Joaquín Ferruz

A cooperative perception system for multiple UAVs: Application to automatic detection of forest fires

This paper presents a cooperative perception system for multiple heterogeneous unmanned aerial vehicles (UAVs). It considers different kind of sensors: infrared and visual cameras and fire detectors. The system is based on a set of multipurpose low-level image-processing functions including segmentation, stabilization of sequences of images, and geo-referencing, and it also involves data fusion algorithms for cooperative perception. It has been tested in field experiments that pursued autonomous multi-UAV cooperative detection, monitoring, and measurement of forest fires. This paper presents the overall architecture of the perception system, describes some of the implemented cooperative perception techniques, and shows experimental results on automatic forest fire detection and localization with cooperating UAVs.

Vision-Based Odometry and SLAM for Medium and High Altitude Flying UAVs

This paper proposes vision-based techniques for localizing an unmanned aerial vehicle (UAV) by means of an on-board camera. Only natural landmarks provided by a feature tracking algorithm will be considered, without the help of visual beacons or landmarks with known positions. First, it is described a monocular visual odometer which could be used as a backup system when the accuracy of GPS is reduced to critical levels. Homography-based techniques are used to compute the UAV relative translation and rotation by means of the images gathered by an onboard camera. The analysis of the problem takes into account the stochastic nature of the estimation and practical implementation issues. The visual odometer is then integrated into a simultaneous localization and mapping (SLAM) scheme in order to reduce the impact of cumulative errors in odometry-based position estimation approaches. Novel prediction and landmark initialization for SLAM in UAVs are presented. The paper is supported by an extensive experimental work where the proposed algorithms have been tested and validated using real UAVs.

Design of Embedded DSP-Based Fuzzy Controllers for Autonomous Mobile Robots

Fuzzy controllers are used in many applications because of their rapid design by translating heuristic knowledge, robustness against perturbations, and smoothness in the control action. However, they require parallel processing and special operators (such as fuzzification or defuzzification) which are not available in standard digital signal processors (DSPs), thus complicating their direct implementation. This paper describes an efficient design methodology that allows starting with any kind of fuzzy controller and subsequently transforming it until a system suitable for easy DSP implementation is obtained. Such methodology is greatly aided by the design environment Xfuzzy 3. The parking problem of an autonomous robot is described to illustrate the steps of this methodology. Real experiments with the autonomous robot ROMEO 4R demonstrate efficiency of the designed fuzzy controller embedded into a stand-alone card based on a fixed-point DSP from Texas Instruments.

Motion compensation and object detection for autonomous helicopter visual navigation in the COMETS system

This work presents real time computer vision techniques for autonomous navigation and operation of unmanned aerial vehicles. The proposed techniques are based on image feature matching and projective methods. Particularly, the paper presents the application to helicopter motion compensation and object detection. These techniques have been implemented in the framework of the COMETS multi-UAV systems. Furthermore, The work presents the application of the proposed techniques in a forest fire scenario in which the COMETS system can be demonstrated.

Unmanned Aerial Vehicle Localization Based on Monocular Vision and Online Mosaicking

This paper presents a new approach for vision-based UAV localization, using mosaics as environment representations. Inter-image motions are used to estimate the motion of the UAV. Online mosaicking is applied to reduce the impact of the accumulative errors in UAV position estimation. A new method to build an stochastic mosaic given the image-to-image homographies is detailed. The mosaic consists of a network of inter-image relations, and is used to create a consistent view of the environment of the UAV and hence, to detect the drift in position estimation by using the mosaic as a resource. The technique could be called simultaneous localization and mosaicking. This technique is specially suitable for monitoring and surveillance tasks in which the UAV will repeatedly cover the same area. The paper also shows experimental results with real UAVs where the benefits of the proposed method are evident.

Homography Based Kalman Filter for Mosaic Building. Applications to UAV position estimation

This paper presents a probabilistic framework where uncertainties can be considered in the mosaic building process. It is shown how can be used as an environment representation for an aerial robot. The inter-image relations are modeled by homographies. The paper shows a robust method to compute them in the case of quasi-planar scenes, and also how to estimate the uncertainties in these local image relations. Moreover, the paper describes how, when a loop is present in the sequence of images, the accumulated drift can be compensated and propagated to the rest of the mosaic. In addition, the relations among images in the mosaic can be used, under certain assumptions, to localize the robot.

Improving vision-based planar motion estimation for unmanned aerial vehicles through online mosaicing

The paper presents a vision-based position estimation method for UAVs. It assumes a planar scene, approximation that usually holds when a vehicle is flying at a relatively high altitude. Monocular image sequences gathered by the UAV are used to estimate the vehicle motion, but accumulative errors can make diverge the estimated position. The proposed method uses an online-built mosaic to correct the drift associated to the planar motion estimation algorithm. The mosaic allows to use not only the current image but also previously recorded information for localization. Results from actual field experiments are presented

Control and perception components for autonomous vehicle guidance. Application to the ROMEO vehicles

Abstract This paper presents several control and perception components that implement navigation behaviours in autonomous vehicles. A behaviour-based control architecture integrating these components is also presented. The paper concentrates on autonomous tracking behaviours. In particular, the tracking of explicit paths, moving targets and environmental features are described. These behaviours have been implemented using several different position estimation techniques: dead reckoning; global position estimation using GPS; and position estimation with respect to the environment. The control architecture has been implemented in ROMEO vehicles at the University of Seville. These autonomous vehicles are adaptated from conventional electric vehicles and are currently used for experiments in autonomous navigation and teleoperation in outdoor environments. A short description of the general characteristics of the ROMEO-3R (tricycle) and ROMEO-4R (four wheels) vehicles is presented. The paper includes results from the tracking of environmenal features with proximity sensors, and visual tracking of moving targets.

Reconfigurable Control Architecture for Distributed Systems in the HERO Autonomous Helicopter

This paper presents the architecture of an onboard controller developed for the HERO autonomous helicopter, which is a low-cost unmanned aerial vehicle research platform. An embedded digital-signal-processor-based low-level controller is devoted to flight control, while a PC-based high-level controller is used for onboard perception tasks and interaction with other agents in a distributed system. The functional design, software architecture, and implementation of the low-level controller are analyzed in detail, focusing mainly on its runtime environment (JULIET) and its capability for flexible reconfiguration. The connectivity functions of the low-level controller with external possibly distributed agents are also addressed. Finally, the results of real autonomous flight experiments are presented, including the tracking of a smooth 3-D path described by over two hundred waypoints.

A visual odometer without 3D reconstruction for aerial vehicles. Applications to building inspection

This paper presents a vision-based method to estimate the * real motion of a single camera from views of a planar patch. Projective techniques allow to estimate camera motion from pixel space apparent motion without explicit 3-D reconstruction. In addition, the paper will present the HELINSPEC project, the framework where the proposed method has been tested, and will detail some applications in external building inspection that make use of the proposed techniques.