Pub Date : 2017-07-10DOI: 10.1109/ICAR.2017.8023656
S. Kleinschmidt, Bernardo Wagner
In this paper, an approach for identifying corresponding image features across different imaging modalities is presented. The method includes spatial alignment of sensor images on short and long distance as well as a probabilistic fusion approach for combining multiple unimodal to multimodal image features. An experimental statistical comparison of uni- and multimodal image features is performed using RGB, IR and thermal cameras. Therefore, the sensors are mounted on an Ackermann steering platform in a typical industrial environment. The multimodal features are examined regarding repetitive characteristics, quantity and spatial distribution.
{"title":"Probabilistic fusion and analysis of multimodal image features","authors":"S. Kleinschmidt, Bernardo Wagner","doi":"10.1109/ICAR.2017.8023656","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023656","url":null,"abstract":"In this paper, an approach for identifying corresponding image features across different imaging modalities is presented. The method includes spatial alignment of sensor images on short and long distance as well as a probabilistic fusion approach for combining multiple unimodal to multimodal image features. An experimental statistical comparison of uni- and multimodal image features is performed using RGB, IR and thermal cameras. Therefore, the sensors are mounted on an Ackermann steering platform in a typical industrial environment. The multimodal features are examined regarding repetitive characteristics, quantity and spatial distribution.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128274310","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 : 2017-07-10DOI: 10.1109/ICAR.2017.8023521
Xiang Li, Xing Su, Yunhui Liu
While robot manipulators have been widely applied in manufacturing and industry, most applications are limited to rigid objects. Increasing demands for manipulating soft objects have been reflected in the emerging 3C manufacturing, such as the soldering of flexible PCBs. Because of the property of deformation, soldering the flexible PCB cannot be performed with conventional robotic manipulation techniques. In this paper, an adaptive region controller is proposed to deal with the deformation of flexible PCBs, where the control objective is specified as a region attached to the flexible PCB. The proposed controller enables an additional assistive arm to reach the region and contact and fix the PCB, which thus eliminates the deformation. A coordination scheme is also developed to activate the soldering end effector after the deformation is stabilized. The stability of the closed-loop system is rigorously proved with Lyapunov methods, and experimental results are presented to illustrate the performance of the proposed controller.
{"title":"Adaptive region control for robotic soldering of flexible PCBs","authors":"Xiang Li, Xing Su, Yunhui Liu","doi":"10.1109/ICAR.2017.8023521","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023521","url":null,"abstract":"While robot manipulators have been widely applied in manufacturing and industry, most applications are limited to rigid objects. Increasing demands for manipulating soft objects have been reflected in the emerging 3C manufacturing, such as the soldering of flexible PCBs. Because of the property of deformation, soldering the flexible PCB cannot be performed with conventional robotic manipulation techniques. In this paper, an adaptive region controller is proposed to deal with the deformation of flexible PCBs, where the control objective is specified as a region attached to the flexible PCB. The proposed controller enables an additional assistive arm to reach the region and contact and fix the PCB, which thus eliminates the deformation. A coordination scheme is also developed to activate the soldering end effector after the deformation is stabilized. The stability of the closed-loop system is rigorously proved with Lyapunov methods, and experimental results are presented to illustrate the performance of the proposed controller.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127342226","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 : 2017-07-10DOI: 10.1109/ICAR.2017.8023665
Zhiwei Liu, Fan Yang, Z. Dong, X. Ye
Nowadays a great amount of space debris threat the safety of space activities, so the space debris removal becomes a hot research field. In particular, on the base of space mechanical arm technology, using mechanical arm to remove space debris proves feasible in the implementation. Traditional space mechanical arms are rigid arms, and in consideration of the uncontrolled momentum of rigid arm, this paper intend to use flexible arm to capture space debris, which can achieve the purpose of stably controlling collision momentum. According to the whole task process that flexible arm captures space debris, this paper built a model of flexible arm and space debris, and establishes their mathematics models. The simulation system is constructed based on the models, and use I/O Completion Port (IOCP) model to ensure the real-time transportation of data produced in collision. Finally, this paper designs a simulation application case to verify the ability of simulation system to support space missions.
