Giulio Sandini

A foveated retina-like sensor using CCD technology

A FOVEATED RETINA-LIKE SENSOR USING CCD TECHNOLOGY J. Van der Spiegel, G. Kreider Univ. of Pennsy... more

On the estimation of depth from motion using an anthropomrphic visual sensor

Lecture Notes in Computer Science, 1990

In this paper the application of an anthropomorphic, retina—like visual sensor for optical flow a... more In this paper the application of an anthropomorphic, retina—like visual sensor for optical flow and depth estimation, is presented. The main advantage, obtained with the non — uniform sampling, is the considerable data reduction, while a high spatial resolution is preserved in the part of the field of view corresponding to the focus of attention.

Dynamic aspects in active vision

CVGIP: Image Understanding, 1992

... 7 Currently, the performances of the CCD sensor are being evaluated using a prototype camera.... more

3-D object reconstruction using stereo and motion

IEEE Transactions on Systems, Man, and Cybernetics, 1989

Ahsfrucf -The extraction of reliable range data from images is investigated, considering, as a po... more Ahsfrucf -The extraction of reliable range data from images is investigated, considering, as a possible solution, the integration of different sensor modalities. Two different algorithms are used to obtain independent estimates of depth from a sequence of stereo images. The results are integrated on the basis of the uncertainty of each measure. The stereo algorithm uses a coarse-to-fine control strategy to compute disparity. An algorithm for depth-from-motion is used exploiting the constraint imposed by active motion of the cameras. To obtain a three-dimensional (3-D) description of the objects, the motion of the cameras is purposively controlled, as to move around the objects in view, while the direction of gaze is kept still toward a fixed point in space. This egomotion strategy, which is similar to that adopted by the human visuomotor system, allows a better exploration of partially occluded objects and simplifies the motion equations. The algorithm has been tested on real scenes, demonstrating a low sensitivity to image noise, mainly due to the integration of independent measures. An experiment, performed on a real scene containing several objects, is presented.

Download

3D feature extraction from sequences of range data

International Symposium of Robotics Research, 1990

Obstacle Detection from a Moving Vehicle

Advances in Human-Computer Interaction, 1995

A developmental approach to visually-guided reaching in artificial systems

Neural Networks, 1999

The aim of the present paper is to propose that the adoption of a framework of biological develop... more The aim of the present paper is to propose that the adoption of a framework of biological development is suitable for the construction of artificial systems. We will argue that a developmental approach does provide unique insights on how to build highly complex and adaptable artificial systems. To illustrate our point, we will use as an example the acquisition of goal-directed reaching. In the initial part of the paper we will outline (a) how mechanisms of biological development can be adapted to the artificial world, and (b) how this artificial development differs from traditional engineering approaches to robotics. An experiment performed on an artificial system initially controlled by motor reflexes is presented, showing the acquisition of visuo-motor maps for ballistic control of reaching without explicit knowledge of the system's kinematic parameters.

Download

Dynamic aspects in active vision

International Journal of Computer Vision, 1992

... 7 Currently, the performances of the CCD sensor are being evaluated using a prototype camera.... more

Gradient driven self-organizing systems

International Conference on Intelligent RObots and Systems - IROS, 1993

The aim of this paper is to discuss and present some experimental data on the use of optical, che... more The aim of this paper is to discuss and present some experimental data on the use of optical, chemical and ultrasound sensors to control the motion of single and cooperating robots. The distinctive feature is that in both cases the motion of the robots is not driven by a localized target (e.g. a light, or a sound) but by a concentration gradient such as the one generated by a gas leak. Experiments using a simple optical sensor reading a variable density pattern of dark spots painted on the ground plane, are presented along with experiments performed using simple chemical sensors measuring the local gradient of a substance. Different strategies are discussed based on different configurations of the sensing devices and reflexive motor controls. The goal of the experiment is to analyze the performance of simple autonomous robots in reaching the point of highest concentration (i.e. the gas leak). This performance has been analyzed for single robots and for cooperating robots using a very simple communication channel

