Pub Date : 2005-07-18DOI: 10.1109/ICAR.2005.1507410
B. Mourllion, D. Gruyer, A. Lambert, S. Glaser
The aim of this paper is to carry out a comparison between several algorithms of the Kalman filters family for nonlinear systems. Alter having presented the most popular of them and showed its limitations, we introduce some new Kalman filters and compare them for the vehicle localization problem. This comparison is based on the predictive step what corresponds to the worst case that it can occur in vehicle localization. Typically, when we achieve a vehicle tracking, if the tracked vehicle is hidden, corrective data are unavailable and therefore the corrective step is disable (time data alignment)
{"title":"Kalman filters comparison for vehicle localization data alignment","authors":"B. Mourllion, D. Gruyer, A. Lambert, S. Glaser","doi":"10.1109/ICAR.2005.1507410","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507410","url":null,"abstract":"The aim of this paper is to carry out a comparison between several algorithms of the Kalman filters family for nonlinear systems. Alter having presented the most popular of them and showed its limitations, we introduce some new Kalman filters and compare them for the vehicle localization problem. This comparison is based on the predictive step what corresponds to the worst case that it can occur in vehicle localization. Typically, when we achieve a vehicle tracking, if the tracked vehicle is hidden, corrective data are unavailable and therefore the corrective step is disable (time data alignment)","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114395213","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507413
W. Tanaka, T. Arai, K. Inoue, T. Takubo, Y. Mae
Parallel mechanism has some good advantages, but small workspace is a big drawback (Merlet, 2000). We have proposed a parallel mechanism with adjustable link parameters in the previous paper (Arai and Takayama, 2000; Arai and Koseki, 2004, 1998). In this mechanism, there is a need to adjust the suitable link parameters for the required workspace for certain task. In this paper, we discuss the workspace and voids of linearly actuated parallel mechanism with adjustable link parameters. We divide the mechanism into normal and transfigured type and compare these parameters with each other in order to analyze the properties of mechanism at different positions
并联机构有一些优点,但工作空间小是一个很大的缺点(Merlet, 2000)。我们在之前的论文中提出了一种连杆参数可调的并联机构(Arai and Takayama, 2000;Arai and Koseki, 2004, 1998)。在这种机制中,需要为特定任务所需的工作空间调整合适的链接参数。本文讨论了连杆参数可调的线性驱动并联机构的工作空间和空隙。为了分析机构在不同位置的性能,我们将机构分为正常型和变形型,并对这些参数进行了比较
{"title":"Workspace analysis of parallel mechanism with adjustable link parameters","authors":"W. Tanaka, T. Arai, K. Inoue, T. Takubo, Y. Mae","doi":"10.1109/ICAR.2005.1507413","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507413","url":null,"abstract":"Parallel mechanism has some good advantages, but small workspace is a big drawback (Merlet, 2000). We have proposed a parallel mechanism with adjustable link parameters in the previous paper (Arai and Takayama, 2000; Arai and Koseki, 2004, 1998). In this mechanism, there is a need to adjust the suitable link parameters for the required workspace for certain task. In this paper, we discuss the workspace and voids of linearly actuated parallel mechanism with adjustable link parameters. We divide the mechanism into normal and transfigured type and compare these parameters with each other in order to analyze the properties of mechanism at different positions","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117121183","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507439
Won S. Kim, Adnan Ansar, Robert D. Steele
This paper presents three technical elements that we have developed to improve the accuracy of the visual target tracking for single-sol approach-and-instrument placement in future Mars rover missions. An accurate, straightforward method of rover mast calibration is achieved by using a total station, a camera calibration target, and four prism targets mounted on the rover. The method was applied to Rocky8 rover mast calibration and yielded a 1.1-pixel rms residual error. Camera pointing requires inverse kinematic solutions for mast pan and tilt angles such that the target image appears right at the center of the camera image. Two issues were raised. Mast camera frames are in general not parallel to the masthead base frame. Further, the optical axis of the camera model in general does not pass through the center of the image. Despite these issues, we managed to derive non-iterative closed-form exact solutions, which were verified with Matlab routines. Actual camera pointing experiments over 50 random target image points yielded less than 1.3-pixel rms pointing error. Finally, a purely geometric method for camera handoff using stereo views of the target has been developed. Experimental test runs show less than 2.5 pixels error on high-resolution Navcam for Pancam-to-Navcam handoff, and less than 4 pixels error on lower-resolution Hazcam for Navcam-to-Hazcam handoff
