A helicopter named Dolly: Behavioural cloning for autonomous helicopter control

This paper considers the pros and cons of using behavioural cloning for the development of low-level helicopter automation modules. Over the course of this project several Behavioural cloning approaches have been investigated. The results of the most effective Behavioural cloning approach are then compared to PID modules designed for the same aircraft. The comparison takes into consideration development time, reliability, and control performance. It has been found that Behavioural cloning techniques employing local approximators and a wide state-space coverage during training can produce stabilising control modules in less time than tuning PID controllers. However, performance and reliabity deficits have been found to exist with the Behavioural Cloning, attributable largely to the time variant nature of the dynamics due to the operating environment, and the pilot actions being poor for teaching. The final conclusion drawn here is that tuning PID modules remains superior to behavioural cloning for low-level helicopter automation.

Classifying an opponent's behaviour in robot soccer

This paper illustrates the prediction of opponent behaviour in a competitive, highly dynamic, multi-agent and partially observableenvironment, namely RoboCup small size league robot soccer. The performance is illustrated in the context of the highly successful robot soccer team, the RoboRoos. The project is broken into three tasks; classification of behaviours, modelling and prediction of behaviours and integration of the predictions into the existing planning system. A probabilistic approach is taken to dealing with the uncertainty in the observations and with representing the uncertainty in the prediction of the behaviours. Results are shown for a classification system using a Naïve Bayesian Network that determines the opponent’s current behaviour. These results are compared to an expert designed fuzzy behaviour classification system. The paper illustrates how the modelling system will use the information from behaviour classification to produce probability distributions that model the manner with which the opponents perform their behaviours. These probability distributions are show to match well with the existing multi-agent planning system (MAPS) that forms the core of the RoboRoos system.

Achieving cooperation in a distributed multi-robot team

DMAPS (Distributed Multi-Agent Planning System) is a planning system developed for distributed multi-robot teams based on MAPS(Multi-Agent Planning System). MAPS assumes that each agent has the same global view of the environment in order to determine the most suitable actions. This assumption fails when perception is local to the agents: each agent has only a partial and unique view of the environment. DMAPS addresses this problem by creating a probabilistic global view on each agent by fusing the perceptual information from each robot. The experimental results on consuming tasks show that while the probabilistic global view is not identical on each robot, the shared view is still effective in increasing performance of the team.

Probabilistic visual recognition of artificial landmarks for simultaneous localization and mapping

Probabilistic robotics most often applied to the problem of simultaneous localisation and mapping (SLAM), requires measures of uncertainty to accompany observations of the environment. This paper describes how uncertainty can be characterised for a vision system that locates coloured landmarks in a typical laboratory environment. The paper describes a model of the uncertainty in segmentation, the internal cameral model and the mounting of the camera on the robot. It explains the implementation of the system on a laboratory robot, and provides experimental results that show the coherence of the uncertainty model.

Proceedings of the Eighth Australian and New Zealand Intelligent Information Systems Conference

These are the full proceedings of the conference.

The expression of conflict in computer-mediated and face-to-face groups

This study integrated the research streams of computer-mediated communication (CMC) and group conflict by comparing the expression of different types of conflict in CMC groups and face-to face (FTF) groups over time. The main aim of the study was to compare the cues-filtered-out approach against the social information processing theory A laboratory study was conducted with 39 groups (19 CMC and 20 FTF) in which members were required to work together over three sessions. The frequencies of task, process, and relationship conflict were analyzed. Findings supported the social information processing theory. There was more process and relationship conflict in CMC groups compared to FTF groups on Day 1. However, this difference disappeared on Days 2 and 3. There was no difference between CMC and FTF groups in the amount of task conflict expressed on any day.

Detection of fruit and the selection of primate visual pigments for color vision

Primates have X chromosome genes for cone photopigments with sensitivity maxima from 535 to 562 nm. Old World monkeys and apes (catarrhines) and the New World ( platyrrhine) genus Alouatta have separate genes for 535-nm ( medium wavelength; M) and 562-nm ( long wavelength; L) pigments. These pigments, together with a 425-nm ( short wavelength) pigment, permit trichromatic color vision. Other platyrrhines and prosimians have a single X chromosome gene but often with alleles for two or three M/L photopigments. Consequently, heterozygote females are trichromats, but males and homozygote females are dichromats. The criteria that affect the evolution of M/L alleles and maintain genetic polymorphism remain a puzzle, but selection for finding food may be important. We compare different types of color vision for detecting more than 100 plant species consumed by tamarins ( Saguinus spp.) in Peru. There is evidence that both frequency-dependent selection on homozygotes and heterozygote advantage favor M/L polymorphism and that trichromatic color vision is most advantageous in dim light. Also, whereas the 562-nm allele is present in all species, the occurrence of 535- to 556-nm alleles varies between species. This variation probably arises because trichromatic color vision favors widely separated pigments and equal frequencies of 535/543- and 562-nm alleles, whereas in dichromats, long-wavelength pigment alleles are fitter.

A First Order Predicate Logic Formulation of the 3D Reconstruction Problem and its Solution Space

This paper defines the 3D reconstruction problem as the process of reconstructing a 3D scene from numerous 2D visual images of that scene. It is well known that this problem is ill-posed, and numerous constraints and assumptions are used in 3D reconstruction algorithms in order to reduce the solution space. Unfortunately, most constraints only work in a certain range of situations and often constraints are built into the most fundamental methods (e.g. Area Based Matching assumes that all the pixels in the window belong to the same object). This paper presents a novel formulation of the 3D reconstruction problem, using a voxel framework and first order logic equations, which does not contain any additional constraints or assumptions. Solving this formulation for a set of input images gives all the possible solutions for that set, rather than picking a solution that is deemed most likely. Using this formulation, this paper studies the problem of uniqueness in 3D reconstruction and how the solution space changes for different configurations of input images. It is found that it is not possible to guarantee a unique solution, no matter how many images are taken of the scene, their orientation or even how much color variation is in the scene itself. Results of using the formulation to reconstruct a few small voxel spaces are also presented. They show that the number of solutions is extremely large for even very small voxel spaces (5 x 5 voxel space gives 10 to 10(7) solutions). This shows the need for constraints to reduce the solution space to a reasonable size. Finally, it is noted that because of the discrete nature of the formulation, the solution space size can be easily calculated, making the formulation a useful tool to numerically evaluate the usefulness of any constraints that are added.