Shrihari Vasudevan

Heteroscedastic Gaussian processes for data fusion in large scale terrain modeling

This paper presents a novel approach to data fusion for stochastic processes that model spatial data. It addresses the problem of data fusion in the context of large scale terrain modeling for a mobile robot. Building a model of large scale and complex terrain that can adequately handle uncertainty and incompleteness in a statistically sound manner is a very challenging problem. To obtain a comprehensive model of such terrain, typically, multiple sensory modalities as well as multiple data sets are required. This work uses Gaussian processes to model large scale terrain. The model naturally provides a multi-resolution representation of space, incorporates and handles uncertainties appropriately and copes with incompleteness of sensory information. Gaussian process regression techniques are applied to estimate and interpolate (to fill gaps in unknown areas) elevation information across the field. In this work, the GP modeling approach is extended to fuse multiple, multi-modal data sets to obtain a best estimate of the elevation given the individual data sets. The individual data sets are treated as different noisy samples of the same underlying terrain. Experiments performed on sparse GPS based survey data and dense laser scanner data taken at mine-sites are reported.

Gaussian Process modeling of large scale terrain

This paper addresses the problem of large scale terrain modeling for a mobile robot. Building a model of large scale terrain data that can adequately handle uncertainty and incompleteness in a statistically sound way is a very challenging problem. This work proposes the use of Gaussian Processes as models of large scale terrain. The proposed model naturally provides a multi-resolution representation of space, incorporates and handles uncertainties aptly and copes with incompleteness of sensory information. Gaussian Process Regression techniques are applied to estimate and interpolate (to fill gaps in unknown areas) elevation information across the field. The estimates obtained are the best linear unbiased estimates for the data under consideration. A single Non-Stationary (Neural Network) Gaussian Process is shown to be powerful enough to model large and complex terrain, handling issues relating to discontinuous data effectively. A local approximation methodology based on KD-Trees is also proposed in order to ensure local smoothness and yet preserve the characteristic features of rich and complex terrain data. The use of the local approximation technique based on KD-Trees further addresses concerns relating to the scalability of the proposed approach for large data sets. Experiments performed on sparse GPS based survey data as well as dense laser scanner data taken at different mine-sites are reported in support of these claims.

Data fusion with Gaussian processes

This paper addresses the problem of fusing multiple sets of heterogeneous sensor data using Gaussian processes (GPs). Experiments on large scale terrain modeling in mining automation are presented. Three techniques in increasing order of model complexity are discussed. The first is based on adding data to an existing GP model. The second approach treats data from different sources as different noisy samples of a common underlying terrain and fusion is performed using heteroscedastic GPs. The final approach, based on dependent GPs, models each data set by a separate GP and learns spatial correlations between data sets through auto and cross covariances. The paper presents a unifying view of approaches to data fusion using GPs, a statistical evaluation that compares these approaches and multiple previously untested variants of them and an insight into the effect of model complexity on data fusion. Experiments suggest that in situations where data being fused is not rich enough to require a complex GP data fusion model or when computational resources are limited, the use of simpler GP data fusion techniques, which are constrained versions of the more generic models, reduces optimization complexity and consequently can enable superior learning of hyperparameters, resulting in a performance gain.

Non-stationary dependent Gaussian processes for data fusion in large-scale terrain modeling

Obtaining a comprehensive model of large and complex terrain typically entails the use of both multiple sensory modalities and multiple data sets. This paper demonstrates the use of dependent Gaussian processes for data fusion in the context of large scale terrain modeling. Specifically, this paper derives and demonstrates the use of a non-stationary kernel (Neural Network) in this context. Experiments performed on multiple large scale (spanning about 5 sq km) 3D terrain data sets obtained from multiple sensory modalities (GPS surveys and laser scans) demonstrate the approach to data fusion and provide a preliminary demonstration of the superior modeling capability of Gaussian processes based on this kernel.

