Pub Date : 1900-01-01DOI: 10.5220/0002209102380243
Christoph Walter, F. Penzlin, N. Elkmann
Artifacts like motion blur are a common problem for vision systems on mobile robots, especially when operating under low light conditions or when using high-resolution sensors. In this contribution we present a scheme for estimating the degree of motion artifacts, especially motion blur, present in a stream of individual camera images. A single quality estimate is derived per frame using data from an inertial measurement unit. Considering limited image processing capacity of resource-constrained mobile robots, we show a number of data processing strategies that are based upon the idea of congestion control by adaptive image rejection.
{"title":"Scheme for Evaluation and Reduction of Motion Artifacts in Mobile Vision Systems","authors":"Christoph Walter, F. Penzlin, N. Elkmann","doi":"10.5220/0002209102380243","DOIUrl":"https://doi.org/10.5220/0002209102380243","url":null,"abstract":"Artifacts like motion blur are a common problem for vision systems on mobile robots, especially when operating under low light conditions or when using high-resolution sensors. In this contribution we present a scheme for estimating the degree of motion artifacts, especially motion blur, present in a stream of individual camera images. A single quality estimate is derived per frame using data from an inertial measurement unit. Considering limited image processing capacity of resource-constrained mobile robots, we show a number of data processing strategies that are based upon the idea of congestion control by adaptive image rejection.","PeriodicalId":302311,"journal":{"name":"ICINCO-RA","volume":"16 Suppl5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130180398","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 : 1900-01-01DOI: 10.5220/0001633401170124
Madjid Boudaba, A. Casals
Finding the global shape of a grasped object directly from touch is time consuming and not highly reliable. This paper describes the relationship between visual features and grasp planning, and correlates visual and tactile information for a better description of the object’s shape and grasping points determination. The grasping process proposed is experimented with a three fingered robotic hand.
{"title":"Grasp configuration matching - using visual and tactile sensor information","authors":"Madjid Boudaba, A. Casals","doi":"10.5220/0001633401170124","DOIUrl":"https://doi.org/10.5220/0001633401170124","url":null,"abstract":"Finding the global shape of a grasped object directly from touch is time consuming and not highly reliable. This paper describes the relationship between visual features and grasp planning, and correlates visual and tactile information for a better description of the object’s shape and grasping points determination. The grasping process proposed is experimented with a three fingered robotic hand.","PeriodicalId":302311,"journal":{"name":"ICINCO-RA","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131617753","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 : 1900-01-01DOI: 10.5220/0001639000650069
L. Jaulin, F. Dabe, A. Bertholom, M. Legris
This paper proposes a set approach for the simultaneous localization and mapping (SLAM) in a submarine context. It shows that this problem can be cast into a constraint satisfaction problem which can be solve efficiently using interval analysis and propagation algorithms. The efficiency of the resulting propagation method is illustrated on the localization of submarine robot, named Redermor. The experiments have been collected by the GESMA (Groupe d’Etude Sous-Marine de l’Atlantique) in the Douarnenez Bay, in Brittany.
本文提出了一套潜艇环境下的同时定位与制图方法。结果表明，该问题可转化为约束满足问题，并可通过区间分析和传播算法有效地求解。以水下机器人Redermor的定位为例，说明了所得到的传播方法的有效性。实验由GESMA (Groupe d 'Etude Sous-Marine de l ' atlanantique)在布列塔尼的douarneez湾收集。
{"title":"A set approach to the simultaneous localization and map building - application to underwater robots","authors":"L. Jaulin, F. Dabe, A. Bertholom, M. Legris","doi":"10.5220/0001639000650069","DOIUrl":"https://doi.org/10.5220/0001639000650069","url":null,"abstract":"This paper proposes a set approach for the simultaneous localization and mapping (SLAM) in a submarine context. It shows that this problem can be cast into a constraint satisfaction problem which can be solve efficiently using interval analysis and propagation algorithms. The efficiency of the resulting propagation method is illustrated on the localization of submarine robot, named Redermor. The experiments have been collected by the GESMA (Groupe d’Etude Sous-Marine de l’Atlantique) in the Douarnenez Bay, in Brittany.","PeriodicalId":302311,"journal":{"name":"ICINCO-RA","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127575346","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 : 1900-01-01DOI: 10.5220/0001201802100216
J. Figueiredo, J. S. D. Costa
A two level hierarchical control strategy is developed over a network of distributed systems. This paper shows the great potential of a control strategy over two layers distributed local controls which are connected with an intelligent centralized control, which has a global view over the system, and permits an actualization of the local references, knowing the complete state of the entire system The tested prototype worked perfectly showing the huge potential of communication systems between distributed processes. These communication systems allow intelligent centralized algorithms to manage decision making problems in real-time environments. The system presented in this paper combines several technologies (local PLCs, SCADA systems and network communications) to reach the goal of efficient management of distributed processes.
