Favio R. Masson

Simultaneous localization and map building using natural features and absolute information

Abstract This work presents real time implementation algorithms of Simultaneous Localization and Map Building (SLAM) with emphasis to outdoor land vehicle applications in large environments. It presents the problematic of outdoors navigation in areas with combination of feature and featureless regions. The aspect of feature detection and validation is investigated to reliably detect the predominant features in the environment. Aided SLAM algorithms are presented that incorporate absolute information in a consistent manner. The SLAM implementation uses the compressed filter algorithm to maintain the map with a cost proportional to number of landmarks in the local area. The information gathered in the local area requires a full SLAM update when the vehicle leaves the local area. Algorithms to reduce the full update computational cost are also presented. Finally, experimental results obtained with a standard vehicle running in unstructured outdoor environment are presented.

Navigation and Mapping in Large Unstructured Environments

In this paper we address the problem of autonomous navigation in very large unstructured environments. A new hybrid metric map (HYMM) structure is presented that combines feature maps with other metric representations in a consistent manner. The global feature map is partitioned into a set of connected local triangular regions (LTRs), which provide a reference for a detailed multidimensional description of the environment. The HYMM framework permits the combination of efficient feature-based simultaneous localization and mapping (SLAM) algorithms for localization with, for example, occupancy grid maps for tasks such as obstacle avoidance, path planning or data association. This fusion of feature and grid maps has several complementary properties; for example, grid maps can assist data association and can facilitate the extraction and incorporation of new landmarks as they become identified from multiple vantage points. In this paper we also present a path-planning technique that efficiently maintains the estimated cost of traversing each LTR. The consistency of the SLAM algorithm is investigated with the introduction of exploration techniques to guarantee a certain measure of performance for the estimation process. Experimental results in outdoor environments are presented to demonstrate the performance of the algorithms proposed.

Robust Simultaneous Localization and Mapping for Very Large Outdoor Environments

This paper addresses the problem of Simultaneous Localization and Mapping (SLAM) when working in very large environments. A Hybrid architecture is presented that makes use of the Extended Kalman Filter to perform SLAM in a very efficient form and a Monte Carlo type filter to resolve the data association problem potentially present when returning to a known location after a large exploration task. The proposed algorithm incorporates significant integrity to the standard SLAM algorithms by providing the ability to handle multimodal distributions in real time. Experimental results in outdoor environments are presented to demonstrate the performance of the algorithm proposed.

Hybrid architecture for simultaneous localization and map building in large outdoor areas

This paper address the problem of navigating in very large outdoor unstructured environments. It presents solutions to the problem of closing large loops in simultaneous localization and map building applications. A hybrid architecture is presented that make use of the extended Kalman filter to perform SLAM in an efficient form and a Monte Carlo type filter to resolve the data association problem present when closing large loops. The proposed algorithm incorporates integrity to the standard SLAM algorithms by allowing multimode distribution to be handled in real time. Experimental results in outdoor environments are also presented.

Hybrid sensor network and fusion algorithm for sound source localization

In this paper, we present a network composed of two-different types of nodes for the task of sound source localization. One of the nodes is a low-power A-scale (dbA) logarithmic sound pressure level sensing (SPLS) unit, and the other is a bearing estimator sensing (BES) unit based on a cross-correlation approach. The sensor boards are mounted on MICADOT nodes, therefore, they are wireless connected. An information fusion algorithm collects the information provided by five SPLS units and one BES unit and provides an estimation of the location of the target. Field results collected from the experiment are shown.

Improving vehicle safety using context based detection of risk

When mining vehicle operators take risks, there is a increased probability of an accident that can cause injuries, fatalities and large financial costs to the mine operators. It can be assumed that the operators do not intentially take unnecessarily high risk, and that the risks are hidden due to factors such as adverse weather, fatigue, visual obstructions, boredom, etc. This paper examines the potential of measuring the risk of danger in a situation by using the safe rules of operation defined by mining safety management. The problem with measuring safety is that the safe rules of operation are heavily dependent on the context of the situation. What is considered normal practice and safe in one part of the mine (such as performing a u-turn in a parking lot) is not safe on a haul road. To be able to measure safety, it is therefore necessary to understand the different context areas in a mine so that feedback of unsafe behaviour presented to the operator is relevant to the context of the situation. This paper presents a novel method for generating context area information using the vehicle trajectory information collected from vehicles in the mine. Results are presented using real-life data collected from several operating fleets of mining vehicles.