{"title":"The design of space debris removed simulation system based on flexible arm","authors":"Zhiwei Liu, Fan Yang, Z. Dong, X. Ye","doi":"10.1109/ICAR.2017.8023665","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023665","url":null,"abstract":"Nowadays a great amount of space debris threat the safety of space activities, so the space debris removal becomes a hot research field. In particular, on the base of space mechanical arm technology, using mechanical arm to remove space debris proves feasible in the implementation. Traditional space mechanical arms are rigid arms, and in consideration of the uncontrolled momentum of rigid arm, this paper intend to use flexible arm to capture space debris, which can achieve the purpose of stably controlling collision momentum. According to the whole task process that flexible arm captures space debris, this paper built a model of flexible arm and space debris, and establishes their mathematics models. The simulation system is constructed based on the models, and use I/O Completion Port (IOCP) model to ensure the real-time transportation of data produced in collision. Finally, this paper designs a simulation application case to verify the ability of simulation system to support space missions.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134060552","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 : 2017-07-10DOI: 10.1109/ICAR.2017.8023488
D. Differt
The majority of approaches for rotationally aligning panoramic images use feature-based methods which extract and match visual clues in both images and analytically determine their rotational offset. However, these methods can be computationally expensive and might suffer from motion blur or images taken in structureless environments (e.g. forests). An alternative approach is the visual compass, a method which simulates a wide range of possible rotational offsets and searches for the best match. While this approach has been successfully implemented for rotations around a single axis, the increasing computation time for 3D rotations limits the usability for real-time applications. It has been suggested to use real spherical harmonics (RSH) to represent panoramic images, to calculate rotations in frequency domain using sparse matrix-vector multiplications. In this paper, we present strategies which are crucial to implement a real-time visual 3D compass using RSH. We provide a software implementation of the visual 3D compass and analyze the effect of increasing rotational misalignment between pairs of panoramic images. Furthermore, we show that the visual 3D compass can be used on low-cost hardware in real-time.
{"title":"Real-time rotational image registration","authors":"D. Differt","doi":"10.1109/ICAR.2017.8023488","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023488","url":null,"abstract":"The majority of approaches for rotationally aligning panoramic images use feature-based methods which extract and match visual clues in both images and analytically determine their rotational offset. However, these methods can be computationally expensive and might suffer from motion blur or images taken in structureless environments (e.g. forests). An alternative approach is the visual compass, a method which simulates a wide range of possible rotational offsets and searches for the best match. While this approach has been successfully implemented for rotations around a single axis, the increasing computation time for 3D rotations limits the usability for real-time applications. It has been suggested to use real spherical harmonics (RSH) to represent panoramic images, to calculate rotations in frequency domain using sparse matrix-vector multiplications. In this paper, we present strategies which are crucial to implement a real-time visual 3D compass using RSH. We provide a software implementation of the visual 3D compass and analyze the effect of increasing rotational misalignment between pairs of panoramic images. Furthermore, we show that the visual 3D compass can be used on low-cost hardware in real-time.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128791752","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 : 2017-07-10DOI: 10.1109/ICAR.2017.8023642
Ajit R. Deshpande, Z. Tse, Hongliang Ren
The field of soft robotics has a wide array of applications, particularly in human-robotic interaction, from medical devices to assembly technology. In this paper, we introduce a novel design for a soft bi-directional pneumatic actuator inspired by the principles of origami. The actuator integrates a variable stiffness application using a layer jamming mechanism (LJM). LJM utilizes the effects of negative pressure on thin layers of material, providing rigidity. Incorporated into an origami bellows structure, the negative pressure causes both contractile action and stiffness, while extensive action is caused by an internal pneumatic chamber, allowing for contractile and extensive force application. Furthermore, the variable stiffness integration improved tensile force application threefold, resistance to outside linear force tenfold, and doubled sheer force resistance. The proposed origami-inspired bi-directional soft pneumatic soft actuator has immense potential to be implemented in complex biomedical applications in the near future.
