César Peris

Grasp Feasibility Computation Based on Cascading Filters. Application to a Three Fingered Gripper

Proceedings of the Second International Conference on Informatics in Control, Automation and Robotics, 2005

A simple, yet effective approach to grasp feasibility analysis is presented. The goal is to reduc... more A simple, yet effective approach to grasp feasibility analysis is presented. The goal is to reduce the computational complexity of such process, whose complexity makes the detection of all feasible grasps for a certain object unavoidable in most occasions. The approach is based on cascading filters of increasing complexity. First, trivial filters are applied to all the grasp examples, thus rejecting all clearly unfeasible grasps with a small computational effort. Then, more complex filters are applied to a reduced number of grasps and, at the end, the full kinematics and collision detection analysis is only performed with a small subset of the grasps. An example application is presented, where the goal is to detect all the possible 2D grasps of a certain object with an articulated three-fingered hand attached to a scara robot. The vertical axis is decoupled, thus resulting in a highly redundant 7 DOF planar device. Simulation results are presented, where the reduction in computational complexity is evaluated in terms of the number of floating point operations required. Such reduction can be as high as 97% of the original computation time. An experimental setup has also been developed, with an industrial scara robot and a specifically designed articulated three-fingered gripper. The gripper has pneumatically actuated opening and closing of the fingers and electrically actuated abduction of the articulated fingers. In such experimental setup, the cascading filters approach shows a good behavior. Besides, the proposed system can be easily adapted to different robot arms and hands.

Download

Monte Carlo Localization Using SIFT Features

Lecture Notes in Computer Science, 2005

The ability of finding its situation in a given environment is crucial for an autonomous agent. W... more The ability of finding its situation in a given environment is crucial for an autonomous agent. While navigating through a space, a mobile robot must be capable of finding its location in a map of the environment (i.e. its pose < x, y, θ >), otherwise, the robot will not be able to complete its task. This problem becomes specially challenging if the robot does not possess any external measure of its global position. Typically, dead-reckoning systems do fail in the estimation of robot's pose when working for long periods of time. In this paper we present a localization method based on the Monte Carlo algorithm. During the last decade this method has been extensively tested in the field of mobile Robotics, proving to be both robust and efficient. On the other hand, our approach takes advantage from the use of a vision sensor. In particular, we have chosen to use SIFT features as visual landmarks finding them suitable for the global localization of a mobile robot. We have succesfully tested our approach in a B21r mobile robot, achieving to globally localize the robot in few iterations. The technique is suitable for office-like environments and behaves correctly in the presence of people and moving objects.

Download

Improving the Readability of Decision Trees Using Reduced Complexity Feature Extraction

Understandability of decision trees depends on two key factors: the size of the trees and the com... more Understandability of decision trees depends on two key factors: the size of the trees and the complexity of their node functions. Most of the attempts to improve the behavior of decision trees have been focused only on reducing their sizes by building the trees on complex features. These features are usually linear or non-linear functions of all the original attributes. In this paper, reduced complexity features are proposed as a way to reduce the size of decision trees while keeping understandable functions at their nodes. The proposed approach is tested on a robot grasping application where the goal is to obtain a system able to classify grasps as valid or invalid and also on three datasets from the UCI repository.

Robust Object Detection in Complex Backgrounds

This paper describes a method for recognizing real three-dimensional objects in non-controlled ba... more This paper describes a method for recognizing real three-dimensional objects in non-controlled backgrounds using independent component analysis to eliminate redundant image information present in each object image. The proposed method is a two-step process that allows a coarse color-based detection and an exact localization using shape information. The paper describes an efficient implementation, making this approach suitable for real-time applications.

