Rafael Arnay

Using Kinect on an Autonomous Vehicle for Outdoors Obstacle Detection

An accurate method to detect obstacles and dangerous areas is the key to the safe performance of autonomous robots. Time of flight sensors can report their existence through the emission, reflection, and measurement of wave patterns, but large wavelength light projection is often unreliable in outdoors environments, due to solar radiation contamination. In this paper, a specific Microsoft Kinect arrangement on a robotic vehicle is proposed, such that outdoors detection is possible. The main contribution of this paper is the description of a sequence of filtering techniques, which translate the depth image provided by the sensor into definite obstacle projections in the navigability map used by the vehicle. A series of experiments proves that the Kinect device is more accurate at detecting obstacles using this procedure than a camera pair using two different stereovision techniques.

Real-time adaptive obstacle detection based on an image database

Abstract In this paper, an innovative method for the detection and avoidance of obstacles is presented. This is based on image registration techniques. The aim of this method is the detection of the possible obstacles that could be in the route where VERDINO (an autonomous electrical vehicle which is going to work in the surroundings of a bioclimatic urbanization as part of the SAGENIA project) navigates. The obstacle detection is one of the most critical parts of the prototype. It is responsible for the detection and later avoidance of the pedestrians, cars, etc. that can damage it or be damaged by the prototype. The algorithm is able to work in real time, with good detection rates and a fast response. It also includes a dynamical database that will allow the vehicle to learn adaptively the current state of the environment, rejecting old images. With this, some of the typical problems related to the image registration techniques are removed. Some examples and results are provided, corroborating the good behavior of the algorithm, which has been tested in simulated and real conditions. The method is also applicable to other tasks, like surveillance for non-stationery cameras or other applications over very different kinds of images.

Applying an Ant Colony Optimization Algorithm to an Artificial Vision Problem in a Robotic Vehicle

In this paper, a problem of artificial vision in a robotic autonomous vehicle consisting of the real time detection and tracking of non-structured roads is addressed by applying an Ant Colony Optimization (ACO) algorithm. The solution adopted tries to find some properties describing the probability that a pixel belongs to the boundaries of the road, and then formalize the road detection problem as an optimization one.

Teaching kinematics with interactive schematics and 3D models

In this paper, some computer applications for teaching forward and inverse kinematics in Robotics are presented. These applications, developed in Unity3D and Python, allow both teachers and students to create and manipulate 3D interactive representations of the studied robotic models. The use of these tools has been proved to help students improve their understanding of the geometric transformations and mathematical operations required to solve both forward and inverse kinematics exercises.

Ant Colony Optimization-based method for optic cup segmentation in retinal images

Graphical abstractDisplay Omitted HighlightsFast and reliable Ant Colony Optimization method for optic cup segmentation.The heuristic information is composed of intensity gradients and vessels curvature information.Using the pheromone trails, the agents achieve good segmentations even in situations where the pallor is weak or non-obvious. An accurate detection of the cup region in retinal images is necessary to obtain relevant measurements for glaucoma detection. In this work, we present an Ant Colony Optimization-based method for optic cup segmentation in retinal fundus images. The artificial agents will construct their solutions influenced by a heuristic that combines the intensity gradient of the optic disc area and the curvature of the vessels. On their own, the exploration capabilities of the agents are limited; however, by sharing the experience of the entire colony, they are capable of obtaining accurate cup segmentations, even in images with a weak or non-obvious pallor. This method has been tested with the RIM-ONE dataset, yielding an average overlapping error of 24.3% of the cup segmentation and an area under the curve (AUC) of 0.7957 using the cup to disc ratio for glaucoma assessment.

Fusion of a Variable Baseline System and a Range Finder

One of the greatest difficulties in stereo vision is the appearance of ambiguities when matching similar points from different images. In this article we analyze the effectiveness of using a fusion of multiple baselines and a range finder from a theoretical point of view, focusing on the results of using both prismatic and rotational articulations for baseline generation, and offer a practical case to prove its efficiency on an autonomous vehicle.

Towards a Multiagent Approach for the VERDINO Prototype

This paper presents a work in progress about the design and development of a multiagent system for an autonomous vehicle (VERDINO). This vehicle (a standard golf cart) has been provided with many different sensors and actuators. The future multiagent system is intended to manage the data provided by the sensors and act on steering orientation and brake and throttle pedals.

A Machine Learning Based System for Analgesic Drug Delivery

Monitoring pain and finding more efficient methods for analgesic administration during anaesthesia is a challenge that attracts the attention of both clinicians and engineers. This work focuses on the application of Machine Learning techniques to assist the clinicians in the administration of analgesic drug. The problem will consider patients undergoing general anaesthesia with intravenous drug infusion. The paper presents a preliminary study based on the use of the signal provided by an analgesia monitor, the Analgesia Nociception Index (ANI) signal. One aim of this research is studying the relation between ANI monitor and the changes in drug titration made by anaesthetist. Another aim is to propose an intelligent system that provides decisions on the drug infusion according to the ANI evolution. To do that, data from 15 patients undergoing cholecystectomy surgery were analysed. In order to establish the relationship between ANI and the analgesic, Machine Learning techniques have been introduced. After training different types of classifier and testing the results with cross validation method, it has been demonstrated that a relation between ANI and the administration of remifentanil can be found.

Safe and reliable navigation in crowded unstructured pedestrian areas

In this paper, the navigation system of the autonomous vehicle prototype Verdino is introduced. Two navigation levels are considered. In the first level, a trajectory is generated from the current position toward a goal that considers two different approaches. In the first, the minimum cost path is obtained using a classical approach (used for regular navigation). The second approach is a little more complex, relying on a set of precomputed primitives representing the motion model of the vehicle, which are used as part of an ARA* algorithm in order to find the best trajectory. This trajectory consists of both forward and backward motion segments for complex maneuvers. In the second level, a local planner is in charge of computing the commands sent to the vehicle in order to follow the trajectory. A set of tentative local trajectories is computed in the Frenet space and scored using several factors, described in this paper. Some results for the two navigation levels are shown at the end of this document. For the global planner, several examples of the maneuvers obtained are shown and certain related factors are quantified and compared. As for the local planner, a study on the influence of the defined weights on the vehicles final behavior is presented. Also, from these tests several configurations have been chosen and ranked according to two different proposed behaviors. The navigation system shown has been tested both in simulated and in real conditions, and the attached video shows the vehicles real-world performance. Graphical abstractDisplay Omitted HighlightsA navigation system has been developed for an autonomous vehicle.The autonomous vehicle can navigate along unstructured and crowded environments.Two planning levels are used, considering two approaches for the first one.The system has been successfully tested in real conditions, results shown.

Detection of Non-structured Roads Using Visible and Infrared Images and an Ant Colony Optimization Algorithm

In this paper, the problem of road detection on unstructured environments is mapped as an optimization one, and an Ant Colony Optimmization algorithm is applied to solve it. This allows that the artificial agents make up for the lack of edge input information with their common memory. This common memory contains the paths followed by the entire colony. From an intuitive point of view, it can be said that in the areas where no edge information can be obtained, the agents will construct pheromone bridges (to the next edge detected pixels), that will allow them to continue constructing their solution, achieving this way a robust road detection. The input information for the algorithm will consist in images captured by cameras in the visible and in the infrared spectrums. Some features of the roads that are wanted to be detected make that in some cases the information from the visible spectrum is more useful than the information from the infrared spectrum while in other cases the infrared ones are more useful. This is why both sources of data are used to improve the global performance of the proposed method.