Pub Date : 2022-05-01DOI: 10.1109/icra46639.2022.9811850
Mengyu Fu, Kiril Solovey, Oren Salzman, Ron Alterovitz
Medical steerable needles can follow 3D curvilinear trajectories inside body tissue, enabling them to move around critical anatomical structures and precisely reach clinically significant targets in a minimally invasive way. Automating needle steering, with motion planning as a key component, has the potential to maximize the accuracy, precision, speed, and safety of steerable needle procedures. In this paper, we introduce the first resolution-optimal motion planner for steerable needles that offers excellent practical performance in terms of runtime while simultaneously providing strong theoretical guarantees on completeness and the global optimality of the motion plan in finite time. Compared to state-of-the-art steerable needle motion planners, simulation experiments on realistic scenarios of lung biopsy demonstrate that our proposed planner is faster in generating higher-quality plans while incorporating clinically relevant cost functions. This indicates that the theoretical guarantees of the proposed planner have a practical impact on the motion plan quality, which is valuable for computing motion plans that minimize patient trauma.
{"title":"Resolution-Optimal Motion Planning for Steerable Needles.","authors":"Mengyu Fu, Kiril Solovey, Oren Salzman, Ron Alterovitz","doi":"10.1109/icra46639.2022.9811850","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9811850","url":null,"abstract":"<p><p>Medical steerable needles can follow 3D curvilinear trajectories inside body tissue, enabling them to move around critical anatomical structures and precisely reach clinically significant targets in a minimally invasive way. Automating needle steering, with motion planning as a key component, has the potential to maximize the accuracy, precision, speed, and safety of steerable needle procedures. In this paper, we introduce the first resolution-optimal motion planner for steerable needles that offers excellent practical performance in terms of runtime while simultaneously providing strong theoretical guarantees on completeness and the global optimality of the motion plan in finite time. Compared to state-of-the-art steerable needle motion planners, simulation experiments on realistic scenarios of lung biopsy demonstrate that our proposed planner is faster in generating higher-quality plans while incorporating clinically relevant cost functions. This indicates that the theoretical guarantees of the proposed planner have a practical impact on the motion plan quality, which is valuable for computing motion plans that minimize patient trauma.</p>","PeriodicalId":73286,"journal":{"name":"IEEE International Conference on Robotics and Automation : ICRA : [proceedings]. IEEE International Conference on Robotics and Automation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9629985/pdf/nihms-1845718.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9769183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1109/ICRA46639.2022.9812325
Hua Yu, Xuanzhe Fan, Yaqing Hou, Yi Liu, Cai Kang, D. Zhou, Qiang Zhang
{"title":"Towards Efficient 3D Human Motion Prediction using Deformable Transformer-based Adversarial Network","authors":"Hua Yu, Xuanzhe Fan, Yaqing Hou, Yi Liu, Cai Kang, D. Zhou, Qiang Zhang","doi":"10.1109/ICRA46639.2022.9812325","DOIUrl":"https://doi.org/10.1109/ICRA46639.2022.9812325","url":null,"abstract":"","PeriodicalId":73286,"journal":{"name":"IEEE International Conference on Robotics and Automation : ICRA : [proceedings]. IEEE International Conference on Robotics and Automation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79822217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.11591/IJRA.V10I2.PP144-148
Waleed Al-Azzawi
Stepper motors are broadly utilized in actual systems, which are marked by non-linear parameters such as internal, external noises and uncertainties from wireless network. As well, a suitable controller is required when the problem is to track the target signal. In this paper, robust controller based on model reference are investigated to wireless control and optimize position and time in stepper motors. The core impression to build a robust controller is to use a model reference control system. Furthermore, simulations are implemented to control stepper motor position and time in two cases: first, when the wireless network without any delay and packet dropout. Second, uncertain equations when the wireless network with time delays and packet dropout. Simulation results demonstrate that proposed controller has achieved and enhanced the performance in tracking and robustness.
