José María Martínez-Otzeta

On the use of Bayesian Networks to develop behaviours for mobile robots

Bayesian Networks are models which capture uncertainties in terms of probabilities that can be used to perform reasoning under uncertainty. This paper presents an attempt to use Bayesian Networks as a learning technique to manage task execution in mobile robotics. To learn the Bayesian Network structure from data, the K2 structural learning algorithm is used, combined with three different net evaluation metrics. The experiment led to a new hybrid multiclassifying system resulting from the combination of 1-NN with the Bayesian Network, that allows one to use the power of the Bayesian Network while avoiding the computational burden of the reasoning mechanism - the so-called evidence propagation process. As an application example we present an approach of the presented paradigm to implement a door-crossing behaviour in a mobile robot using only sonar readings, in an environment with smooth walls and doors. Both the performance of the learning mechanism and the experiments run in the real robot-environment system show that Bayesian Networks are valuable learning mechanisms, able to deal with the uncertainty and variability inherent to such systems.

RGB-D, Laser and Thermal Sensor Fusion for People Following in a Mobile Robot

Detecting and tracking people is a key capability for robots that operate in populated environments. In this paper, we used a multiple sensor fusion approach that combines three kinds of sensors in order to detect people using RGB-D vision, lasers and a thermal sensor mounted on a mobile platform. The Kinect sensor offers a rich data set at a significantly low cost, however, there are some limitations to its use in a mobile platform, mainly that the Kinect algorithms for people detection rely on images captured by a static camera. To cope with these limitations, this work is based on the combination of the Kinect and a Hokuyo laser and a thermopile array sensor. A real-time particle filter system merges the information provided by the sensors and calculates the position of the target, using probabilistic leg and thermal patterns, image features and optical flow to this end. Experimental results carried out with a mobile platform in a Science museum have shown that the combination of different sensory cues increases the reliability of the people following system.

Classifier hierarchy learning by means of genetic algorithms

Classifier combination falls in the so called data mining area. Its aim is to combine some paradigms from the supervised classification - sometimes with a previous non-supervised data division phase - in order to improve the individual accuracy of the component classifiers. Formation of classifier hierarchies is an alternative among the several methods of classifier combination. In this paper we present a novel method to find good hierarchies of classifiers for given databases. In this new proposal, a search is performed by means of genetic algorithms, returning the best individual according to the classification accuracy over the dataset, estimated through 10-fold cross-validation. Experiments have been carried out over 14 databases from the UCI repository, showing an improvement in the performance compared to the single classifiers. Moreover, similar or better results than other approaches, such as decision tree bagging and boosting, have been obtained.

On the use of a low-cost thermal sensor to improve Kinect people detection in a mobile robot.

Detecting people is a key capability for robots that operate in populated environments. In this paper, we have adopted a hierarchical approach that combines classifiers created using supervised learning in order to identify whether a person is in the view-scope of the robot or not. Our approach makes use of vision, depth and thermal sensors mounted on top of a mobile platform. The set of sensors is set up combining the rich data source offered by a Kinect sensor, which provides vision and depth at low cost, and a thermopile array sensor. Experimental results carried out with a mobile platform in a manufacturing shop floor and in a science museum have shown that the false positive rate achieved using any single cue is drastically reduced. The performance of our algorithm improves other well-known approaches, such as C4 and histogram of oriented gradients (HOG).

Fusing multiple image transformations and a thermal sensor with kinect to improve person detection ability

This paper proposes a novel approach to combine data from multiple low-cost sensors to detect people in a mobile robot. Robust detection of people is a key capability required for robots working in environments with people. Several works have shown the benefits of fusing data from complementary sensors. The Kinect sensor provides a rich data set at a significantly low cost, however, it has some limitations for its use on a mobile platform, mainly that people detection algorithms rely on images captured by a static camera. To cope with these limitations, this work is based on the fusion of Kinect and a thermical sensor (thermopile) mounted on top of a mobile platform. We propose the implementation of an evolutionary selection of sequences of image transformation to detect people through supervised classifiers. Experimental results carried out with a mobile platform in a manufacturing shop floor show that the percentage of wrong classified using only Kinect is drastically reduced with the classification algorithms and with the combination of the three information sources. Extra experiments are presented as well to show the benefits of the image transformation sequence idea here presented.