Evaluation of Three Vision Based Object Perception Methods for a Mobile Robot

This paper addresses visual object perception applied to mobile robotics. Being able to perceive household objects in unstructured environments is a key capability in order to make robots suitable to perform complex tasks in home environments. However, finding a solution for this task is daunting: it requires the ability to handle the variability in image formation in a moving camera with tight time constraints. The paper brings to attention some of the issues with applying three state of the art object recognition and detection methods in a mobile robotics scenario, and proposes methods to deal with windowing/segmentation. Thus, this work aims at evaluating the state-of-the-art in object perception in an attempt to develop a lightweight solution for mobile robotics use/research in typical indoor settings.

Large-scale terrain modeling from multiple sensors with dependent Gaussian processes

Terrain modeling remains a challenging yet key component for the deployment of ground robots to the field. The difficulty arrives from the variability of terrain shapes, sparseness of the data, and high degree uncertainty often encountered in large, unstructured environments. This paper presents significant advances to data fusion for stochastic processes modeling spatial data, demonstrated in large-scale terrain modeling tasks. We explore dependent Gaussian processes to provide a multi-resolution representation of space and associated uncertainties, while integrating sensors from different modalities. Experiments performed on multiple multi-modal datasets (3D laser scans and GPS) demonstrate the approach for terrains of about 5 km2.

Information fusion in multi-task Gaussian process models

This paper evaluates heterogeneous information fusion using multi-task Gaussian processes in the context of geological resource modeling. Specifically, it empirically demonstrates that information integration across heterogeneous information sources leads to superior estimates of all the quantities being modeled, compared to modeling them individually. Multi-task Gaussian processes provide a powerful approach for simultaneous modeling of multiple quantities of interest while taking correlations between these quantities into consideration. Experiments are performed on large scale real sensor data.

Bearing and gear failure detection for brushless DC motors with adaptive feature extraction and classification

This paper presents a novel approach to adaptively select features for early fault detection on bearings and gears connected to brushless DC motors (BLDCM). Multisensor data are collected using a state-of-the-art testing platform to induce faults on BLDCMs with time varying conditions. Due to the high number of features and sensor channels available, determining the right data to identify faults can be a daunting task to achieve. A series of gears and bearings are tested. An algorithm using adaptive selection of features is proposed to improve fault detection. A benchmark data set is built containing multi-sensing data for different fault scenarios for BLDCMs with time varying conditions. The algorithm presented in this work is applied on measurements data to be included in the data set.

Condition monitoring of brushless DC motors with non-stationary dynamic conditions

This work introduces a new multi-sensor measurement framework for condition monitoring of brushless DC motors (BLDCM) with bearings. An experimental platform for equipment health monitoring is used for producing different faults on BLDCMs and log the measurement data. This work is oriented to maximize the life-cycle of industrial machinery and prevent catastrophic failures and their environmental consequences through reliable behavior classification. A public benchmark data set containing key failure scenarios is being built based on this work. This data set will be unique with respect to other available data sets due to the different sensors used and include more extensive scenarios such as non-stationary (time varying) conditions. A BLDCM with a bearing is tested under non-stationary conditions, and the scenario for their failure is developed. Supervised learning classifiers such as back propagation neural network and support vector machine are used to identify the fault state in the equipment.

A Mine on Its Own

This article presents a study of Gaussian process (GP) models applied to the problems of modeling and data fusion in the context of large-scale terrain modeling. The proposed model naturally provides a multiresolution representation of space, incorporates and handles uncertainties aptly, and copes with incompleteness of sensory information. These attributes are considered essential to support most field robotics applications, including autonomous mining. GP regression techniques are applied to estimate and interpolate (to fill gaps in occluded areas) elevation information across the field. GP approximation methods are introduced to enable the application of the proposed techniques to large data sets. To obtain a comprehensive model of complex terrain, typically, multiple sensory modalities and multiple data sets are required. The GP modeling approach is consequently extended to fuse multiple, multimodal data sets to obtain a best estimate of the elevation given the individual data sets. Two different GP-based concepts are applied to perform data fusion-heteroscedastic GPs and dependent GPs (DGPs). Thus, this article presents a report on an ongoing study of the use of GPs and several GPbased concepts to the problem of large-scale terrain modeling in the context of mining automation.