{"title":"Two layer control strategy applied to building automation","authors":"J. Figueiredo, J. S. D. Costa","doi":"10.5220/0001201802100216","DOIUrl":"https://doi.org/10.5220/0001201802100216","url":null,"abstract":"A two level hierarchical control strategy is developed over a network of distributed systems. This paper shows the great potential of a control strategy over two layers distributed local controls which are connected with an intelligent centralized control, which has a global view over the system, and permits an actualization of the local references, knowing the complete state of the entire system The tested prototype worked perfectly showing the huge potential of communication systems between distributed processes. These communication systems allow intelligent centralized algorithms to manage decision making problems in real-time environments. The system presented in this paper combines several technologies (local PLCs, SCADA systems and network communications) to reach the goal of efficient management of distributed processes.","PeriodicalId":302311,"journal":{"name":"ICINCO-RA","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127632045","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 : 1900-01-01DOI: 10.5220/0001218502290234
Raquel Ros Espinoza, R. L. D. Mántaras, J. P. Gruart
The problem that a robot navigates autonomously through its environment, builds its own map and localizes itself in the map, is still an open problem. It is known as the SLAM (Simultaneous Localization and Map Building) problem. This problem is made even more difficult when we have several robots cooperating to build a common map of an unknown environment, due to the problem of map integration of several submaps built independently by each robot, and with a high degree of error, making the map matching specially difficult. Most of the approaches to solve map building problems are quantitative, resulting in a great computational cost and a low level of abstraction. In order to fulfil these drawbacks qualitative models have been recently used. However, qualitative models are non deterministic. Therefore, the solution recently adopted has been to mix both qualitative and quantitative models to represent the environment and build maps. However, no reasoning process has been used to deal with the information stored in maps up to now, therefore maps are only static storage of landmarks. In this paper we propose a novel method for cooperative map building based on hybrid (qualitative+quantitative) representation which includes also a reasoning process. Distinctive landmarks acquisition for map representation is provided by the cognitive vision and infrared modules which compute differences from the expected data according to the current map and the actual information perceived. We will store in the map the relative orientation information of the landmarks which appear in the environment, after a qualitative reasoning process, therefore the map will be independent of the point of view of the robot. Map integration will then be achieved by localizing each robot in the maps made by the other robots, through a process of pattern matching of the hybrid maps elaborated by each robot, resulting in an integrated map which all robots share, and which is the main objective of this work. This map building method is currently being tested on a team of Sony AIBO four
{"title":"Cooperative map building using qualitative reasoning for several AIBO robots","authors":"Raquel Ros Espinoza, R. L. D. Mántaras, J. P. Gruart","doi":"10.5220/0001218502290234","DOIUrl":"https://doi.org/10.5220/0001218502290234","url":null,"abstract":"The problem that a robot navigates autonomously through its environment, builds its own map and localizes itself in the map, is still an open problem. It is known as the SLAM (Simultaneous Localization and Map Building) problem. This problem is made even more difficult when we have several robots cooperating to build a common map of an unknown environment, due to the problem of map integration of several submaps built independently by each robot, and with a high degree of error, making the map matching specially difficult. Most of the approaches to solve map building problems are quantitative, resulting in a great computational cost and a low level of abstraction. In order to fulfil these drawbacks qualitative models have been recently used. However, qualitative models are non deterministic. Therefore, the solution recently adopted has been to mix both qualitative and quantitative models to represent the environment and build maps. However, no reasoning process has been used to deal with the information stored in maps up to now, therefore maps are only static storage of landmarks. In this paper we propose a novel method for cooperative map building based on hybrid (qualitative+quantitative) representation which includes also a reasoning process. Distinctive landmarks acquisition for map representation is provided by the cognitive vision and infrared modules which compute differences from the expected data according to the current map and the actual information perceived. We will store in the map the relative orientation information of the landmarks which appear in the environment, after a qualitative reasoning process, therefore the map will be independent of the point of view of the robot. Map integration will then be achieved by localizing each robot in the maps made by the other robots, through a process of pattern matching of the hybrid maps elaborated by each robot, resulting in an integrated map which all robots share, and which is the main objective of this work. This map building method is currently being tested on a team of Sony AIBO four","PeriodicalId":302311,"journal":{"name":"ICINCO-RA","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125208610","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 : 1900-01-01DOI: 10.5220/0001643600700075
