and challenging conditions (e.g., objects obstructed by other objects and/or the environment). To solve these challenges, we leverage four dexterous picking skills inspired by human manipulation techniques and propose methods based on deep neural networks that predict when and how to apply the skills based on the shape of the objects, their relative locations to each other, and the environmental factors. We utilize a compliant, under-actuated hand to reliably apply the identified skills in an open-loop manner. The capabilities of the proposed system are evaluated through a series of real-world experiments, comprising 45 trials with 150+ grasps, to assess its reliability and robustness, particularly in cluttered settings. The videos of all experiments are provided at https://***/. This research helps bridge the gap between human and robotic grasping, showcasing promising results in various practical scenarios.

关键词： Shape Force Humanoid robots Grasping Robot sensing systems Robustness Environmental factors Sensors Monitoring Videos

来源：评论

学校读者我要写书评

暂无评论

Leveraging Ultrasound Sensing for Virtual Object Manipulation in Immersive Environments

Leveraging Ultrasound Sensing for Virtual Object Manipulatio...

引用

International Workshop on Wearable and Implantable Body Sensor Networks (BSN)

作者： Keshav Bimbraw Jack Rothenberg Haichong Zhang Robotics Engineering Worcester Polytechnic Institute Worcester USA Robotics Engineering Biomedical Engineering Worcester Polytechnic Institute Worcester USA

Hand gesture recognition is a fundamental component of intuitive and immersive user interfaces in virtual reality (VR) applications. This paper presents a data-driven approach utilizing ultrasound data and deep learning techniques for hand gesture recognition in VR interfaces. The proposed methodology involves acquiring data from a subject, training a model using the acquired data, and evaluating the model’s performance on both the training data and during real-time inference. The evaluation metrics primarily focus on accuracy percentage: measuring the classifier’s performance in correctly classifying hand gestures. 4 hand gestures were primarily considered for the study and demonstration. For offline evaluation with a 20% test-train split, an accuracy percentage of 91% was observed. For online evaluation, an accuracy percentage of 92% was achieved. Results on the classification of 7 hand gestures were also analyzed for both online and online evaluation due to the promising results from the 4 gesture classification. The latency of the pipeline, from ultrasound data acquisition using screenshots to sending commands for VR object manipulation, was measured to be 59.48 milliseconds. The results demonstrate the effectiveness of the approach in accurately recognizing hand gestures, both during training and in real-time inference. We supplement our results with a video of the forearm ultrasound data being used to control a custom-designed VR game in a low-latency fashion. This research provides valuable insights into the performance and applicability of ultrasound-based hand gesture recognition techniques in VR interfaces. By employing deep learning and leveraging real-time data acquisition, this approach paves the way for intuitive and immersive interactions in various VR applications. The study contributes to the field of body sensor networks, highlighting the potential of forearm ultrasound based data-driven techniques for enhancing user interaction and immersion in VR

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feasibility of Spectra-Based Quantification Algorithm for Non-Linear Photoacoustic Contrast Agents

Feasibility of Spectra-Based Quantification Algorithm for No...

引用

Photons Plus Ultrasound: Imaging and Sensing 2023

作者： Serebrennikova, Liudmila Gao, Shang Murakami, Ryo Boinapally, Srikanth Ray, Sangeeta Pomper, Martin G. Zhang, Haichong K. Biomedical Engineering Department Worcester Polytechnic Institute MA United States Robotics Engineering Department Worcester Polytechnic Institute MA United States Computer Science Department Worcester Polytechnic Institute MA United States Radiology and Radiological Science Johns Hopkins University School of Medicine ME United States

ISBN: (纸本)9781510658639

Photoacoustic (PA) imaging is a technique that visualizes the optical absorption characteristics with ultrasound-like spatial resolution. It has been demonstrated that molecular targeted contrast agents (CAs) have great potential in applying to the early detection of tumor. These CAs attach to the tissues of the subject of interest, i.e., the cancerous cells, and emit PA signals based on the absorbed light. Precise quantification of the CA expression is desired to identify the degree of the malignancies. The current quantification of the CA expression is based on the strength of the PA intensity with the assumption of its linearity between them. However, the estimation accuracy of such a method is limited because the PA intensity is affected by many factors including the light, sound, and tissue interactions and the use of CAs that do not present linearity. Here, we investigate a robust quantification method by using the spectroscopic relationship between the dye concentration and its corresponding PA variation. We introduce a spectroscopic decomposition algorithm considering multiple reference spectra to accommodate the non-linear behavior of sample concentrations. The in vitro validation of the concept was performed using the synthesized PA CA possessing the non-linear property. The concentration of the samples was successfully estimated with the algorithm. The introduced method improved the quantification accuracy by reducing the averaging estimation error from 15.89 μM to 1.80 μM, compared with the conventional estimation. © 2023 SPIE.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

Acoustic reflector-enabled forward-viewing ultrasound image-guided access

引用

Journal of Medical Imaging 2025年第2期12卷 025002页

作者： Tang, Yichuan Rahaman, Ashiqur Gonzalez, Araceli B. Abouaf, Issac Malik, Aditya Sorokin, Igor Zhang, Haichong Worcester Polytechnic Institute Department of Robotics Engineering WorcesterMA United States Worcester Polytechnic Institute Department of Biomedical Engineering WorcesterMA United States University of Massachusetts Medical School Department of Urology WorcesterMA United States

