Riccardo Cassinis

Unsupervised matching of visual landmarks for robotic homing using Fourier–Mellin transform

Abstract This paper presents an algorithm that uses visual information to achieve the homing of an autonomous agent inside a previously visited environment. An image grabbed at the target position is compared with the currently perceived one to determine the relative position of the robot and of its target. Only particular regions of the image, called Visual References, are taken into account. A Visual References correlation criterion that uses the Fourier–Mellin Transform to match the Visual References in different images is employed. This transform in fact allows computing Visual References that are invariant to rotation, scaling and translation. Robustness due to the use of the Mellin Transform in the Visual References selection and coupling leads to more precise navigation. Tests and results are presented.

A robot self-localization system based on omnidirectional color images

Abstract A self-localization system for autonomous mobile robots is presented. This system estimates the robot position in previously learned environments, using data provided solely by an omnidirectional visual perception subsystem composed of a camera and of a special conical reflecting surface. It performs an optical pre-processing of the environment, allowing a compact representation of the collected data. These data are then fed to a learning subsystem that associates the perceived image to an estimate of the actual robot position. Both neural networks and statistical methods have been tested and compared as learning subsystems. The system has been implemented and tested and results are presented.

A bee-inspired visual homing using color images

Abstract This paper presents a visual homing algorithm for autonomous robots inspired by the behaviour of bees and other social insects. The homing method presented is based on an affine motion model whose parameters are estimated by a best matching criterion. No attempts are made to recognize the objects or to extract 3D models from the scene. Improvements in the algorithm and in the use of colour information are introduced in order to enhance the efficiency of the navigation vector estimate. Tests and results are presented.

A novel visual landmark matching for a biologically inspired homing

Abstract This paper presents a homing algorithm for an autonomous robot that uses only visual information. An image grabbed at the target position is compared with the perceived one to determine the position of the robot and its target. Visual landmarks are extracted autonomously from the images and a correlation criterion, based on a novel visual landmark descriptor equalization, is presented.

AMIRoLoS an active marker internet-based robot localization system

SAURON (Surveillance AUtonomous Robots Over Network) is a research project focused on the use of autonomous patrolling robots for surveillance purposes. This paper presents the structure of SAURON localization module AMIRoLoS (Active Marker Internet-based Robot Localization System). It provides on demand the robot position in indoor and outdoor environments using active markers and commercial off-the-shelf web-cams. The system has a client-server architecture, and is now part of a message-oriented middleware that is under development at the University of Brescia. The functionality of the localization module has been demonstrated with real-world experiments.

A bee-inspired robot visual homing method

This paper presents a proposal for a visual homing algorithm inspired by the behaviours of social insects. The homing method presented is based on an affine motion model of which parameters are estimated by the best matching criteria. In the matching phase no attempts are made either to recognise objects or to extract 3D models of the scene. Hypotheses and perspectives about the use of single landmarks by bees are introduced. The tests and experimental results are presented.

Guidance principle and robustness issues for a biologically-inspired visual homing

Analyses the guidance principle and the robustness features of a biologically-inspired visual homing algorithm for autonomous robots. The homing strategy uses colour images and is based on an affine matching model whose parameters are used to estimate real navigation displacement in the environment. The guidance principle of the visual homing is proven to be a visual potential function with an equilibrium point located at the goal position. The presence of a potential function means that classical control-theory principles based on the Lyapunov functions can be applied to assess the robustness of the navigation strategy.

Intelligent Telepresence: Introducing Virtual Reality In Advanced Robots

The paper discusses some issues about a telepresence system to be used for remote driving of robots that operate in hazardous and/or hostile environments. The emphasis is on the problem of efficiently using and integrating information from different sensors, in order to provide the remote operator with readily understandable and usable data.

Robotic Transnasal Endoscopic Skull Base Surgery: Systematic Review of the Literature and Report of a Novel Prototype for a Hybrid System (Brescia Endoscope Assistant Robotic Holder)

BACKGROUND Although robotics has already been applied to several surgical fields, available systems are not designed for endoscopic skull base surgery (ESBS). New conception prototypes have been recently described for ESBS. The aim of this study was to provide a systematic literature review of robotics for ESBS and describe a novel prototype developed at the University of Brescia. METHODS PubMed and Scopus databases were searched using a combination of terms, including Robotics OR Robot and Surgery OR Otolaryngology OR Skull Base OR Holder. The retrieved papers were analyzed, recording the following features: interface, tools under robotic control, force feedback, safety systems, setup time, and operative time. A novel hybrid robotic system has been developed and tested in a preclinical setting at the University of Brescia, using an industrial manipulator and readily available off-the-shelf components. RESULTS A total of 11 robotic prototypes for ESBS were identified. Almost all prototypes present a difficult emergency management as one of the main limits. The Brescia Endoscope Assistant Robotic holder has proven the feasibility of an intuitive robotic movement, using the surgeons head position: a 6 degree of freedom sensor was used and 2 light sources were added to glasses that were therefore recognized by a commercially available sensor. CONCLUSIONS Robotic system prototypes designed for ESBS and reported in the literature still present significant technical limitations. Hybrid robot assistance has a huge potential and might soon be feasible in ESBS.

Neural networks for autonomous path-following with an omnidirectional image sensor

This paper presents a path-following system implemented with two different types of neural networks, that enables an autonomous mobile robot to return along a previously learned path in a dynamic environment. The path-following is based on data provided by an omnidirectional conical visual system, derived from the COPIS sensor, but with different optical reflective properties. The system uses optical and software processing and a neural network to learn the path, described as a sequence of selected points. In the navigation phase it drives the robot along this learned path. Interesting results have been achieved using low cost equipment. Test and results are presented.