Steve Scheding

A Bayesian Algorithm for Simultaneous Localisation and Map Building

This paper describes a full probabilistic solution to the Simultaneous Localisation and Mapping (SLAM) problem. Previously, the SLAM problem could only be solved in real time through the use of the Kalman Filter. This generally restricts the application of SLAM methods to domains with straight-forward (analytic) environment and sensor models. In this paper the Sum-of-Gaussian (SOG) method is used to approximate more general (arbitrary) probability distributions. This representation permits the generalizations made possible by particle filter or Monte-Carlo methods, while inheriting the real-time computational advantages of the Kalman filter. The method is demonstrated by its application to sub-sea field data consisting of both sonar and visual observation of near-field landmarks.

Experiments in autonomous underground guidance

This paper presents the results of an experimental program for evaluating sensors and sensing technologies in an underground mining applications. The objective of the experiments is to infer what combinations of sensors will provide reliable navigation systems for autonomous vehicles operating in a harsh underground environment. Results from a wide range of sensors are presented and analysed. A conclusion as to the best combination of sensors is drawn.

Multisensor data fusion for underwater navigation

Abstract This paper describes a generic framework for combining information from several physically different sensors into a single composite multi-dimensional scene description. It is shown that features extracted from such a description are more robust than those extracted from a single sensor. Experimental results from an underwater vehicle are presented.

Slip modelling and aided inertial navigation of an LHD

This paper describes the theoretical development and experimental evaluation of a guidance system for an autonomous load, haul and dump truck (LHD) for use in underground mining. The particular contributions of this paper are in designing the navigation system to be able to cope with vehicle slip in rough uneven terrain using information from an inertial navigation system (INS) and a bearing only laser. Results are presented using data obtained during field trials.

Multiple target tracking using Sequential Monte Carlo Methods and statistical data association

This paper presents two approaches for the problem of multiple target tracking (MTT) and specifically people tracking. Both filters are based on sequential Monte Carlo methods (SMCM) and joint probability data association (JPDA). The filters have been implemented and tested on real data from a laser measurement system. Experiments show that both approaches are able to track multiple moving persons. A comparison of both filters is given and the advantages and disadvantages of the two approaches are presented.

Towards reliable perception for Unmanned Ground Vehicles in challenging conditions

This work aims to promote reliability and integrity in autonomous perceptual systems, with a focus on outdoor unmanned ground vehicle (UGV) autonomy. For this purpose, a comprehensive UGV system, comprising many different exteroceptive and proprioceptive sensors has been built. The first contribution of this work is a large, accurately calibrated and synchronised, multi-modal data-set, gathered in controlled environmental conditions, including the presence of dust, smoke and rain. The data have then been used to analyse the effects of such challenging conditions on perception and to identify common perceptual failures. The second contribution is a presentation of methods for mitigating these failures to promote perceptual integrity in adverse environmental conditions.

The Marulan Data Sets: Multi-sensor Perception in a Natural Environment with Challenging Conditions

In this paper we present large, accurately calibrated and time-synchronized data sets, gathered outdoors in controlled and variable environmental conditions, using an unmanned ground vehicle (UGV), equipped with a wide variety of sensors. These include four 2D laser scanners, a radar scanner, a color camera and an infrared camera. It provides a full description of the system used for data collection and the types of environments and conditions in which these data sets have been gathered, which include the presence of airborne dust, smoke and rain.

Effect of Experimental Factors on the Recognition of Affective Mental States through Physiological Measures

Reliable classification of an individuals affective state through processing of physiological response requires the use of appropriate machine learning techniques, and the analysis of how experimental factors influence the data recorded. While many studies have been conducted in this field, the effect of many of these factors is yet to be properly investigated and understood. This study investigates the relative effects of number of subjects, number of recording sessions, sampling rate and a variety of different classification approaches. Results of this study demonstrate accurate classification is possible in isolated sessions and that variation between sessions and subjects has a significant effect on classifier success. The effect of sampling rate is also shown to impact on classifier success. The results also indicate that affective space is likely to be continuous and that developing an understanding of the dimensions of this space may offer a reliable way of comparing results between subjects and studies.

Calibration of range sensor pose on mobile platforms

This paper describes a new methodology for calculating the translational and rotational offsets of a range sensor to a reference coordinate frame on the platform to which it is affixed. The technique consists of observing an environment of known or partially known geometry, from which the offsets are determined by minimizing the error between the sensed data and the known structure. Analytic results are presented which derive the necessary conditions for a successful optimisation. Practical results confirm the analysis and show that it is possible to obtain more precise results than those obtained through hand measurement.

Non-parametric Learning to Aid Path Planning over Slopes

In this paper we address the problem of closing the loop from perception to action selection for unmanned ground vehicles, with a focus on navigating slopes. A new non-parametric learning technique is presented to generate a mobility representation where the maximum feasible speed is used as a criterion to classify the world. The inputs to the algorithm are terrain gradients derived from an elevation map and past observations of wheel slip. It is argued that such a representation can aid in path planning with improved selection of vehicle heading and velocity in off-road slopes. In addition, an information theoretic test is proposed to validate a chosen proprioceptive representation (such as slip) for mobility map generation. Results of mobility map generation and its benefits to path planning are shown.