{"title":"Wireless stepper motor control and optimization based on robust control theory","authors":"Waleed Al-Azzawi","doi":"10.11591/IJRA.V10I2.PP144-148","DOIUrl":"https://doi.org/10.11591/IJRA.V10I2.PP144-148","url":null,"abstract":"Stepper motors are broadly utilized in actual systems, which are marked by non-linear parameters such as internal, external noises and uncertainties from wireless network. As well, a suitable controller is required when the problem is to track the target signal. In this paper, robust controller based on model reference are investigated to wireless control and optimize position and time in stepper motors. The core impression to build a robust controller is to use a model reference control system. Furthermore, simulations are implemented to control stepper motor position and time in two cases: first, when the wireless network without any delay and packet dropout. Second, uncertain equations when the wireless network with time delays and packet dropout. Simulation results demonstrate that proposed controller has achieved and enhanced the performance in tracking and robustness.","PeriodicalId":73286,"journal":{"name":"IEEE International Conference on Robotics and Automation : ICRA : [proceedings]. IEEE International Conference on Robotics and Automation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49548972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.11591/IJRA.V10I2.PP114-122
K. Manjunath, Yogeen S. Honnavar, Rakesh Pritmani, K. Sethuraman
The objective of this work is to develop methodologies to detect, and report the noncompliant images with respect to indian space research organisation (ISRO) recruitment requirements. The recruitment software hosted at U. R. rao satellite centre (URSC) is responsible for handling recruitment activities of ISRO. Large number of online applications are received for each post advertised. In many cases, it is observed that the candidates are uploading either wrong or non-compliant images of the required documents. By non-compliant images, we mean images which do not have faces or there is not enough clarity in the faces present in the images uploaded. In this work, we attempt to address two specific problems namely: 1) To recognise image uploaded to recruitment portal contains a human face or not. This is addressed using a face detection algorithm. 2) To check whether images uploaded by two or more applications are same or not. This is achieved by using machine learning (ML) algorithms to generate similarity score between two images, and then identify the duplicate images. Screening of valid applications becomes very challenging as the verification of such images using a manual process is very time consuming and requires large human efforts. Hence, we propose novel ML techniques to determine duplicate and non-face images in the applications received by the recruitment portal.
{"title":"Detection of duplicate and non-face images in the eRecruitment applications using machine learning techniques","authors":"K. Manjunath, Yogeen S. Honnavar, Rakesh Pritmani, K. Sethuraman","doi":"10.11591/IJRA.V10I2.PP114-122","DOIUrl":"https://doi.org/10.11591/IJRA.V10I2.PP114-122","url":null,"abstract":"The objective of this work is to develop methodologies to detect, and report the noncompliant images with respect to indian space research organisation (ISRO) recruitment requirements. The recruitment software hosted at U. R. rao satellite centre (URSC) is responsible for handling recruitment activities of ISRO. Large number of online applications are received for each post advertised. In many cases, it is observed that the candidates are uploading either wrong or non-compliant images of the required documents. By non-compliant images, we mean images which do not have faces or there is not enough clarity in the faces present in the images uploaded. In this work, we attempt to address two specific problems namely: 1) To recognise image uploaded to recruitment portal contains a human face or not. This is addressed using a face detection algorithm. 2) To check whether images uploaded by two or more applications are same or not. This is achieved by using machine learning (ML) algorithms to generate similarity score between two images, and then identify the duplicate images. Screening of valid applications becomes very challenging as the verification of such images using a manual process is very time consuming and requires large human efforts. Hence, we propose novel ML techniques to determine duplicate and non-face images in the applications received by the recruitment portal.","PeriodicalId":73286,"journal":{"name":"IEEE International Conference on Robotics and Automation : ICRA : [proceedings]. IEEE International Conference on Robotics and Automation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41968423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.11591/IJRA.V10I2.PP91-103
Maincer Dihya, M. Moufid, Boudjedir Chemseddine, Bounabi Moussaab
Fault detection in robotic manipulators is necessary for their monitoring and represents an effective support to use them as independent systems. This present study investigates an enhanced method for representation of the faultless system behavior in a robot manipulator based on a multi-layer perceptron (MLP) neural network learning model which produces the same behavior as the real dynamic manipulator. The study was based on generation of residue by contrasting the actual output of the manipulator with those of the neural network; Then, a time delay control (TDC) is applied to compensate the fault, in which a typical sliding mode command is used to delete the time delay estimate produced by the belated signal in order to obtain strong performances. The results of the simulations performed on a model of the SCARA arm manipulator, showed a good trajectory tracking and fast convergence speed in the presence of faults on the sensors. In addition, the command is completely model independent, for both TDC and MLP neural network, which represents a major advantage of the proposed command.
