Detecting and selecting proper landmarks is a key issue to solve Simultaneous Localization and Mapping (SLAM). In this work, we present a novel approach to perform this landmark detection. Our approach is based on usi...
详细信息
Detecting and selecting proper landmarks is a key issue to solve Simultaneous Localization and Mapping (SLAM). In this work, we present a novel approach to perform this landmark detection. Our approach is based on using three sources of information: 1) three-dimensional topological information from SLAM; 2) context information to characterize regions of interest (RoI); and 3) features extracted from these RoIs. Topological information is taken from the SLAM algorithm, i.e. the three-dimensional approximate position of the landmark with a certain level of uncertainty. Contextual information is obtained by segmenting the image into background and RoIs. Features extracted from points of interest are then computed by using common feature extractors such as SIFT and SURF. This information is used to associate new observations with known landmarks obtained from previous observations. The proposed approach is tested under a real unstructured underwater environment using the SPARUS AUV. Results demonstrate the validity of our approach, improving map consistency.
The Object Oriented Control Architecture for Autonomy (O 2 CA 2 ) is a control architecture being developed at the University of Girona for the GARBI underwater vehicle. Conceived as a hybrid, it is organised in three...
详细信息
The Object Oriented Control Architecture for Autonomy (O 2 CA 2 ) is a control architecture being developed at the University of Girona for the GARBI underwater vehicle. Conceived as a hybrid, it is organised in three layers (Deliberative, Control Execution and Reactive) merging the deliberation mechanisms of planning with reactive behaviours in charge of controlling the robot. The aim of this paper is to provide an overall description of the whole architecture and an in depth description of the Reactive-layer. The concepts of the architecture have been tested with the simulation of a simple mission consisting of navigating through a sequence of way-points while avoiding contact with obstacles.
We present a computervision system that associates omnidirectional vision with structured light with the aim of obtaining depth information for a 360 degrees field of view. The approach proposed in this article combi...
详细信息
We present a computervision system that associates omnidirectional vision with structured light with the aim of obtaining depth information for a 360 degrees field of view. The approach proposed in this article combines an omnidirectional camera with a panoramic laser projector. The article shows how the sensor is modelled and its accuracy is proved by means of experimental results. The proposed sensor provides useful information for robot navigation applications, pipe inspection, 3D scene modelling etc.
The design of a steering and depth control of an underwater vehicle is of interest from the point of view of motion stabilisation as well as manoeuvring performance. The paper describes how a Fuzzy-like Proportional D...
详细信息
The design of a steering and depth control of an underwater vehicle is of interest from the point of view of motion stabilisation as well as manoeuvring performance. The paper describes how a Fuzzy-like Proportional Derivative Controller (Fuzzy-like PD Control) is used to control the course-changing and course-keeping tracking mission and motion of an underwater vehicle. The idea for this type of control architecture is to identify the optimum values, in terms of control performance and robustness, of the parameters of the F-like PD Controller. These parameters may be the scaling factors that are applied in the input/output of the PD part of the controller as well as the fuzzy sets of the fuzzy part of the controller. The values of the scaling factors for the error, the change-of-error and the control output are optimised based on experiments. In this work a method has been developed to control the yaw and depth of an underwater robot in terms of course-changing and course-keeping. The controller is synthesised in two parts. Firstly it is applied in horizontal xy and secondly in vertical xz surface. Experiments in a real environment were planned using the Taguchi Design of Experiments and performed to investigate the capabilities of the controller. The results are presented and analysed extensively.
暂无评论