Purpose: Existing ultrasound (US) image-guided needle access methods applied in various surgical procedures (such as percutaneous nephrolithotomy) face the challenge of keeping the needle tip visible during the insertion process due to the unguaranteed alignment between the US image and needle. We propose a needle insertion mechanism with reflector-integrated US imaging, where the US image plane and the needle are mechanically aligned, and the needle is inserted in a forward- viewing style to provide more intuitive access. Approach: An acoustic reflector is used to redirect the US image plane while the needle goes through the slit in the middle of the acoustic reflector so that the needle path aligns with the US image plane. Both the bracket holding the needle and the acoustic reflector are rotatable to provide clinicians with the flexibility to search for the optimal needle insertion orientation. Effects of the slit in the reflector on the quality of post-reflection ultrasound images were evaluated. Needle tip visibility was evaluated in water and ex vivo beef tissue. Needle access accuracy was evaluated using point targets embedded in gelatin, and errors between the needle tip and point targets are estimated from X-ray images. Results: The slit in the reflector has limited effects on post-reflection image quality. The needle tip was visible in water and in ex vivo tissue, and its visibility was quantified using a signal-to-noise ratio. Needle access results showed an average insertion error of less than 3 mm. Conclusions: Our results demonstrate the clinical potential of the reflector-enabled forward-viewing US image-guided access mechanism. © 2025 Society of Photo-Optical Instrumentation Engineers (SPIE).

关键词： Ultrasonography

来源：评论

学校读者我要写书评

暂无评论

Utilizing Inpainting for Training Keypoint Detection Algorithms Towards Markerless Visual Servoing

Utilizing Inpainting for Training Keypoint Detection Algorit...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Sreejani Chatterjee Duc Doan Berk Calli Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This paper presents a novel strategy to train keypoint detection models for robotics applications. Our goal is to develop methods that can robustly detect and track natural features on robotic manipulators. Such features can be used for vision-based control and pose estimation purposes, when placing artificial markers (e.g. ArUco) on the robot’s body is not possible or practical in runtime. Prior methods require accurate camera calibration and robot kinematic models in order to label training images for the keypoint locations. In this paper, we remove these dependencies by utilizing inpainting methods: In the training phase, we attach ArUco markers along the robot’s body and then label the keypoint locations as the center of those markers. We, then, use an inpainting method to reconstruct the parts of the robot occluded by the ArUco markers. As such, the markers are artificially removed from the training images, and labeled data is obtained to train markerless keypoint detection algorithms without the need for camera calibration or robot models. Using this approach, we trained a model for realtime keypoint detection and used the inferred keypoints as control features for an adaptive visual servoing scheme. We obtained successful control results with this fully model-free control strategy, utilizing natural robot features in the runtime and not requiring camera calibration or robot models in any stage of this process.

关键词： Training Adaptation models Runtime Robot kinematics Cameras Feature extraction Visual servoing

来源：评论

学校读者我要写书评

暂无评论

RUS-Sim: A Robotic Ultrasound Simulator Modeling Patient-Robot Interaction and Real-Time Image Acquisition

RUS-Sim: A Robotic Ultrasound Simulator Modeling Patient-Rob...

引用

IEEE International Symposium on Applications of Ferroelectrics (ISAF)

作者： Xihan Ma Yernar Zhetpissov Haichong K. Zhang Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798350371901

ISBN: (纸本)9798350371918

Robotic ultrasound (US) imaging techniques are gaining increasing attention among the community. However, during the development of a robotic US system (RUSS), it is necessary to verify the effectiveness of the system inside a simulation environment before the deployment in the real world. Unfortunately, a simulation tool that considers both the dynamics of a robot system and the acquisition of US images has not been available. To address this need, we present RUS-Sim, a robotic US simulator built based on a well-established robotic simulation platform. RUS-Sim features (i) simulation of patient-robot interaction and (ii) real-time simulation of US images from the CT scan of an actual patient. Preliminary experiments show that the simulated RUSS can be controlled to maintain constant contact force (control error: 0.021 ± 0.105 N) on the patient body along the scan trajectory while collecting realistic US images at a rate of 50 fps.

关键词： Ultrasonic imaging Computed tomography Imaging Real-time systems Acoustics Trajectory Force control Robots Frequency control

来源：评论

学校读者我要写书评

暂无评论

Grow-to-Shape Control of Variable Length Continuum Robots via Adaptive Visual Servoing

Grow-to-Shape Control of Variable Length Continuum Robots vi...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Abhinav Gandhi Shou-Shan Chiang Cagdas D. Onal Berk Calli Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In this paper, we propose an adaptive eye-to-hand vision-based control methodology, which enables a closed-loop grow-to-shape capability for variable length continuum manipulators in 2D. Our method utilizes shape features of the continuum robot, i.e. module curvature and length, which are obtained from the image. Our adaptive control algorithm servos the robot to converge and track the desired values of these features in the image space without the need of a robot model. As a result the robot starts from a minimum length configuration and grows into a given desired shape, always staying on the course of the desired shape. We believe that this approach unlocks capabilities for variable length continuum robots by leveraging their actuation redundancy and avoiding obstacles while carrying out object manipulation or inspection tasks in cluttered and constrained environments. We perform experiments in simulations and on a real robot to assess the performance of our visual servoing algorithm. Our experimental results demonstrate the controllers ability to accurately converge the current features to their references, for a variety of desired shapes in the image, while ensuring a smooth tracking response. We also present some proof of concept results demonstrating the effectiveness of this technique for controlling the robot in constrained environments. Markedly, this is the first successful demonstration for automatic grow-to-shape control using visual feedback for variable length continuum manipulators.

关键词： Visualization Shape Redundancy Inspection Aerospace electronics Manipulators Visual servoing Continuum robots Servomotors Intelligent robots

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：