On The Estimation Of Depth From Motion Using An Anthropomorphic Visual Sensor

European Conference on Computer Vision, 1990

In this paper the application of an anthropomorphic, retina—like visual sensor for optical flow a... more In this paper the application of an anthropomorphic, retina—like visual sensor for optical flow and depth estimation, is presented. The main advantage, obtained with the non — uniform sampling, is the considerable data reduction, while a high spatial resolution is preserved in the part of the field of view corresponding to the focus of attention. As for depth estimation a tracking egomotion strategy is adopted which greatly simplifies the motion equations, and naturally fits with the characteristics of the retinal sensor (the displacement is smaller wherever the image resolution is higher). A quantitative error analysis is carryed out, determining the uncertainty of range measurements. An experiment, performed on a real image sequence, is presented.

Active Tracking Strategy for Monocular Depth Inference over Multiple Frames

IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990

The extraction of depth information from a sequence of images is investigated. An algorithm that ... more The extraction of depth information from a sequence of images is investigated. An algorithm that exploits the constraint imposed by active motion of the camera is described. Within this framework, in order to facilitate measurement of the navigation parameters, a constrained egomotion strategy was adopted in which the position of the fixation point is stabilized during the navigation (in an

Divergent stereo in autonomous navigation: From bees to robots

International Journal of Computer Vision, 1995

This article presents some experiments of a real-time navigation system driven by two cameras poi... more This article presents some experiments of a real-time navigation system driven by two cameras pointing laterally to the navigation direction (Divergent Stereo). Similarly to what has been proposed in (Franceschini et al. 1991; Coombs and Roberts 1992), our approach (Sandini et al. 1992; Santos-Victor et al. 1993) assumes that, for navigation purposes, the driving information is not distance (as it is obtainable by a stereo setup) but motion and, more precisely, by the use of qualitative optical-flow information computed over nonoverlapping areas of the visual field of two cameras. Following this idea, a mobile vehicle has been equipped with a pair of cameras looking laterally (much like honeybees) and a controller based on fast, real-time computation of optical flow has been implemented. The control of the mobile robot (Robee) is based on the comparison between the apparent image velocity of the left and the right cameras. The solution adopted is derived from recent studies (Srinivasan 1991) describing the behavior of freely flying honeybees and the mechanisms they use to perceive range. This qualitative information (no explicit measure of depth is performed) is used in many experiments to show the robustness of the approach, and a detailed description of the control structure is presented to demonstrate the feasibility of the approach in driving the mobile robot within a cluttered environment. A discussion about the potentialities of the approach and the implications in terms of sensor structure is also presented.

Download

On the advantages of polar and log-polar mapping for direct estimation of time-to-impact from optical flow

IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993

The estimation of time to impact is of vital importance for animals as well as for autonomous rob... more The estimation of time to impact is of vital importance for animals as well as for autonomous robots. The optical ow, which is the two-dimensional projection on the retinal plane of the relative, three-dimensional motion between the observer and the objects in the scene can be used to estimate the time to impact. In this paper the application of an anthropomorphic, retina-like visual sensor and the advantages of polar and log-polar mapping for visual navigation are investigated.

Download

Active vision based on space-variant sensing

Dynamic Vergence Using Log-Polar Images

International Journal of Computer Vision, 1997

Vergence provides robot vision systems with a crucial degree of freedom: it enables fixation of p... more Vergence provides robot vision systems with a crucial degree of freedom: it enables fixation of points in visual space at different distances from the observer. Vergence control, therefore, affects the performance of the stereo system as well as the results of motion estimation and tracking and, as such, must satisfy different requirements in order to be able to provide not only a stable fixation, but a stable binocular fusion, and a fast, smooth and accurate reaction to changes in the environment. To obtain this kind of performance the paper focuses specifically on the use of dynamic visual information to drive vergence control. In this context, moreover, the use of a space-variant, anthropomorphic sensor is described and some advantages in relation to vergence control are discussed to demonstrate the relevance of image plane geometry for this particular task. Expansion or contraction patterns and the temporal evolution of the degree of fusion measured in the log-polar domain are the inputs to the vergence control system and determine robust and accurate steering of the two cameras. Real-time experiments are presented to demonstrate the performance of the system covering different key situations.