Fernando Juan Berenguer Císcar, F. Monasterio-Huelin
This work presents a method for planning sinusoidal trajectories for an actuated joint, so that the oscillation frequency follows linear profiles, like trapezoidal ones, defined by the user or by a high level planner. The planning method adds a cubic polynomial function for the last segment of the trajectory in order to reach a desired final position of the joint. We apply this planning method to an underactuated bipedal mechanism which gait is generated by the oscillatory movement of its tail. Using linear frequency profiles allow us to modify the speed of the mechanism and to study the efficiency of the system at different speed values.
{"title":"Trajectory planning using oscillatory chirp functions applied to bipedal locomotion","authors":"Fernando Juan Berenguer Císcar, F. Monasterio-Huelin","doi":"10.5220/0001643600700075","DOIUrl":"https://doi.org/10.5220/0001643600700075","url":null,"abstract":"This work presents a method for planning sinusoidal trajectories for an actuated joint, so that the oscillation frequency follows linear profiles, like trapezoidal ones, defined by the user or by a high level planner. The planning method adds a cubic polynomial function for the last segment of the trajectory in order to reach a desired final position of the joint. We apply this planning method to an underactuated bipedal mechanism which gait is generated by the oscillatory movement of its tail. Using linear frequency profiles allow us to modify the speed of the mechanism and to study the efficiency of the system at different speed values.","PeriodicalId":302311,"journal":{"name":"ICINCO-RA","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130822243","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 : 1900-01-01DOI: 10.5220/0002209200720078
C. Dahmen
This paper proposes a tracking algorithm for the extraction of threedimensional position data from SEM images. An algorithm based on active contours with region-based minimization is chosen as basis for twodimensional tracking. This algorithm is then augmented by the incorporation of defocus analysis to estimate the out-of-focus displacement of the object. To solve the ambiguity of the out-of-focus displacement, the astigmatism of the SEM images is used. The separate calculation of variances for the rows and columns of the image enables a successful direction estimation. With the information on the direction, the out-of-focus displacement and the working distance of the acquired image, the distance of the object to the electron gun can be calculated. In combination with the twodimensional part of the tracking, a full threedimensional coordinate set is generated. The approach is tested and evaluated using a positioning setup and the principal feasibility is shown.
{"title":"Threedimensional Tracking using Object Defocus - In Twodimensional Scanning Electron Microscope Images","authors":"C. Dahmen","doi":"10.5220/0002209200720078","DOIUrl":"https://doi.org/10.5220/0002209200720078","url":null,"abstract":"This paper proposes a tracking algorithm for the extraction of threedimensional position data from SEM images. An algorithm based on active contours with region-based minimization is chosen as basis for twodimensional tracking. This algorithm is then augmented by the incorporation of defocus analysis to estimate the out-of-focus displacement of the object. To solve the ambiguity of the out-of-focus displacement, the astigmatism of the SEM images is used. The separate calculation of variances for the rows and columns of the image enables a successful direction estimation. With the information on the direction, the out-of-focus displacement and the working distance of the acquired image, the distance of the object to the electron gun can be calculated. In combination with the twodimensional part of the tracking, a full threedimensional coordinate set is generated. The approach is tested and evaluated using a positioning setup and the principal feasibility is shown.","PeriodicalId":302311,"journal":{"name":"ICINCO-RA","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131125414","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 : 1900-01-01DOI: 10.5220/0002205600600066
J. Yang, Patrick W. Dymond, M. Jenkin
Estimating a robot’s reachable workspace is a fundamental problem in robotics. For simple kinematic chains within an empty environment this computation can be relatively straightforward. For mobile kinematic structures and cluttered environments, the problem becomes more challenging. An efficient probabilistic method for workspace estimation is developed by applying a hierarchical strategy and developing extensions to a probabilistic motion planner. Rather than treating each of the degrees of freedom (DOFs) ‘equally’, a hierarchical representation is used to maximize the volume of the robot’s workspace that is identified as reachable for each probe of the environment. Experiments with a simulated mobile manipulator demonstrate that the hierarchical approach is an effective alternative to the use of an estimation process based on the use of a traditional probabilistic planner.