Range Based Localisation Using RF and the Application to Mining Safety

This paper describes the derivation and experimental validation of a novel sensor model for radio frequency sensors to be used for localisation purposes. A comprehensive description of the modelling aspects is presented. Outdoor range only tracking results using the newly derived model are fully described with a comparison to the free space model commonly used for radio frequency applications. Although this approach is applicable for generic localisation purposes in indoor and outdoor environments, it is of fundamental importance when applied to proximity detection involving large machines. In particular in environments such as mining, stevedoring and construction there is a need to detect the presence of personnel in close proximity to machines. A close proximity system that makes use of the newly derived model is presented working with a 100 tons mining haul truck

Robust Navigation and Mapping Architecture for Large Environments

AbstractThis paper addresses the problem of Simultaneous Localization and Mapping (SLAM) for very largeenvironments. A Hybrid architecture is presented that makes use of the Extended Kalman Filter toperform SLAM in a very efficient form and a Monte Carlo localiser to resolve data association problemspotentially present when returning to a known location after a large exploration period. Algorithmsto improve the convergence of the Monte Carlo filter are presented that consider vehicle and sensoruncertainty. The proposed algorithm incorporates significant integrity to the standard SLAM algorithmsby providing the ability to handle multimodal distributions over robot pose in real time while themapping process is on hold. Experimental results in outdoor environments are presented to demonstratethe performance of the algorithm proposed.KeywordsBayes Estimation, Bootstrap Filter, SLAM, Navigation I. IntroductionReliable autonomous navigation in highly unstructured outdoor environments presentsformidable problems in terms of sensing, perception and navigation algorithms [1]. Theproblem of localization given a map of the environment or estimating the map knowingthe vehicle position is known to be a solved problem and has been in fact applied in manyresearch and industrial applications [2] [3]. Outdoor environments present additionalchallenges due to the lack of sensors and perception algorithms that can work reliably inall environments and under all weather conditions.This is starting to change with sensors like Laser and Radars capable of returning 2-Dand 3-D reliable and consistent information and with important progress in perceptionalgorithms [4] [5]. Once the sensing and perception problem is addressed, the localizationproblem can be solved using a number of approaches. Some methods are based on thenon-linear version of the Kalman Filter, the Extended Kalman Filter (EKF). Othermethods use approximations of the probabilistic density of the states conditioned to themeasures obtained. These approaches can be classified into three categories: the mixtureof densities [6], the grid based methods [7] and the Monte Carlo methods [8].2

Using Delayed Observations for Long-Term Vehicle Tracking in Large Environments

The tracking of vehicles over large areas with limited position observations is of significant importance in many industrial applications. This paper presents algorithms for long-term vehicle motion estimation based on a vehicle motion model that incorporates the properties of the working environment and information collected by other mobile agents and fixed infrastructure collection points. The prediction algorithm provides long-term estimates of vehicle positions using speed and timing profiles built for a particular environment and considering the probability of a vehicle stopping. A limited number of data collection points distributed around the field are used to update the estimates, with negative information (no communication) also used to improve the prediction. This paper introduces the concept of observation harvesting, a process in which peer-to-peer communication between vehicles allows egocentric position updates to be relayed among vehicles and finally conveyed to the collection point for an improved position estimate. Positive and negative communication information is incorporated into the fusion stage, and a particle filter is used to incorporate the delayed observations harvested from vehicles in the field to improve the position estimates. The contributions of this work enable the optimization of fleet scheduling using discrete observations. Experimental results from a typical large-scale mining operation are presented to validate the algorithms.

Using Absolute Non-Gaussian Non-White Observations in Gaussian SLAM

In the navigation context it is typical the presence of sensors that introduce uncertainties that cannot be modeled as white Gaussian noise. Such measures cannot be directly used in gaussian estimators. This paper presents a technique that allows the consistent processing of this type of measurements in combination with a standard EKF estimator. The method can be applied in an efficient implementation of SLAM based on a Gaussian estimator.