{"title":"Rover mast calibration, exact camera pointing, and camera handoff for visual target tracking","authors":"Won S. Kim, Adnan Ansar, Robert D. Steele","doi":"10.1109/ICAR.2005.1507439","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507439","url":null,"abstract":"This paper presents three technical elements that we have developed to improve the accuracy of the visual target tracking for single-sol approach-and-instrument placement in future Mars rover missions. An accurate, straightforward method of rover mast calibration is achieved by using a total station, a camera calibration target, and four prism targets mounted on the rover. The method was applied to Rocky8 rover mast calibration and yielded a 1.1-pixel rms residual error. Camera pointing requires inverse kinematic solutions for mast pan and tilt angles such that the target image appears right at the center of the camera image. Two issues were raised. Mast camera frames are in general not parallel to the masthead base frame. Further, the optical axis of the camera model in general does not pass through the center of the image. Despite these issues, we managed to derive non-iterative closed-form exact solutions, which were verified with Matlab routines. Actual camera pointing experiments over 50 random target image points yielded less than 1.3-pixel rms pointing error. Finally, a purely geometric method for camera handoff using stereo views of the target has been developed. Experimental test runs show less than 2.5 pixels error on high-resolution Navcam for Pancam-to-Navcam handoff, and less than 4 pixels error on lower-resolution Hazcam for Navcam-to-Hazcam handoff","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121853988","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507450
R. Bostelman, T. Hong, R. Madhavan
The performance evaluation of an obstacle detection and segmentation algorithm for automated guided vehicle (AGV) navigation using a 3D real-time range camera is the subject of this paper. Our approach has teen tested successfully on British safety standard recommended object sizes and materials placed on the vehicle path. The segmented (mapped) obstacles are then verified using absolute measurements obtained using a relatively accurate 2D scanning laser rangefinder. Sensor mounting and sensor modulation issues are also described through representative data sets
{"title":"Towards AGV safety and navigation advancement obstacle detection using a TOF range camera","authors":"R. Bostelman, T. Hong, R. Madhavan","doi":"10.1109/ICAR.2005.1507450","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507450","url":null,"abstract":"The performance evaluation of an obstacle detection and segmentation algorithm for automated guided vehicle (AGV) navigation using a 3D real-time range camera is the subject of this paper. Our approach has teen tested successfully on British safety standard recommended object sizes and materials placed on the vehicle path. The segmented (mapped) obstacles are then verified using absolute measurements obtained using a relatively accurate 2D scanning laser rangefinder. Sensor mounting and sensor modulation issues are also described through representative data sets","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129935133","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507469
W. Lai, J. Yan, M. Motamed, S. Green
A dynamically scaled flapping-wing model has been developed to investigate the aerodynamic phenomena and flight performance of insect-scale flapping wings. The mechanism consists of two wings, each having 3 rotational degrees of freedom, mounted on a linear stage to permit translation in a fluid-filled tank. Each wing is equipped with a sensor for instantaneous measurement of the time-varying forces and torques. The setup permits one wing to be designated as the fore wing and the other as the hind wing so that interactions between them can be analysed to understand flight for four-winged insects. The apparatus is versatile enough to explore a range of wing morphologies as well as operational wing trajectory parameters
{"title":"Force measurements on a scaled mechanical model of dragonfly in forward flight","authors":"W. Lai, J. Yan, M. Motamed, S. Green","doi":"10.1109/ICAR.2005.1507469","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507469","url":null,"abstract":"A dynamically scaled flapping-wing model has been developed to investigate the aerodynamic phenomena and flight performance of insect-scale flapping wings. The mechanism consists of two wings, each having 3 rotational degrees of freedom, mounted on a linear stage to permit translation in a fluid-filled tank. Each wing is equipped with a sensor for instantaneous measurement of the time-varying forces and torques. The setup permits one wing to be designated as the fore wing and the other as the hind wing so that interactions between them can be analysed to understand flight for four-winged insects. The apparatus is versatile enough to explore a range of wing morphologies as well as operational wing trajectory parameters","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125045663","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507481
B. Jiang, A. Sample, R. Wistort, A. Mamishev
Maintenance of distributed infrastructures requires periodic measurement of many physical variables at numerous locations. This task can potentially be accomplished with autonomous robotic mobile platforms. The challenges in realizing this vision include electromechanical design of the robot itself, integration of sensors able to estimate the physical properties of the infrastructure, and autonomous operation. This paper describes the electromechanical and sensing system design of the autonomous robot for the inspection of electric power cables. The multiprocessor distributed control architecture developed in this project allows real-time operation of multiple sensors and a possibility to switch between an autonomous mode of operation and a remote-controlled one. The diagnostic sensor array includes thermal, visual, dielectric, and acoustic sensors for the measurement of cable status. Laboratory tests demonstrate the ability of integrated sensors to measure parameters of interest with the resolution required by the application. Field tests in the underground cable system demonstrate the ability of the designed platform to travel along the cable, navigate typical obstacles, and communicate with the host computer