{"title":"Origami-inspired bi-directional soft pneumatic actuator with integrated variable stiffness mechanism","authors":"Ajit R. Deshpande, Z. Tse, Hongliang Ren","doi":"10.1109/ICAR.2017.8023642","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023642","url":null,"abstract":"The field of soft robotics has a wide array of applications, particularly in human-robotic interaction, from medical devices to assembly technology. In this paper, we introduce a novel design for a soft bi-directional pneumatic actuator inspired by the principles of origami. The actuator integrates a variable stiffness application using a layer jamming mechanism (LJM). LJM utilizes the effects of negative pressure on thin layers of material, providing rigidity. Incorporated into an origami bellows structure, the negative pressure causes both contractile action and stiffness, while extensive action is caused by an internal pneumatic chamber, allowing for contractile and extensive force application. Furthermore, the variable stiffness integration improved tensile force application threefold, resistance to outside linear force tenfold, and doubled sheer force resistance. The proposed origami-inspired bi-directional soft pneumatic soft actuator has immense potential to be implemented in complex biomedical applications in the near future.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125179839","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 : 2017-07-10DOI: 10.1109/ICAR.2017.8023530
Huy Dinh, Quilong Yuan, V. Iastrebov, G. Seet
Applying masking tape to a particular area is a very important step for protecting an uninvolved surface in processes like mechanical part repairing or surface protection. In the past, the task was very time-consuming and required a lot of manual works. In recent years, with some advances in the fields of automatic robotic system and computer vision, the task now can be completed with the help of an automatic taping system containing a 3D scanner, a manipulator and a rotating platform. This implementation has been proved to provide better quality and be at least twice as fast as comparing to the work done by a human operator. However, there are still some limitations of this setup. First, it is difficult for the user to monitor the taping process since the system uses the 3D scanner to reconstruct the surface model and there is no calibrated projector to overlay the manipulator's trajectory over the real surface. Second, the main user is supposed to use a computer with keyboard and mouse to identify the area for masking which requires some expert knowledge and might not be appropriate in an industrial context where people wear protective equipment such as gloves or helmet. This paper introduces the use of spatial augmented reality technology and wearable device in the semi-automatic taping robotic system and the related calibration algorithms to enhance the user experience. The framework and its components are presented, with a case study and some results.
{"title":"Augmented reality interface for taping robot","authors":"Huy Dinh, Quilong Yuan, V. Iastrebov, G. Seet","doi":"10.1109/ICAR.2017.8023530","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023530","url":null,"abstract":"Applying masking tape to a particular area is a very important step for protecting an uninvolved surface in processes like mechanical part repairing or surface protection. In the past, the task was very time-consuming and required a lot of manual works. In recent years, with some advances in the fields of automatic robotic system and computer vision, the task now can be completed with the help of an automatic taping system containing a 3D scanner, a manipulator and a rotating platform. This implementation has been proved to provide better quality and be at least twice as fast as comparing to the work done by a human operator. However, there are still some limitations of this setup. First, it is difficult for the user to monitor the taping process since the system uses the 3D scanner to reconstruct the surface model and there is no calibrated projector to overlay the manipulator's trajectory over the real surface. Second, the main user is supposed to use a computer with keyboard and mouse to identify the area for masking which requires some expert knowledge and might not be appropriate in an industrial context where people wear protective equipment such as gloves or helmet. This paper introduces the use of spatial augmented reality technology and wearable device in the semi-automatic taping robotic system and the related calibration algorithms to enhance the user experience. The framework and its components are presented, with a case study and some results.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121372673","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 : 2017-07-10DOI: 10.1109/ICAR.2017.8023501
Junghwan Lee, Heechan Shin, Sung-eui Yoon
We present a novel, data-driven kinodynamic motion planner. Our sampling-based planner is based on using a physics simulator as a black box to compute a trajectory considering dynamics, even when we cannot derive exact propagation functions. To improve its overall efficiency, we pre-compute a motion database containing different motions simulated with different controls and states defined in the local frame of a robot. We then use the motion database to efficiently estimate the simulated trajectory during iterations of our planner. When the planner requests the best control to reach a desired state from a query state, we retrieve nearby motions that are close to the query state and pick the motion that is closest to the desired state for the tree extension. To control accuracy of our planner with a high efficiency, we lazily validate retrieved motions. The pre-constructed motion database contains modular trajectories and thus can be reused for other test cases, where we have different composition of obstacles or different start/goal states.