Dynamic selection of the best base classifier in One versus One

Class binarization strategies decompose the original multi-class problem into several binary sub-problems. One versus One (OVO) is one of the most popular class binarization techniques, which considers every pair of classes as a different sub-problem. Usually, the same classifier is applied to every sub-problem and then all the outputs are combined by some voting scheme. In this paper we present a novel idea where for each test instance we try to assign the best classifier in each sub-problem of OVO. To do so, we have used two simple Dynamic Classifier Selection (DCS) strategies that have not been yet used in this context. The two DCS strategies use K-NN to obtain the local region of the test-instance, and the classifier that performs the best for those instances in the local region, is selected to classify the new test instance. The difference between the two DCS strategies remains in the weight of the instance. In this paper we have also proposed a novel approach in those DCS strategies. We propose to use the K-Nearest Neighbor Equality (K-NNE) method to obtain the local accuracy. K-NNE is an extension of K-NN in which all the classes are treated independently: the K nearest neighbors belonging to each class are selected. In this way all the classes take part in the final decision. We have carried out an empirical study over several UCI databases, which shows the robustness of our proposal.

Laser Based People Following Behaviour in an Emergency Environment

Rescue robots have a large application potential in rescue tasks, minimizing risks and improving the human action in this kind of situations. Given the characteristics of the environment in which a rescue robot has to work, sensors may suffer damage and severe malfunctioning. This paper presents a backup system able to follow a person when camera readings are not available, but the laser sensor is still working correctly. A probabilistic model of a leg shape is implemented, along with a Kalman filter for robust tracking. This system can be useful when the robot has suffered some damage that requires it to be returned to the base for repairing.

Particle Filtering for Industrial 6DOF Visual Servoing

Visual servoing allows the introduction of robotic manipulation in dynamic and uncontrolled environments. This paper presents a position-based visual servoing algorithm using particle filtering. The objective is the grasping of objects using the 6 degrees of freedom of the robot manipulator in non-automated industrial environments using monocular vision. A particle filter has been added to the position-based visual servoing algorithm to deal with the different noise sources of those industrial environments. Experiments performed in the real industrial scenario of ROBOFOOT (http://www.robofoot.eu/) project showed accurate grasping and high level of stability in the visual servoing process.

Automatic quality inspection of percussion cap mass production by means of 3d machine vision and machine learning techniques

The exhaustive quality control is becoming very important in the worlds globalized market One of these examples where quality control becomes critical is the percussion cap mass production These elements must achieve a minimum tolerance deviation in their fabrication This paper outlines a machine vision development using a 3D camera for the inspection of the whole production of percussion caps This system presents multiple problems, such as metallic reflections in the percussion caps, high speed movement of the system and mechanical errors and irregularities in percussion cap placement Due to these problems, it is impossible to solve the problem by traditional image processing methods, and hence, machine learning algorithms have been tested to provide a feasible classification of the possible errors present in the percussion caps.

People following behaviour in an industrial enviroment using laser and stereo camera

Mobile robots have a large application potential in industrial shop floors, improving the human action in this kind of environments. The productivity can be greatly increased while reducing cost, particularly for surface operations such as material transport, survey and sampling. In this paper a system able to follow a worker in an industrial environment based on information provided by a laser scan and a stereo camera is presented. In order to accomplish this goal, a probabilistic approach for human leg detection based on data provided by a laser scan is used, enhanced with an histogram based depth detector. The proposed approach also integrates tracking techniques as Kalman Filters to endow the system with an error recovering tool to be used in a real environment.