{"title":"Autonomous robotic monitoring of underground cable systems","authors":"B. Jiang, A. Sample, R. Wistort, A. Mamishev","doi":"10.1109/ICAR.2005.1507481","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507481","url":null,"abstract":"Maintenance of distributed infrastructures requires periodic measurement of many physical variables at numerous locations. This task can potentially be accomplished with autonomous robotic mobile platforms. The challenges in realizing this vision include electromechanical design of the robot itself, integration of sensors able to estimate the physical properties of the infrastructure, and autonomous operation. This paper describes the electromechanical and sensing system design of the autonomous robot for the inspection of electric power cables. The multiprocessor distributed control architecture developed in this project allows real-time operation of multiple sensors and a possibility to switch between an autonomous mode of operation and a remote-controlled one. The diagnostic sensor array includes thermal, visual, dielectric, and acoustic sensors for the measurement of cable status. Laboratory tests demonstrate the ability of integrated sensors to measure parameters of interest with the resolution required by the application. Field tests in the underground cable system demonstrate the ability of the designed platform to travel along the cable, navigate typical obstacles, and communicate with the host computer","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115744531","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507457
Luo Jun, Shaorong Xie, Zhenbang Gong
The cable-stayed bridge is of intense popular interest in modern middle-span bridge construction. However, as main supporting parts, cables can't be maintained by efficient methods. The cable maintenance robot developed in this paper is the first application of special robots to cables of cable-stayed bridges. The paper puts forward design method of modularizing which can simplify the design course greatly. The key problems of new climbing mechanisms and painting mechanism applying to arbitrary-gradient cables are developed. The cable robot system can fulfil a series of maintenance of the cables such as cleaning, painting and detecting cables. The shortcomings such as low efficiency, high cost, less safety of artificial methods that are normally adopted in cable-stayed bridges are overcome. Furthermore, the paper deals theoretically with the linear dynamic response of cable under robot's moving on a horizontal cable with constant magnitude and velocity by including the effect of its mass
{"title":"Cable maintenance robot and its dynamic response moving on the horizontal cable","authors":"Luo Jun, Shaorong Xie, Zhenbang Gong","doi":"10.1109/ICAR.2005.1507457","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507457","url":null,"abstract":"The cable-stayed bridge is of intense popular interest in modern middle-span bridge construction. However, as main supporting parts, cables can't be maintained by efficient methods. The cable maintenance robot developed in this paper is the first application of special robots to cables of cable-stayed bridges. The paper puts forward design method of modularizing which can simplify the design course greatly. The key problems of new climbing mechanisms and painting mechanism applying to arbitrary-gradient cables are developed. The cable robot system can fulfil a series of maintenance of the cables such as cleaning, painting and detecting cables. The shortcomings such as low efficiency, high cost, less safety of artificial methods that are normally adopted in cable-stayed bridges are overcome. Furthermore, the paper deals theoretically with the linear dynamic response of cable under robot's moving on a horizontal cable with constant magnitude and velocity by including the effect of its mass","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127085179","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507456
Xiaolin Hu
Simulation-based study plays important roles in robotic systems development. This paper describes robot-in-the-loop simulation, which is a novel simulation method that we developed to allow real robots and robot models to work together for system-wide measurement and test. To support robot-in-the-loop simulation, a simulated virtual environment is developed. Several kinds of sensor/actuator interface models are defined to allow real robots to interact with the virtual environment. To demonstrate the capability of robot-in-the-loop simulation, three mobile robot examples were developed and are presented in the paper in an incremental way. These examples illustrate the usages and configurations of robot-in-the-loop simulation under different situations
{"title":"Applying robot-in-the-loop-simulation to mobile robot systems","authors":"Xiaolin Hu","doi":"10.1109/ICAR.2005.1507456","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507456","url":null,"abstract":"Simulation-based study plays important roles in robotic systems development. This paper describes robot-in-the-loop simulation, which is a novel simulation method that we developed to allow real robots and robot models to work together for system-wide measurement and test. To support robot-in-the-loop simulation, a simulated virtual environment is developed. Several kinds of sensor/actuator interface models are defined to allow real robots to interact with the virtual environment. To demonstrate the capability of robot-in-the-loop simulation, three mobile robot examples were developed and are presented in the paper in an incremental way. These examples illustrate the usages and configurations of robot-in-the-loop simulation under different situations","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132773456","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507492