3D Object Recognition from Appearance: PCA Versus ICA Approaches

Two feature extraction techniques (PCA/ICA) for recognition of 3D objects from appearance are com... more Two feature extraction techniques (PCA/ICA) for recognition of 3D objects from appearance are compared with respect to different recognition approaches (universal/object subspaces). A class separation ratio is defined, and several recognition experiments are performed using the COIL-100 database. The results show that both techniques produce similar recognition rates when universal subspaces are used; but, when object subspaces are used, ICA

Continuous navigation of a mobile robot with an appearance-based approach

Appearance-based approaches have become a feasible technique applied to robot navigation. They ar... more Appearance-based approaches have become a feasible technique applied to robot navigation. They are based on the direct comparison of images without any feature extraction. This approach presents several advantages comparing to model-based methods, such as their application to non-structured environments and the relative simplicity of the control they offer. This work presents the continuous navigation of a mobile robot, using an appearance-based method. The objective is the following of pre-recorded routes, using just visual information acquired with a couple of parallel cameras. In this approach, low-resolution frontal images along the route to follow are stored. This is done in an automated way, what allows optimizing the database size. Several control schemas have been tested to improve the accuracy in the navigation, such as P, PD and PD with variable parameters, whose experimental results are presented.

Download

Grasp feasibility computation based on cascading filters. application to a three fingered gripper

International Conference on Informatics in Control, Automation and Robotics, 2005

A simple, yet effective approach to grasp feasibility analysis is presented. The goal is to reduc... more A simple, yet effective approach to grasp feasibility analysis is presented. The goal is to reduce the computational complexity of such process, whose complexity makes the detection of all feasible grasps for a certain object unavoidable in most occasions. The approach is based on cascading filters of increasing complexity. First, trivial filters are applied to all the grasp examples, thus rejecting all clearly unfeasible grasps with a small computational effort. Then, more complex filters are applied to a reduced number of grasps and, at the end, the full kinematics and collision detection analysis is only performed with a small subset of the grasps. An example application is presented, where the goal is to detect all the possible 2D grasps of a certain object with an articulated three-fingered hand attached to a scara robot. The vertical axis is decoupled, thus resulting in a highly redundant 7 DOF planar device. Simulation results are presented, where the reduction in computational complexity is evaluated in terms of the number of floating point operations required. Such reduction can be as high as 97% of the original computation time. An experimental setup has also been developed, with an industrial scara robot and a specifically designed articulated three-fingered gripper. The gripper has pneumatically actuated opening and closing of the fingers and electrically actuated abduction of the articulated fingers. In such experimental setup, the cascading filters approach shows a good behavior. Besides, the proposed system can be easily adapted to different robot arms and hands.

Download

Continuous navigation of a mobile robot with an appearance-based approach

International Conference on Informatics in Control, Automation and Robotics, 2005

Appearance-based approaches have become a feasible technique applied to robot navigation. They ar... more Appearance-based approaches have become a feasible technique applied to robot navigation. They are based on the direct comparison of images without any feature extraction. This approach presents several advantages comparing to model-based methods, such as their application to non-structured environments and the relative simplicity of the control they offer. This work presents the continuous navigation of a mobile robot, using an appearance-based method. The objective is the following of pre-recorded routes, using just visual information acquired with a couple of parallel cameras. In this approach, low-resolution frontal images along the route to follow are stored. This is done in an automated way, what allows optimizing the database size. Several control schemas have been tested to improve the accuracy in the navigation, such as P, PD and PD with variable parameters, whose experimental results are presented.

Download

Recognition and location of real objects using eigenimages and a neural network classifier

A representation using eigenimages that achieves in two stages identify the object and locate its... more A representation using eigenimages that achieves in two stages identify the object and locate its pose is addressed.In this paper we demonstrate how a mixture of two approaches based on eigenspaces with some little modifications resolve the problem of identification and the location of the object. In the first stage we recognize the object by means of PCA* (Principal Component

3D Object Recognition from Appearance: PCA Versus ICA Approaches

Lecture Notes in Computer Science, 2004

Two feature extraction techniques (PCA/ICA) for recognition of 3D objects from appearance are com... more Two feature extraction techniques (PCA/ICA) for recognition of 3D objects from appearance are compared with respect to different recognition approaches (universal/object subspaces). A class separation ratio is defined, and several recognition experiments are performed using the COIL-100 database. The results show that both techniques produce similar recognition rates when universal subspaces are used; but, when object subspaces are used, ICA

Improving the Readability of Decision Trees Using Reduced Complexity Feature Extraction

Lecture Notes in Computer Science, 2005

Understandability of decision trees depends on two key factors: the size of the trees and the com... more Understandability of decision trees depends on two key factors: the size of the trees and the complexity of their node functions. Most of the attempts to improve the behavior of decision trees have been focused only on reducing their sizes by building the trees on complex features. These features are usually linear or non-linear functions of all the original attributes. In this paper, reduced complexity features are proposed as a way to reduce the size of decision trees while keeping understandable functions at their nodes. The proposed approach is tested on a robot grasping application where the goal is to obtain a system able to classify grasps as valid or invalid and also on three datasets from the UCI repository.

