Andrea Cesetti

A Vision-Based Guidance System for UAV Navigation and Safe Landing using Natural Landmarks

In this paper a vision-based approach for guidance and safe landing of an Unmanned Aerial Vehicle (UAV) is proposed. The UAV is required to navigate from an initial to a final position in a partially known environment. The guidance system allows a remote user to define target areas from a high resolution aerial or satellite image to determine either the waypoints of the navigation trajectory or the landing area. A feature-based image-matching algorithm finds the natural landmarks and gives feedbacks to an onboard, hierarchical, behaviour-based control system for autonomous navigation and landing. Two algorithms for safe landing area detection are also proposed, based on a feature optical flow analysis. The main novelty is in the vision-based architecture, extensively tested on a helicopter, which, in particular, does not require any artificial landmark (e.g., helipad). Results show the appropriateness of the vision-based approach, which is robust to occlusions and light variations.

A Visual Global Positioning System for Unmanned Aerial Vehicles Used in Photogrammetric Applications

The combination of photogrammetric aerial and terrestrial recording methods can provide new opportunities for photogrammetric applications. A UAV (Unmanned Aerial Vehicle), in our case a helicopter system, can cover both the aerial and quasi-terrestrial image acquisition methods. A UAV can be equipped with an on-board high resolution camera and a priori knowledge of the operating area where to perform photogrammetric tasks. In this general scenario our paper proposes vision-based techniques for localizing a UAV. Only natural landmarks provided by a feature tracking algorithm will be considered, without the help of visual beacons or landmarks with known positions. The novel idea is to perform global localization, position tracking and localization failure recovery (kidnapping) based only on visual matching between current view and available georeferenced satellite images. The matching is based on SIFT features and the system estimates the position of the UAV and its altitude on the base of the reference image. The vision system replaces the GPS signal combining position information from visual odometry and georeferenced imagery. Georeferenced satellite or aerial images must be available on-board beforehand or downloaded during the flight. The growing availability of high resolution satellite images (e.g., provided by Google Earth or other local information sources) makes this topic very interesting and timely. Experiments with both synthetic (i.e., taken from satellites or datasets and pre elaborated) and real world images have been performed to test the accuracy and the robustness of our method. Results show sufficient performance if compared with common GPS systems and give a good performance also in the altitude estimation, even if in this last case there are only preliminary results.

A Framework for Simulation and Testing of UAVs in Cooperative Scenarios

Today, Unmanned Aerial Vehicles (UAVs) have deeply modified the concepts of surveillance, Search&Rescue, aerial photogrammetry, mapping, etc. The kinds of missions grow continuously; missions are in most cases performed by a fleet of cooperating autonomous and heterogeneous vehicles. These systems are really complex and it becomes fundamental to simulate any mission stage to exploit benefits of simulations like repeatability, modularity and low cost. In this paper a framework for simulation and testing of UAVs in cooperative scenarios is presented. The framework, based on modularity and stratification in different specialized layers, allows an easy switching from simulated to real environments, thus reducing testing and debugging times, especially in a training context. Results obtained using the proposed framework on some test cases are also reported.

Vision-based autonomous navigation and landing of an unmanned aerial vehicle using natural landmarks

This paper presents the design and implementation of a vision-based navigation and landing algorithm for an autonomous helicopter. The vision system allows to define target areas from a high resolution aerial or satellite image to determine the waypoints of the navigation trajectory or the landing area. The helicopter is required to navigate from an initial position to a final position in a partially known environment using GPS and vision, to locate a landing target (a helipad of a known shape or a natural landmark) and to land on it. The vision system, using a feature-based image matching algorithm, finds the area and gives feedbacks to the control system for autonomous landing. Vision is used for accurate target detection, recognition and tracking. The helicopter updates its landing target parameters owing to vision and uses an on board behavior-based controller to follow a path to the landing site. Results show the appropriateness of the vision-based approach that does not require any artificial landmark (e.g., helipad) and is quite robust to occlusions, light variations and seasonal changes (e.g., brown or green leaves).

Autonomous safe landing of a vision guided helicopter

In this paper a vision-based system for safe autonomous landing of a helicopter-based Unmanned Aerial Vehicle (UAV) is presented. The remote user selects target areas from high resolution aerial or satellite images. These areas are tracked by a feature-based image matching algorithm that identifies natural landmarks and gives feedbacks for control purposes.

A Service Oriented Architecture supporting an autonomous mobile robot for industrial applications

This paper presents the design and implementation of a control system for autonomous navigation based on a Service Oriented Architecture (SOA) supporting a mobile robot suitable for industrial applications. The robot is required to perform generic high-level tasks in indoor structured environments. The control architecture, developed within the Microsoft Robotics Developer Studio (MRDS), allows to encapsulate the controller functionalities as a set of services that interact and exchange data among them. This approach allows to guarantee flexibility, scalability and reliability. The accurate testing, carried out in simulated and real environments, shows good real-time performances.

From Simulated to Real Scenarios: A Framework for Multi-UAVs

In this paper a framework for simulation of Unmanned Aerial Vehicles (UAVs), oriented to rotary wings aerial vehicles, is presented. It allows UAV simulations for stand-alone agents or multi-agents exchanging data in cooperative scenarios. The framework, based on modularity and stratification in different specialized layers, allows an easy switching from simulated to real environments, thus reducing testing and debugging times. CAD modelling supports the framework mainly with respect to extraction of geometrical parameters and virtualization. Useful applications of the framework include pilot training, testing and validation of UAVs control strategies, especially in an educational context, and simulation of complex missions.

Development of a flexible test platform for household appliance testing based on mobile agents

This paper describes an innovative and flexible test platform for the household appliances test based on mobile agents, in order to carry out efficient data collection and analysis and to assist products design by providing defective components identification. The diagnostic system is specifically designed for the life-test laboratories, in which the mobile agent performs several measurements on many products over a long period of time, using different sensors mounted on board of the platform. The architecture and realization of the test platform is illustrated and described in details, focusing on the aspects related with autonomous mobile agent development, such as: navigation and perception in an indoor highly structured environment with unpredictable minor changes, manipulation and physical interaction with the product, image recognition of the environment and of the product. A prototype test platform has been developed and the first results show that it is feasible and effective for the improvement of the level of automation and quality of a life-test laboratory.

Service Oriented Soft Real-time implementation of SLAM capability for mobile robots

Abstract This paper focuses on solving practical challenges inherent from the use of state-of-art mobile robotics techniques in a resource hungry embedded mobile unit without inherent support for hard real-time operation. Such problems include real-time constraints, sensor acquisition independence from robot movement, multi-rate parallel data acquisition and memory limitations.

Field Robot Supporting the Activities of a Household Appliances Laboratory

Abstract The development of a field robot for diagnosis and testing in the production line and laboratories (e.g., life test labs) of household appliances is considered. The proposed system targets the repetitive task of taking numerous measurements on products in order to guarantee a standardized and repeatable quality control. In this solution the diagnosis and testing station is not a fixed system but a flexible one, based on mobile robot with sensory and diagnostic skills. Such system achieves high flexibility own to its mobile nature and cost reduction due to the reduction in the number of measurement devices. The system can be interconnected with surrounding production and test systems to provide relevant feedback information for an integrated production and measurement process. This paper focuses on the aspects related with autonomous mobile platform development. A navigation module has been developed to guarantee the reliable performance in an indoor highly structured environment with position uncertainties of devices to be tested. A localization procedure has been integrated in the navigation module making use of Service Oriented Architecture (SOA). Preliminary tests show the feasibility of the proposed solution for the considered field application.