{"title":"Switched time delay control based on neural network for fault detection and compensation in robot","authors":"Maincer Dihya, M. Moufid, Boudjedir Chemseddine, Bounabi Moussaab","doi":"10.11591/IJRA.V10I2.PP91-103","DOIUrl":"https://doi.org/10.11591/IJRA.V10I2.PP91-103","url":null,"abstract":"Fault detection in robotic manipulators is necessary for their monitoring and represents an effective support to use them as independent systems. This present study investigates an enhanced method for representation of the faultless system behavior in a robot manipulator based on a multi-layer perceptron (MLP) neural network learning model which produces the same behavior as the real dynamic manipulator. The study was based on generation of residue by contrasting the actual output of the manipulator with those of the neural network; Then, a time delay control (TDC) is applied to compensate the fault, in which a typical sliding mode command is used to delete the time delay estimate produced by the belated signal in order to obtain strong performances. The results of the simulations performed on a model of the SCARA arm manipulator, showed a good trajectory tracking and fast convergence speed in the presence of faults on the sensors. In addition, the command is completely model independent, for both TDC and MLP neural network, which represents a major advantage of the proposed command.","PeriodicalId":73286,"journal":{"name":"IEEE International Conference on Robotics and Automation : ICRA : [proceedings]. IEEE International Conference on Robotics and Automation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46031245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.11591/IJRA.V10I2.PP123-132
Karim H. Erian, Pedro Regalado, J. Conrad
This paper discusses a novel algorithm for solving a missing data problem in the machine learning pre-processing stage. A model built to help lenders evaluate home loans based on numerous factors by learning from available user data, is adopted in this paper as an example. If one of the factors is missing for a person in the dataset, the currently used methods delete the whole entry therefore reducing the size of the dataset and affecting the machine learning model accuracy. The novel algorithm aims to avoid losing entries for missing factors by breaking the dataset into multiple subsets, building a different machine learning model for each subset, then combining the models into one machine learning model. In this manner, the model makes use of all available data and only neglects the missing values. Overall, the new algorithm improved the prediction accuracy by 5% from 93% accuracy to 98% in the home loan example.
{"title":"Missing data handling for machine learning models","authors":"Karim H. Erian, Pedro Regalado, J. Conrad","doi":"10.11591/IJRA.V10I2.PP123-132","DOIUrl":"https://doi.org/10.11591/IJRA.V10I2.PP123-132","url":null,"abstract":"This paper discusses a novel algorithm for solving a missing data problem in the machine learning pre-processing stage. A model built to help lenders evaluate home loans based on numerous factors by learning from available user data, is adopted in this paper as an example. If one of the factors is missing for a person in the dataset, the currently used methods delete the whole entry therefore reducing the size of the dataset and affecting the machine learning model accuracy. The novel algorithm aims to avoid losing entries for missing factors by breaking the dataset into multiple subsets, building a different machine learning model for each subset, then combining the models into one machine learning model. In this manner, the model makes use of all available data and only neglects the missing values. Overall, the new algorithm improved the prediction accuracy by 5% from 93% accuracy to 98% in the home loan example.","PeriodicalId":73286,"journal":{"name":"IEEE International Conference on Robotics and Automation : ICRA : [proceedings]. IEEE International Conference on Robotics and Automation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44132991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.11591/IJRA.V10I2.PP104-113
Nira Mawangi Sarif, R. Ngadengon, H. A. Kadir, M. H. A. Jalil, K. Abidi
Autonomous underwater vehicle (AUV) are underwater robotic devices intended to explore hostiles territories in underwater domain. AUVs research gaining popularity among underwater research community because of its extensive applications and challenges to overcome unpredictable ocean behavior. The aim of this paper is to design discrete time terminal sliding mode control (DTSMC) reaching law-based employed to NPS AUV II purposely to improve the dynamic response of the closed loop system. This is accomplished by introducing a nonlinear component to sliding surface design in which the system state accelerated, and chattering effect is suppressed. The nonlinear component consist of fractional power is to ensure steeper slope of the sliding surface in the vicinity of the equilibrium point which lead to quicker convergence speed. Thus, the chattering effect in the control action suppressed as the convergence of the system state accelerated. The stability of the control system is proven by using Sarpturk analysis and the performance of the DTSMC is demonstrated through simulation study. The performance of DTSMC is benchmarked with DSMC and PID controller
