Mário Saleiro

A Low-Cost Classroom-Oriented Educational Robotics System

Over the past few years, there has been a growing interest in using robots in education. The use of these tangible devices in combination with problem-based learning activities results in more motivated students, higher grades and a growing interest in the STEM areas. However, most educational robotics systems still have some restrictions like high cost, long setup time, need of installing software in childrens computers, etc. We present a new, low-cost, classroom-oriented educational robotics system that does not require the installation of any software. It can be used with computers, tablets or smartphones. It also supports multiple robots and the system can be setup and is ready to be used in under 5 minutes. The robotics system that will be presented has been successfully used by two classes of 3rd and 4th graders. Besides improving mathematical reasoning, the system can be employed as a motivational tool for any subject.

Biological models for active vision: towards a unified architecture

Building a general-purpose, real-time active vision system completely based on biological models is a great challenge. We apply a number of biologically plausible algorithms which address different aspects of vision, such as edge and keypoint detection, feature extraction, optical flow and disparity, shape detection, object recognition and scene modelling into a complete system. We present some of the experiments from our ongoing work, where our system leverages a combination of algorithms to solve complex tasks.

Biologically Inspired Vision for Indoor Robot Navigation

Ultrasonic, infrared, laser and other sensors are being applied in robotics. Although combinations of these have allowed robots to navigate, they are only suited for specific scenarios, depending on their limitations. Recent advances in computer vision are turning cameras into useful low-cost sensors that can operate in most types of environments. Cameras enable robots to detect obstacles, recognize objects, obtain visual odometry, detect and recognize people and gestures, among other possibilities. In this paper we present a completely biologically inspired vision system for robot navigation. It comprises stereo vision for obstacle detection, and object recognition for landmark-based navigation. We employ a novel keypoint descriptor which codes responses of cortical complex cells. We also present a biologically inspired saliency component, based on disparity and colour.

BINK : Biological Binary Keypoint Descriptor

Learning robust keypoint descriptors has become an active research area in the past decade. Matching local features is not only important for computational applications, but may also play an important role in early biological vision for disparity and motion processing. Although there were already some floating-point descriptors like SIFT and SURF that can yield high matching rates, the need for better and faster descriptors for real-time applications and embedded devices with low computational power led to the development of binary descriptors, which are usually much faster to compute and to match. Most of these descriptors are based on purely computational methods. The few descriptors that take some inspiration from biological systems are still lagging behind in terms of performance. In this paper, we propose a new biologically inspired binary keypoint descriptor: BINK. Built on responses of cortical V1 cells, it significantly outperforms the other biologically inspired descriptors. The new descriptor can be easily integrated with a V1-based keypoint detector that we previously developed for real-time applications.

Biologically Inspired Vision for Human-Robot Interaction

Human-robot interaction is an interdisciplinary research area that is becoming more and more relevant as robots start to enter our homes, workplaces, schools, etc. In order to navigate safely among us, robots must be able to understand human behavior, to communicate, and to interpret instructions from humans, either by recognizing their speech or by understanding their body movements and gestures. We present a biologically inspired vision system for human-robot interaction which integrates several components: visual saliency, stereo vision, face and hand detection and gesture recognition. Visual saliency is computed using color, motion and disparity. Both the stereo vision and gesture recognition components are based on keypoints coded by means of cortical V1 simple, complex and end-stopped cells. Hand and face detection is achieved by using a linear SVM classifier. The system was tested on a child-sized robot.

A Freehand System for the Management of Orders Picking and Loading of Vehicles

The process of picking goods from a warehouse and loading distribution vehicles is done in a systematic manner which in general corresponds to a certain order. For instance in the delivery of goods, it may be important to load the transportation vehicles in the reverse order of the customers visit, in furtherance of better accessing the products when unloading/delivering. This management can be troublesome if the human-computer interface requires the use of devices, like mouses or keyboards, which are difficult to be used under certain condition (e.g., human with dirty hands or wearing thick gloves/clothes). In this paper it is presented a proof-of-concept in the area of picking goods from a warehouse and the corresponding vehicle loading when using equipments which do not allow easy use of common human-computer interfaces. In this sense, an application using a 3D sensor was programmed to implement the human-computer interaction based on simple swipe gestures to navigate through the options, menu and their (de)selection.

A Fast Neural-Dynamical Approach to Scale-Invariant Object Detection

We present a biologically-inspired method for object detection which is capable of online and one-shot learning of object appearance. We use a computationally efficient model of V1 keypoints to select object parts with the highest information content and model their surroundings by a simple binary descriptor based on responses of cortical cells. We feed these features into a dynamical neural network which binds compatible features together by employing a Bayesian criterion and a set of previously observed object views. We demonstrate the feasibility of our algorithm for cognitive robotic scenarios by evaluating detection performance on a dataset of common household items.