Recognition and location of real objects using eigenimages and a neural network classifier

Visual Communications and Image Processing 2003, Pts 1-3, 2003

Recognition and location of real objects using eigenimages and a neural network classifier. [Proc... more

Monte Carlo Localization Using SIFT Features

Lecture Notes in Computer Science, 2005

The ability of finding its situation in a given environment is crucial for an autonomous agent. W... more The ability of finding its situation in a given environment is crucial for an autonomous agent. While navigating through a space, a mobile robot must be capable of finding its location in a map of the environment (i.e. its pose < x, y, θ >), otherwise, the robot will not be able to complete its task. This problem becomes specially challenging if the robot does not possess any external measure of its global position. Typically, dead-reckoning systems do fail in the estimation of robot's pose when working for long periods of time. In this paper we present a localization method based on the Monte Carlo algorithm. During the last decade this method has been extensively tested in the field of mobile Robotics, proving to be both robust and efficient. On the other hand, our approach takes advantage from the use of a vision sensor. In particular, we have chosen to use SIFT features as visual landmarks finding them suitable for the global localization of a mobile robot. We have succesfully tested our approach in a B21r mobile robot, achieving to globally localize the robot in few iterations. The technique is suitable for office-like environments and behaves correctly in the presence of people and moving objects.

Download

Robust Object Detection in Complex Background using ICA Compression

This paper describes a method for recognizing real three-dimensional objects in non-controlled ba... more This paper describes a method for recognizing real three-dimensional objects in non-controlled backgrounds using independent component analysis to eliminate redundant image information present in each object image. The proposed method is a two-step process that allows a coarse color-based detection and an exact localization using shape information. The paper describes an efficient implementation, making this approach suitable for real-time applications.

Recolab: Prácticas De Control Sobre Procesos Reales Vía Internet Utilizando Matlab

ceautomatica.es

Resumen En este artículo se presentan algunos resultados y avances conseguidos en el uso de un la... more

Download

Control de enfoque de un sistema activo de visión estereoscópica

Se presenta un sistema de control de enfoque para un sistema de visión tridimensional activo, den... more

Control de enfoque de un sistema activo de visión estereoscópica

Kinematic Redundancy in Robot Grasp Synthesis. An Efficient Tree-based Representation

Proceedings of the 2005 IEEE International Conference on Robotics and Automation, 2005

A redundancy resolution technique devoted to grasp synthesis is presented. Given a set of contact... more A redundancy resolution technique devoted to grasp synthesis is presented. Given a set of contact points and a certain robot arm and gripper, the goal is to select both the best assignment of gripper fingers to contact points and the best joint values that allow the fingers to reach such contact points. The system proposed is based on the generation of an inverse kinematics tree where fast searches can be performed in order to find the optimum configuration. Optimality is defined as similarity to previously stored examples over a hierarchical structure of configuration data, which includes finger assignments and robot joints.

Simulation and Scheduling of Real-Time Computer Vision Algorithms

by Santiago Puente and César Peris

Lecture Notes in Computer Science, 1999

A fully integrated development tool for computer vision systems has been built in the framewo r k... more A fully integrated development tool for computer vision systems has been built in the framewo r k o f t h i s p a p e r . There are many applications that help the user in the design of such systems, using graphical interfaces and function libraries. Even in some cases, the nal source code can be generated by these applications. This paper goes a step beyond it allows the development of computer vision systems from a distributed environment. Besides, and as a distinctive c haracteristic with regard to other similar utilities, the system is able to automatically optimize task scheduling and assignment, depending on the available hardware.

Download

Uploads

Papers by César Peris

Log In