{"title":"A discrete-time terminal sliding mode controller design for an autonomous underwater vehicle","authors":"Nira Mawangi Sarif, R. Ngadengon, H. A. Kadir, M. H. A. Jalil, K. Abidi","doi":"10.11591/IJRA.V10I2.PP104-113","DOIUrl":"https://doi.org/10.11591/IJRA.V10I2.PP104-113","url":null,"abstract":"Autonomous underwater vehicle (AUV) are underwater robotic devices intended to explore hostiles territories in underwater domain. AUVs research gaining popularity among underwater research community because of its extensive applications and challenges to overcome unpredictable ocean behavior. The aim of this paper is to design discrete time terminal sliding mode control (DTSMC) reaching law-based employed to NPS AUV II purposely to improve the dynamic response of the closed loop system. This is accomplished by introducing a nonlinear component to sliding surface design in which the system state accelerated, and chattering effect is suppressed. The nonlinear component consist of fractional power is to ensure steeper slope of the sliding surface in the vicinity of the equilibrium point which lead to quicker convergence speed. Thus, the chattering effect in the control action suppressed as the convergence of the system state accelerated. The stability of the control system is proven by using Sarpturk analysis and the performance of the DTSMC is demonstrated through simulation study. The performance of DTSMC is benchmarked with DSMC and PID controller","PeriodicalId":73286,"journal":{"name":"IEEE International Conference on Robotics and Automation : ICRA : [proceedings]. IEEE International Conference on Robotics and Automation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47417411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.11591/IJRA.V10I2.PP75-90
Ahmed M. Hassan, R. M. Asif, A. Rehman, Zuhaib Nishtar, Mohammed K. A. Kaabar, Khan Afsar
Water plays a significant role among other existing natural resources. The daily demand for water supplies is increasingly on the rise as the population grows. To minimize the consumption of water in irrigation, several proposals were suggested. The currently existing system known as the automated irrigation system for effective water resource use with the prediction of the weather (AISWP) functions with a single farm that lacks the reliability in the precision of weather forecasting. So, a robot-based irrigation system has been proposed to improve the performance of the system. To minimize the water usage for crops, an automated irrigation system has been developed which irrigates the field in acres. An additional characteristic of the system has also been given for the soil pH measurement to allow the use of fertilizers accordingly. The solar-powered robot is managed wirelessly by a designated application. The robot is attached with various sensors and with a highresolution camera that tests crop conditions and senses the soil state. The application has been created to provide information about the soil’s condition such as temperature level, humidity level, water level, and level of nutrients to the PC/Laptop with the real-time values via the GSM module.
{"title":"Design and development of an Irrigation Mobile Robot","authors":"Ahmed M. Hassan, R. M. Asif, A. Rehman, Zuhaib Nishtar, Mohammed K. A. Kaabar, Khan Afsar","doi":"10.11591/IJRA.V10I2.PP75-90","DOIUrl":"https://doi.org/10.11591/IJRA.V10I2.PP75-90","url":null,"abstract":"Water plays a significant role among other existing natural resources. The daily demand for water supplies is increasingly on the rise as the population grows. To minimize the consumption of water in irrigation, several proposals were suggested. The currently existing system known as the automated irrigation system for effective water resource use with the prediction of the weather (AISWP) functions with a single farm that lacks the reliability in the precision of weather forecasting. So, a robot-based irrigation system has been proposed to improve the performance of the system. To minimize the water usage for crops, an automated irrigation system has been developed which irrigates the field in acres. An additional characteristic of the system has also been given for the soil pH measurement to allow the use of fertilizers accordingly. The solar-powered robot is managed wirelessly by a designated application. The robot is attached with various sensors and with a highresolution camera that tests crop conditions and senses the soil state. The application has been created to provide information about the soil’s condition such as temperature level, humidity level, water level, and level of nutrients to the PC/Laptop with the real-time values via the GSM module.","PeriodicalId":73286,"journal":{"name":"IEEE International Conference on Robotics and Automation : ICRA : [proceedings]. IEEE International Conference on Robotics and Automation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49220594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01Epub Date: 2021-10-18DOI: 10.1109/icra48506.2021.9562040
Makoto Jinno, Gang Li, Niravkumar Patel, Iulian Iordachita
Retinal surgeons are required to manipulate multiple surgical instruments in a confined intraocular space, while the instruments are constrained at the small incisions made on the sclera. Furthermore, physiological hand tremor can affect the precision of the instrument motion. The Steady-Hand Eye Robot (SHER), developed in our previous study, enables tremor-free tool manipulation by employing a cooperative control scheme whereby the surgeon and robot can co-manipulate the surgical instruments. Although SHER enables precise and tremor-free manipulation of surgical tools, its straight and rigid structure imposes certain limitations, as it can only approach a target on the retina from one direction. As a result, the instrument could potentially collide with the eye lens when attempting to access the anterior portion of the retina. In addition, it can be difficult to approach a target on the retina from a suitable direction when accessing its anterior portion for procedures such as vein cannulation or membrane peeling. Snake-like robots offer greater dexterity and allow access to a target on the retina from suitable directions, depending on the clinical task at hand. In this study, we present an integrated, high-dexterity, cooperative robotic assistant for intraocular micromanipulation. This robotic assistant comprises an improved integrated robotic intraocular snake (I2RIS) with a user interface (a tactile switch or joystick unit) for the manipulation of the snake-like distal end and the SHER, with a detachable end-effector to which the I2RIS can be attached. The integrated system was evaluated through a set of experiments wherein subjects were requested to touch or insert into randomly-assigned targets. The results indicate that the high-dexterity robotic assistant can touch or insert the tip into the same target from multiple directions, with no significant increase in task completion time for either user interface.