{"title":"Data-driven kinodynamic RRT","authors":"Junghwan Lee, Heechan Shin, Sung-eui Yoon","doi":"10.1109/ICAR.2017.8023501","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023501","url":null,"abstract":"We present a novel, data-driven kinodynamic motion planner. Our sampling-based planner is based on using a physics simulator as a black box to compute a trajectory considering dynamics, even when we cannot derive exact propagation functions. To improve its overall efficiency, we pre-compute a motion database containing different motions simulated with different controls and states defined in the local frame of a robot. We then use the motion database to efficiently estimate the simulated trajectory during iterations of our planner. When the planner requests the best control to reach a desired state from a query state, we retrieve nearby motions that are close to the query state and pick the motion that is closest to the desired state for the tree extension. To control accuracy of our planner with a high efficiency, we lazily validate retrieved motions. The pre-constructed motion database contains modular trajectories and thus can be reused for other test cases, where we have different composition of obstacles or different start/goal states.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122386213","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 : 2017-07-10DOI: 10.1109/ICAR.2017.8023651
Dianle Zhou, Jinglun Zhou, Maojun Zhang, Dao Xiang, Zhiwei Zhong
With the rapid development of unmanned aerial vehicles (UAVs) technology, it is necessary to ensure the safe and stable landing on the carrier. In this paper, we present a deep learning for UAVs Landing carrier in different conditions. Firstly it analysis of different sea conditions deck motion, constructs a simulation model of the system. The waves motion, deck motion, and then to the aircraft landing motion models are simulation. Then according to a large number of previous land runway, mobile landing platform experimental data, UAV model, wind model and deck motion model build aircraft carrier simulation system. That is based on deep learning, to estimate the safety conditions of contact carrier aircraft and deck. Then, it simulate the deck in different sea conditions and wave motion under the harsh conditions of motion, to testing the deck can withstand the landing limit to make feasibility analysis. Finally, using there simulation data use for UAVs landing on river platform. Simulation results show that the sea conditions with effective longitudinal deviation and lateral deviation of the ship is the most significant. Level 4, level 5, and level 6 sea conditions idea landing condition success rate are 98%, 70.8%, 63%. And it successful uses for landing in river platform.
{"title":"Deep learning for unmanned aerial vehicles landing carrier in different conditions","authors":"Dianle Zhou, Jinglun Zhou, Maojun Zhang, Dao Xiang, Zhiwei Zhong","doi":"10.1109/ICAR.2017.8023651","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023651","url":null,"abstract":"With the rapid development of unmanned aerial vehicles (UAVs) technology, it is necessary to ensure the safe and stable landing on the carrier. In this paper, we present a deep learning for UAVs Landing carrier in different conditions. Firstly it analysis of different sea conditions deck motion, constructs a simulation model of the system. The waves motion, deck motion, and then to the aircraft landing motion models are simulation. Then according to a large number of previous land runway, mobile landing platform experimental data, UAV model, wind model and deck motion model build aircraft carrier simulation system. That is based on deep learning, to estimate the safety conditions of contact carrier aircraft and deck. Then, it simulate the deck in different sea conditions and wave motion under the harsh conditions of motion, to testing the deck can withstand the landing limit to make feasibility analysis. Finally, using there simulation data use for UAVs landing on river platform. Simulation results show that the sea conditions with effective longitudinal deviation and lateral deviation of the ship is the most significant. Level 4, level 5, and level 6 sea conditions idea landing condition success rate are 98%, 70.8%, 63%. And it successful uses for landing in river platform.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122674834","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 : 2017-07-10DOI: 10.1109/ICAR.2017.8023631
R. Jamisola, Carlos Mastalli
Biological limbs normally come in pairs: mammals have four, insects have six, arachnids have eight, and centipedes have one pair of legs per body segment. This work attempts to interpret the biological method of controlling paired legs (here treated as dual-arms) in opposite and adjacent pairs to achieve a holistic controller of a large four-legged animal (here treated as a combined four-arm robot). A modular relative Jacobian controls a dual-arm as a single manipulator with a single end-effector, and is expressed in terms of the Jacobians of each of the stand-alone manipulators. In this work, the two opposite pairs of legs are treated as single end-effector dual-arms, and then these two dual-arms are combined together to form a single end-effector four-arm robot. The four-arm controller uses the same principle as a single end-effector controller of a dual-arm, and thus results into a single end-effector controller of a four-arm. A modular relative Jacobian of the four arms is derived. Gazebo simulation results are shown for two gait patterns of a four-legged animal, namely, pacing and trotting.
