Yerai Berenguer

Position Estimation and Local Mapping Using Omnidirectional Images and Global Appearance Descriptors

This work presents some methods to create local maps and to estimate the position of a mobile robot, using the global appearance of omnidirectional images. We use a robot that carries an omnidirectional vision system on it. Every omnidirectional image acquired by the robot is described only with one global appearance descriptor, based on the Radon transform. In the work presented in this paper, two different possibilities have been considered. In the first one, we assume the existence of a map previously built composed of omnidirectional images that have been captured from previously-known positions. The purpose in this case consists of estimating the nearest position of the map to the current position of the robot, making use of the visual information acquired by the robot from its current (unknown) position. In the second one, we assume that we have a model of the environment composed of omnidirectional images, but with no information about the location of where the images were acquired. The purpose in this case consists of building a local map and estimating the position of the robot within this map. Both methods are tested with different databases (including virtual and real images) taking into consideration the changes of the position of different objects in the environment, different lighting conditions and occlusions. The results show the effectiveness and the robustness of both methods.

Using Omnidirectional Vision to Create a Model of the Environment: A Comparative Evaluation of Global-Appearance Descriptors

Nowadays, the design of fully autonomous mobile robots is a key discipline. Building a robust model of the unknown environment is an important ability the robot must develop. Using this model, this robot must be able to estimate its current position and to navigate to the target points. The use of omnidirectional vision sensors is usual to solve these tasks. When using this source of information, the robot must extract relevant information from the scenes both to build the model and to estimate its position. The possible frameworks include the classical approach of extracting and describing local features or working with the global appearance of the scenes, which has emerged as a conceptually simple and robust solution. While feature-based techniques have been extensively studied in the literature, appearance-based ones require a full comparative evaluation to reveal the performance of the existing methods and to tune correctly their parameters. This work carries out a comparative evaluation of four global-appearance techniques in map building tasks, using omnidirectional visual information as the only source of data from the environment.

Monte-Carlo Workspace Calculation of a Serial-Parallel Biped Robot

This paper presents the Monte-Carlo calculation of the work-space of a biped redundant robot for climbing 3D structures. The robot has a hybrid serial-parallel architecture since each leg is composed of two parallel mechanisms connected in series. First, the workspace of the parallel mechanisms is characterized. Then, a Monte-Carlo algorithm is applied to compute the reachable workspace of the biped robot solving only the forward kinematics. This algorithm is modified to compute also the constant-orientation workspace. The algorithms have been implemented in a simulator that can be used to study the variation of the workspace when the geometric parameters of the robot are modified. The simulator is useful for designing the robot, as the examples show.

Second-order Taylor Stability Analysis of Isolated Kinematic Singularities of Closed-chain Mechanisms.

When the geometric design of a closed-chain mechanism is non-generic, the singularity locus of the mechanism may exhibit isolated points. It is well known that these isolated points are unstable since they disappear or generate/reveal cusps when the geometric design of the mechanism slightly deviates from a non-generic design, possibly affecting the ability of the mechanism to reconfigure without crossing undesirable singularities. This paper presents a method based on second-order Taylor expansions to determine how these isolated singularities transform when perturbing the different geometric parameters of a non-generic mechanism. The method consists in approximating the singularity locus by a conic section near the isolated singularity, and classifying the resulting conic in terms of the perturbations of the different geometric parameters. Two nongeneric closed-chain mechanisms are used to illustrate the presented method: an orthogonal 3R serial arm with specified position for its tip, and the planar Stewart parallel platform.

Calculation of the Boundaries and Barriers of the Workspace of a Redundant Serial-parallel Robot using the Inverse Kinematics

This paper presents the workspace analysis of a redundant serial-parallel robot. Due to the complexity of the robot, the complex constraints (joint limits and no-interference between the legs of the robot), and the globally serial structure of the robot, a discretization method based on the forward kinematics would be most appropriate to compute the workspace. However, this widely used method can only obtain the external boundaries of the workspace, missing the internal barriers that hinder the motion of the robot, which may exist inside the boundaries. To avoid missing these barriers, we use a discretization method that uses the solution of the inverse kinematic problem of the robot. By studying the feasibility of attaining a desired position and orientation by the different branches of the solution to the inverse kinematics, the proposed discretization method is able to obtain both the external boundaries and the internal barriers of the workspace. Some examples are presented to show the importance of these internal barriers in the motions of the robot inside the workspace.