M. Prats, P. Sanz, A. del Pobil
In this paper we present two new approaches developed in the context of autonomous search for localization and manipulation of books in a semi-structured environment, like a library. Search for books is done by means of visual information which is also integrated with force sensing for book manipulation. Interest regions are located using a local segmentation algorithm with automatic threshold selection. From the extracted visual features, we have implemented a fast tracking method by means of model-based matching. We also apply some recognition techniques in order to find the desired book and to guide the gripper over it. Grasping is finally done by integrating visual and force perception into a global hybrid control law. We have applied the implemented algorithms to the UJI librarian robot and results show the robustness of the implemented search algorithm as well as its fast performance. With respect to the grasping system, vision and force coupling are shown to be an adequate combination of sensors for book manipulation
{"title":"Perception-based search and manipulation in a semi-structured environment","authors":"M. Prats, P. Sanz, A. del Pobil","doi":"10.1109/ICAR.2005.1507492","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507492","url":null,"abstract":"In this paper we present two new approaches developed in the context of autonomous search for localization and manipulation of books in a semi-structured environment, like a library. Search for books is done by means of visual information which is also integrated with force sensing for book manipulation. Interest regions are located using a local segmentation algorithm with automatic threshold selection. From the extracted visual features, we have implemented a fast tracking method by means of model-based matching. We also apply some recognition techniques in order to find the desired book and to guide the gripper over it. Grasping is finally done by integrating visual and force perception into a global hybrid control law. We have applied the implemented algorithms to the UJI librarian robot and results show the robustness of the implemented search algorithm as well as its fast performance. With respect to the grasping system, vision and force coupling are shown to be an adequate combination of sensors for book manipulation","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116684194","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507463
D. Fernández, A. Price
Outdoor mobile robots are often faced with the problem of trying to navigate through an unknown environment. Areas that appear simple to humans can be very difficult for a robot to accurately and consistently describe. Poorly structured dirt roads, such as fire-access tracks and bush-walking tracks, are often overlooked in research but are highly important passageways for emergency support crews, such as search-and-rescue teams and firefighters tackling bush fires. This paper presents a method of autonomously detecting and hence tracking such roads using colour vision. Central to the process is a method of characterising the road surface through a statistical colour description, which makes minimal assumptions about the road. A highly simplified and generalised road model is used to ignore the background and contain the road, and weighted control points are used to generate a spline-based trajectory along the road, which is intended to be used for motion-control of a robot trying to traverse these tracks. Inherent to the system is the avoidance or safe traversal of certain types of obstacles. The combination of simple modelling and efficient processing algorithms has resulted in a usable average processing speed of approximately eight frames per second on the 1.7 GHz Pentium-4 test machine
{"title":"Visual detection and tracking of poorly structured dirt roads","authors":"D. Fernández, A. Price","doi":"10.1109/ICAR.2005.1507463","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507463","url":null,"abstract":"Outdoor mobile robots are often faced with the problem of trying to navigate through an unknown environment. Areas that appear simple to humans can be very difficult for a robot to accurately and consistently describe. Poorly structured dirt roads, such as fire-access tracks and bush-walking tracks, are often overlooked in research but are highly important passageways for emergency support crews, such as search-and-rescue teams and firefighters tackling bush fires. This paper presents a method of autonomously detecting and hence tracking such roads using colour vision. Central to the process is a method of characterising the road surface through a statistical colour description, which makes minimal assumptions about the road. A highly simplified and generalised road model is used to ignore the background and contain the road, and weighted control points are used to generate a spline-based trajectory along the road, which is intended to be used for motion-control of a robot trying to traverse these tracks. Inherent to the system is the avoidance or safe traversal of certain types of obstacles. The combination of simple modelling and efficient processing algorithms has resulted in a usable average processing speed of approximately eight frames per second on the 1.7 GHz Pentium-4 test machine","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132498722","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}