{"title":"Bio-inspired holistic control through modular relative Jacobian for combined four-arm robots","authors":"R. Jamisola, Carlos Mastalli","doi":"10.1109/ICAR.2017.8023631","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023631","url":null,"abstract":"Biological limbs normally come in pairs: mammals have four, insects have six, arachnids have eight, and centipedes have one pair of legs per body segment. This work attempts to interpret the biological method of controlling paired legs (here treated as dual-arms) in opposite and adjacent pairs to achieve a holistic controller of a large four-legged animal (here treated as a combined four-arm robot). A modular relative Jacobian controls a dual-arm as a single manipulator with a single end-effector, and is expressed in terms of the Jacobians of each of the stand-alone manipulators. In this work, the two opposite pairs of legs are treated as single end-effector dual-arms, and then these two dual-arms are combined together to form a single end-effector four-arm robot. The four-arm controller uses the same principle as a single end-effector controller of a dual-arm, and thus results into a single end-effector controller of a four-arm. A modular relative Jacobian of the four arms is derived. Gazebo simulation results are shown for two gait patterns of a four-legged animal, namely, pacing and trotting.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124509325","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 : 2017-07-10DOI: 10.1109/ICAR.2017.8023504
Prarinya Siritanawan, Moratuwage Diluka Prasanjith, Danwei W. Wang
In this paper, we propose a novel 3D feature point detection algorithm using Multiresolution Surface Variation (MSV). The proposed algorithm is used to extract 3D features from a cluttered, unstructured environment for use in realtime Simultaneous Localisation and Mapping (SLAM) algorithms running on a mobile robot. The salient feature of the proposed method is that, it can not only handle dense, uniform 3D point clouds (such as those obtained from Kinect or rotating 2D Lidar), but also (perhaps more importantly) handle sparse, non-uniform 3D point clouds (obtained from sensors such as 3D Lidar) and produce robust, repeatable key points that are specifically suitable for SLAM. The efficacy of the proposed method is evaluated using a dataset collected from a mobile robot with a 3D Velodyne Lidar (VLP-16) mounted on top.
{"title":"3D feature points detection on sparse and non-uniform pointcloud for SLAM","authors":"Prarinya Siritanawan, Moratuwage Diluka Prasanjith, Danwei W. Wang","doi":"10.1109/ICAR.2017.8023504","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023504","url":null,"abstract":"In this paper, we propose a novel 3D feature point detection algorithm using Multiresolution Surface Variation (MSV). The proposed algorithm is used to extract 3D features from a cluttered, unstructured environment for use in realtime Simultaneous Localisation and Mapping (SLAM) algorithms running on a mobile robot. The salient feature of the proposed method is that, it can not only handle dense, uniform 3D point clouds (such as those obtained from Kinect or rotating 2D Lidar), but also (perhaps more importantly) handle sparse, non-uniform 3D point clouds (obtained from sensors such as 3D Lidar) and produce robust, repeatable key points that are specifically suitable for SLAM. The efficacy of the proposed method is evaluated using a dataset collected from a mobile robot with a 3D Velodyne Lidar (VLP-16) mounted on top.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114061392","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：