Kinematic Analysis and Simulation of a Hybrid Biped Climbing Robot

This paper presents a novel climbing robot that explores 3-D truss structures for maintenance and inspection tasks. The robot is biped and has a hybrid serial-parallel architecture since each leg is composed of two parallel mechanisms connected in series. First, the forward kinematic problem of the complete robot is solved, obtaining the relative position and orientation between the feet in terms of the ten joint coordinates of the robot. The inverse kinematics is more complex due to the redundancy of the robot. Hence, a simplified inverse kinematic problem that assumes planar and symmetric movements is analyzed. Then, a tool to simulate the kinematics of the robot is presented, and it is used to demonstrate that the robot can completely explore 3-D structures, even when some movements are restricted to be planar and symmetric.

SLAM Algorithm by using Global Appearance of Omnidirectional Images.

This work presents a SLAM algorithm to estimate the position and orientation of a mobile robot while simultaneously creating the map of the environment. It uses only visual information provided by a catadioptric system mounted on the robot formed by a camera pointing towards a convex mirror. It provides the robot with omnidirectional images that contain information with a field of view of 360 degrees around the camera-mirror axis. Each omnidirectional scene acquired by the robot is described using global appearance descriptors. Thanks to their compactness, this kind of descriptors permits running the algorithm in real time. The method consists of three different steps. First, the robot calculates the pose of the robot (location and orientation) and creates a new node in the map. This map is formed by connected nodes between them. Second, it detects loop closures between the new node and the nodes of the map. Finally, the map is optimized by using an optimization algorithm and the detected loop closures. Two different sets of images have been used to test the effectiveness of the method. They were captured in two real environments, while the robot traversed two paths. The results of the experiments show the effectiveness of our method.

Movement Direction Estimation Using Omnidirectional Images in a SLAM Algorithm

This work presents a method to estimate the movement direction of a mobile robot using only visual information, without any other additional sensor. This visual information is provided by a catadioptric system mounted on the robot and formed by a camera pointing towards a convex mirror. It provides the robot with omnidirectional images that contain information with a field of view of 360\(^\circ \) around the camera-mirror axis. A SLAM algorithm is presented to test the method that estimates the movement direction of the robot. This SLAM method uses two different global appearance descriptors to calculate the orientation of the robot and the distance between two different positions. The method to calculate the movement direction is based on landmarks extraction, using SURF features. A set of omnidirectional images has been considered to test the effectiveness of this method.

A Simulation Tool for Visualizing the Assembly Modes and Singularity Locus of 3RPR Planar Parallel Robots

This paper presents a graphical and intuitive tool for simulating the forward kinematics of planar parallel 3RPR robots with arbitrary geometric design. The proposed tool allows the user to visualize the singularity locus of the robot and the evolution of all the solutions to its forward kinematic problem in the complex plane. The user can modify all the geometric design parameters of the robot and instantaneously visualize the effect of these modifications on the singularity locus. As the presented examples illustrate, the proposed tool is especially useful for visualizing the coalescence of different solutions of the forward kinematic problem when approaching higher-order singularities, as well as for visualizing how these special singularities transform when perturbing the different geometric parameters of the robot.

Generation of Data Sets Simulating Different Kinds of Cameras in Virtual Environments

In this paper a platform to create different kinds of data sets from virtual environments is presented. These data sets contain some information about the visual appearance of the environment and the distance from some reference positions to all the objects. Robot localization and mapping using images are two active fields of research and new algorithms are continuously proposed. These algorithms have to be tested with several sets of images to validate them. This task can be made using actual images; however, sometimes when a change in the parameters of the vision system is needed to optimize the algorithms, this system must be replaced and new data sets must be captured. This supposes a high cost and slowing down the first stages of the development. The objective of this work is to develop a versatile tool that permits generating data sets to test efficiently mapping and localization algorithms with mobile robots. Another advantage of this platform is that the images can be generated from any position of the environment and with any rotation. Besides, the images generated have not noise; this is an advantage since it allows carrying out a preliminary test of the algorithms under ideal conditions. The virtual environment can be created easily and modified depending on the desired characteristics. At last, the platform permits carrying out another advanced tasks using the images and the virtual environment.