{"title":"Hierarchical Probabilistic Estimation of Robot Reachable Workspace","authors":"J. Yang, Patrick W. Dymond, M. Jenkin","doi":"10.5220/0002205600600066","DOIUrl":"https://doi.org/10.5220/0002205600600066","url":null,"abstract":"Estimating a robot’s reachable workspace is a fundamental problem in robotics. For simple kinematic chains within an empty environment this computation can be relatively straightforward. For mobile kinematic structures and cluttered environments, the problem becomes more challenging. An efficient probabilistic method for workspace estimation is developed by applying a hierarchical strategy and developing extensions to a probabilistic motion planner. Rather than treating each of the degrees of freedom (DOFs) ‘equally’, a hierarchical representation is used to maximize the volume of the robot’s workspace that is identified as reachable for each probe of the environment. Experiments with a simulated mobile manipulator demonstrate that the hierarchical approach is an effective alternative to the use of an estimation process based on the use of a traditional probabilistic planner.","PeriodicalId":302311,"journal":{"name":"ICINCO-RA","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132262542","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 : 1900-01-01DOI: 10.1007/978-3-540-79142-3_20
M. Cecco, E. Marcuzzi, L. Baglivo, M. Zaccariotto
{"title":"Reactive simulation for real-time obstacle avoidance","authors":"M. Cecco, E. Marcuzzi, L. Baglivo, M. Zaccariotto","doi":"10.1007/978-3-540-79142-3_20","DOIUrl":"https://doi.org/10.1007/978-3-540-79142-3_20","url":null,"abstract":"","PeriodicalId":302311,"journal":{"name":"ICINCO-RA","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133211001","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 : 1900-01-01DOI: 10.5220/0002167800050012
Federico Tombari, K. Konolige
In this paper we investigate the suitability of stereo vision for robot manipulation tasks, which require highfidelity real-time 3D information in the presence of motion. We compare spatial regularization methods for stereo and spacetime stereo, the latter relying on integration of information over time as well as space. In both cases we augment the scene with textured projection, to alleviate the well-known problem of noise in lowtextured areas. We also propose a new spatial regularization method, local smoothing, that is more efficient than current methods, and produces almost equivalent results. We show that in scenes with moving objects spatial regularization methods are more accurate than spacetime stereo, while remaining computationally simpler. Finally, we propose an extension of regularization-based algorithms to the temporal domain, so to further improve the performance of regularization methods within dynamic scenes.
{"title":"A Practical Stereo System based on Regularization and Texture Projection","authors":"Federico Tombari, K. Konolige","doi":"10.5220/0002167800050012","DOIUrl":"https://doi.org/10.5220/0002167800050012","url":null,"abstract":"In this paper we investigate the suitability of stereo vision for robot manipulation tasks, which require highfidelity real-time 3D information in the presence of motion. We compare spatial regularization methods for stereo and spacetime stereo, the latter relying on integration of information over time as well as space. In both cases we augment the scene with textured projection, to alleviate the well-known problem of noise in lowtextured areas. We also propose a new spatial regularization method, local smoothing, that is more efficient than current methods, and produces almost equivalent results. We show that in scenes with moving objects spatial regularization methods are more accurate than spacetime stereo, while remaining computationally simpler. Finally, we propose an extension of regularization-based algorithms to the temporal domain, so to further improve the performance of regularization methods within dynamic scenes.","PeriodicalId":302311,"journal":{"name":"ICINCO-RA","volume":"280 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131670165","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：