{"title":"An Integrated High-dexterity Cooperative Robotic Assistant for Intraocular Micromanipulation.","authors":"Makoto Jinno, Gang Li, Niravkumar Patel, Iulian Iordachita","doi":"10.1109/icra48506.2021.9562040","DOIUrl":"https://doi.org/10.1109/icra48506.2021.9562040","url":null,"abstract":"<p><p>Retinal surgeons are required to manipulate multiple surgical instruments in a confined intraocular space, while the instruments are constrained at the small incisions made on the sclera. Furthermore, physiological hand tremor can affect the precision of the instrument motion. The Steady-Hand Eye Robot (SHER), developed in our previous study, enables tremor-free tool manipulation by employing a cooperative control scheme whereby the surgeon and robot can co-manipulate the surgical instruments. Although SHER enables precise and tremor-free manipulation of surgical tools, its straight and rigid structure imposes certain limitations, as it can only approach a target on the retina from one direction. As a result, the instrument could potentially collide with the eye lens when attempting to access the anterior portion of the retina. In addition, it can be difficult to approach a target on the retina from a suitable direction when accessing its anterior portion for procedures such as vein cannulation or membrane peeling. Snake-like robots offer greater dexterity and allow access to a target on the retina from suitable directions, depending on the clinical task at hand. In this study, we present an integrated, high-dexterity, cooperative robotic assistant for intraocular micromanipulation. This robotic assistant comprises an improved integrated robotic intraocular snake (I2RIS) with a user interface (a tactile switch or joystick unit) for the manipulation of the snake-like distal end and the SHER, with a detachable end-effector to which the I2RIS can be attached. The integrated system was evaluated through a set of experiments wherein subjects were requested to touch or insert into randomly-assigned targets. The results indicate that the high-dexterity robotic assistant can touch or insert the tip into the same target from multiple directions, with no significant increase in task completion time for either user interface.</p>","PeriodicalId":73286,"journal":{"name":"IEEE International Conference on Robotics and Automation : ICRA : [proceedings]. IEEE International Conference on Robotics and Automation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8552997/pdf/nihms-1684315.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39579549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.11591/IJRA.V10I2.PP133-143
Yunfei Fang, Shengzhi Du, L. Boubchir, Karim D Djouani
Small unmanned aerial vehicles applications had erupted in many fields including conservation management. Automatic object detection methods for such aerial imagery were in high demand to facilitate more efficient and economical wildlife management and research. This paper aimed to detect hoofed animals in aerial images taken from a quad-rotor in Southern Africa. Objects captured in this way were small both in absolute pixels and from an object-to-image ratio point of view, which were not perfectly suit for general purposed object detectors. We proposed a method based on the iconic Faster region-based convolutional neural networks (R-CNN) framework with atrous convolution layers in order to retain the spatial resolution of the feature map to detect small objects. A good choice of anchors was of prime importance in detecting small objects. The performance of the proposed Faster R-CNN with atrous convolutional filters in the backbone network was proven to be outstanding in our scenario by comparing to other object detection architectures.
{"title":"Detecting African hoofed animals in aerial imagery using convolutional neural network","authors":"Yunfei Fang, Shengzhi Du, L. Boubchir, Karim D Djouani","doi":"10.11591/IJRA.V10I2.PP133-143","DOIUrl":"https://doi.org/10.11591/IJRA.V10I2.PP133-143","url":null,"abstract":"Small unmanned aerial vehicles applications had erupted in many fields including conservation management. Automatic object detection methods for such aerial imagery were in high demand to facilitate more efficient and economical wildlife management and research. This paper aimed to detect hoofed animals in aerial images taken from a quad-rotor in Southern Africa. Objects captured in this way were small both in absolute pixels and from an object-to-image ratio point of view, which were not perfectly suit for general purposed object detectors. We proposed a method based on the iconic Faster region-based convolutional neural networks (R-CNN) framework with atrous convolution layers in order to retain the spatial resolution of the feature map to detect small objects. A good choice of anchors was of prime importance in detecting small objects. The performance of the proposed Faster R-CNN with atrous convolutional filters in the backbone network was proven to be outstanding in our scenario by comparing to other object detection architectures.","PeriodicalId":73286,"journal":{"name":"IEEE International Conference on Robotics and Automation : ICRA : [proceedings]. IEEE International Conference on Robotics and Automation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48708605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号