Download

Surface EMG for force control of mechanical hands

2008 IEEE International Conference on Robotics and Automation, 2008

The dexterity of active hand prosthetics is limited not only due to the limited availability of d... more The dexterity of active hand prosthetics is limited not only due to the limited availability of dexterous prosthetic hands, but mainly due to limitations in interfaces. How is an amputee supposed to command the prosthesis what to do (i.e., how to grasp an object) and with what force (i.e., holding a hammer or grasping an egg)? So far, in literature, the most interesting results have been achieved by applying machine learning to forearm surface electromyography (EMG) to classify finger movements; but this approach lacks, in general, the possibility of quantitatively determining the force applied during the grasping act.

Download

Internal models of reaching and grasping

Advanced Robotics, 2007

One of the most distinguishing features of cognitive systems is the ability to predict the future... more One of the most distinguishing features of cognitive systems is the ability to predict the future course of actions and the results of ongoing behaviors, and in general to plan actions well in advance. Neuroscience has started examining the neural basis of these skills with behavioral or animal studies and it is now relatively well understood that the brain builds models of the physical world through learning. These models are sometimes called 'internal models', meaning that they are the internal rehearsal (or simulation) of the world enacted by the brain. In this paper we investigate the possibility of building internal models of human behaviors with a learning machine that has access to information in principle similar to that used by the brain when learning similar tasks. In particular, we concentrate on models of reaching and grasping, and we report on an experiment in which biometric data collected from human users during grasping was used to train a support vector machine. We then assess to what degree the models built by the machine are faithful representations of the actual human behaviors. The results indicate that the machine is able to predict reasonably well human reaching and grasping, and that prior knowledge of the object to be grasped improves the performance of the machine, while keeping the same computational cost.

Download

Active vision based on space-variant sensing

The icub cognitive architecture: Interactive development in a humanoid robot

Development and Learning, …, Jul 11, 2007

This paper describes the design of a cognitive architecture for the iCub : an open-systems 53 deg... more This paper describes the design of a cognitive architecture for the iCub : an open-systems 53 degree-offreedom cognitive humanoid robot. At 94 cm tall, the iCub is the same size as a three year-old child and is designed to be able to crawl on all fours and sit up. Its hands will allow dexterous manipulation, its head and eyes are fully articulated, and it has visual, vestibular, auditory, and haptic sensory capabilities. We begin by reviewing briefly the enactive approach to cognition, highlighting the requirements for phylogenetic configuration, the necessity for ontogenetic development, and the importance of humanoid embodiment. After a short look at the the iCub's mechanical and electronic specifications, we detail the iCub cognitive architecture, addressing the iCub phylogeny, i.e. the robot's intended innate abilities, the modulation of these skills by circuits inspired by the functionality of the hippocampus, basal ganglia, and amygdala. The architecture also include a prospective ability whereby sensorimotor behaviours can be simulated and then used to influence the action selection in the basal ganglia. We conclude by outlining our scenario for ontogenesis based on human neo-natal development.

Download

Dynamic Vergence Using Log-Polar Images

International Journal of Computer Vision, 1997

Vergence provides robot vision systems with a crucial degree of freedom: it enables fixation of p... more Vergence provides robot vision systems with a crucial degree of freedom: it enables fixation of points in visual space at different distances from the observer. Vergence control, therefore, affects the performance of the stereo system as well as the results of motion estimation and tracking and, as such, must satisfy different requirements in order to be able to provide not only a stable fixation, but a stable binocular fusion, and a fast, smooth and accurate reaction to changes in the environment. To obtain this kind of performance the paper focuses specifically on the use of dynamic visual information to drive vergence control. In this context, moreover, the use of a space-variant, anthropomorphic sensor is described and some advantages in relation to vergence control are discussed to demonstrate the relevance of image plane geometry for this particular task. Expansion or contraction patterns and the temporal evolution of the degree of fusion measured in the log-polar domain are the inputs to the vergence control system and determine robust and accurate steering of the two cameras. Real-time experiments are presented to demonstrate the performance of the system covering different key situations.

Download

Uploads

Papers by Giulio Sandini

Log In