Lluís Pacheco

Improving Clustering Algorithms for Image Segmentation using Contour and Region Information

In image segmentation, clustering algorithms are very popular because they are intuitive and, some of them, easy to implement. For instance, the k-means is one of the most used in the literature, and many authors successfully compare their new proposal with the results achieved by the k-means. However, it is well known that clustering image segmentation has many problems. For instance, the number of regions of the image has to be known a priori, as well as different initial seed placement (initial clusters) could produce different segmentation results. Most of these algorithms could be slightly improved by considering the coordinates of the image as features in the clustering process (to take spatial region information into account). In this paper we propose a significant improvement of clustering algorithms for image segmentation. The method is qualitatively and quantitative evaluated over a set of synthetic and real images, and compared with classical clustering approaches. Results demonstrate the validity of this new approach

Image Mosaicking for Estimating the Motion of an Underwater Vehicle

A composite image constructed by combining a set of smaller images is known as mosaic. Mosaics of the ocean floor are very useful in undersea exploration, creation of visual maps, navigation, etc. A feature-based mosaicking method is proposed, based on textural parameters of certain parts of the image. Textures significantly help in the identification of given features of the image. The tracking of these features over time solves the matching problem in consecutive frames. The correspondence is established with the aid of a cross-correlation algorithm, applied to the colour components of the image in the HSI space. Once the correspondence has been found a displacement vector is obtained relating the features of two images of the sequence. The motion parameters between consecutive frames are estimated through an error minimisation technique. Once the best transformation between two frames has been found, images are warped together composing the mosaic, and information about the vehicle motion is recovered. The experimental results on real images show the effectiveness of the proposed method. Copyright  2000 IFAC

Smart Structural Control Strategies for Offshore Wind Power Generation with Floating Wind Turbines

In recent years, wind energy is the fastest growing clean and renewable energy source in the world. However, most of the wind farm development has been limited to the land space and shallow water regions. Recently, several European countries (including Spain), USA and Japan started to plan floating offshore wind farms. In June of 2009, the first floating offshore wind turbine (Hywind) of the world was installed by Statoil-Hydro and Siemens on the coast of Karmoy, near the port of Bergen, Norway. In general, floating offshore wind farms are considered to be more difficult to design and install. However, in deep waters they are less sensitive to the space availability, noise restriction, and visual pollution, among others. Moreover, the wind power generation is more effective due to that floating offshore wind farm are exposed to a much stronger and steadier wind field.

Experimental Modeling and Control Strategies on an Open Mobile Robot Platform PRIM

This research work deals with the problem of modeling and design of low level speed controller for the mobile robot PRIM. The main objective is to develop an effective educational tool. On one hand, the interests in using the open mobile platform PRIM consist in integrating several highly related subjects to the automatic control theory in an educational context, by embracing the subjects of communications, signal processing, sensor fusion and hardware design, amongst others. On the other hand, the idea is to implement useful navigation strategies such that the robot can be served as a mobile multimedia information point. It is in this context, when navigation strategies are oriented to goal achievement, that a local model predictive control is attained. Hence, such studies are presented as a very interesting control strategy in order to develop the future capabilities of the system

Integrating visual odometry and dead-reckoning for robot localization and obstacle detection

The research presented introduces a new methodology to infer environment structure and robot localization by using a monocular machine vision system. The local field of view is constrained to the vicinity of the mobile robot in order to accomplish with robust navigation issues. The strategy proposed uses optical flow techniques and planar models to obtain qualitative 3D information and robot localization by using time integration series of acquired frames. In this way, different space resolution and meaningful corner information are considered. The different significant image points are correlated from camera pose knowledge and odometer data. The robot localization is achieved combining on board and visual odometer systems for reducing dead reckoning problems. Therefore, the two system errors are compared in a parallel process that selects the most accurate robot localization. Moreover, it is used to infer qualitative 3D information, when mismatches between both odometer systems are produced, due to the fact that the planar floor model is not accomplished. In this context, experimental results that reinforce the effectivity of the work developed are reported by using the available lab mobile platform. Other remarkable features of the strategy presented are its simplicity and the low computational cost.

Trajectory Planning with Control Horizon Based on Narrow Local Occupancy Grid Perception

The occupancy grid framework provides a robust and unified approach to a variety of problems in spatial robot perception and navigation [1]. The occupancy field can be depicted by a probability density function that relates the sensor measures with the real cell state. The Bayesian estimation formulation is proposed by researchers; in this sense not only the use of the last sensor observation measure but also the consideration of the last occupancy estimate are proposed for occupancy. The use of the 2D grids for static indoor mapping is proposed in [2]. Other works propose multidimensional grids for multi target tracking by using obstacle state space with Bayesian filtering techniques [3]. The integration of perception and planning is an interesting topic; hence planning cycles are reported in [4], in which it is considered a time horizon where partial trajectories are planned until the robot state is close to the goal. This work proposes a methodology that obtains a local cell and trajectory, within a narrow grid provided by the on robot system perception, which approaches the robot to the final desired objective. The local data grid is presented as a horizon for making the trajectory planning. A practical approach for differential driven WMR (wheeled mobile robots) is shown by using monocular information and model based control strategies.

Constrained Monocular Obstacle Perception with Just One Frame

This paper presents a monocular perception system tested on wheeled mobile robots. Its significant contribution is the use of a single image to obtain depth information (one bit) when robots detect obstacles. The constraints refer to the environment. Flat and homogeneous floor radiance is assumed. Results emerge from using a set of multi-resolution focus measurement thresholds to avoid obstacle collision. The algorithms simplicity and the robustness achieved can be considered the key points of this work. On-robot experimental results are reported and a broad range of indoor applications is possible. However, false obstacle detection occurs when the constraints fail. Thus, proposals to overcome it are explained.

Testing PID and MPC Performance for Mobile Robot Local Path-following

This paper outlines the online performance of a control law based on PID (proportional-integral-derivative) controllers and MPC (model predictive control) for mobile robot local path-following. Both techniques share the use of a set of different dynamic models. PID controllers are used for controlling the speed of the robots wheels, while high level algorithms compute the necessary wheel speeds in order to generate a motion that approaches the vehicle towards the desired path. Meanwhile, local MPC is implemented by computing the horizon of suitable coordinates that arise from the set of command input combinations. Therefore, command speeds that correspond to the desired point are obtained by minimizing a cost function in which the population of the available coordinates is taken into account.

Local model predictive control experiences with differential driven wheeled mobile robots

This work extends a previously developed research concerning about the use of local model predictive control in differential driven mobile robots. Hence, experimental results are presented as a way to improve the methodology by considering aspects as trajectory accuracy and time performance. In this sense, the cost function and the prediction horizon are important aspects to be considered. The aim of the present work is to test the control method by measuring trajectory tracking accuracy and time performance. Moreover, strategies for the integration with perception system and path planning are briefly introduced. In this sense, monocular image data can be used to plan safety trajectories by using goal attraction potential fields.

Control Education within A Multidisciplinary Summer Course on Applied Mobile Robotics

Abstract This paper presents our teaching experience in control educational issues through a summer course ” Applied Mobile Robotics”. The main aim is to integrate different knowledge related to control and computer science through an adequate robotic framework that acts as an educational multidisciplinary tool in the course. As a practical approach, the majority of educational activities of the course are carried out at our university labs. The students are greatly motivated by working on such a robotic platform, which permits them to consolidate the acquired knowledge and to extend their complementary curricula.