Developing grounded representations for robots through the principles of sensorimotor coordination

Robots currently recognise and use objects through algorithms that are hand-coded or specifically trained. Such robots can operate in known, structured environments but cannot learn to recognise or use novel objects as they appear. This thesis demonstrates that a robot can develop meaningful object representations by learning the fundamental relationship between action and change in sensory state; the robot learns sensorimotor coordination. Methods based on Markov Decision Processes are experimentally validated on a mobile robot capable of gripping objects, and it is found that object recognition and manipulation can be learnt as an emergent property of sensorimotor coordination.

Computational science for undergraduate biologists via QUT.Bio.Excel

Molecular biology is a scientific discipline which has changed fundamentally in character over the past decade to rely on large scale datasets – public and locally generated - and their computational analysis and annotation. Undergraduate education of biologists must increasingly couple this domain context with a data-driven computational scientific method. Yet modern programming and scripting languages and rich computational environments such as R and MATLAB present significant barriers to those with limited exposure to computer science, and may require substantial tutorial assistance over an extended period if progress is to be made. In this paper we report our experience of undergraduate bioinformatics education using the familiar, ubiquitous spreadsheet environment of Microsoft Excel. We describe a configurable extension called QUT.Bio.Excel, a custom ribbon, supporting a rich set of data sources, external tools and interactive processing within the spreadsheet, and a range of problems to demonstrate its utility and success in addressing the needs of students over their studies.

A Study of feature extraction algorithms for optical flow tracking

Sparse optical flow algorithms, such as the Lucas-Kanade approach, provide more robustness to noise than dense optical flow algorithms and are the preferred approach in many scenarios. Sparse optical flow algorithms estimate the displacement for a selected number of pixels in the image. These pixels can be chosen randomly. However, pixels in regions with more variance between the neighbours will produce more reliable displacement estimates. The selected pixel locations should therefore be chosen wisely. In this study, the suitability of Harris corners, Shi-Tomasi's “Good features to track", SIFT and SURF interest point extractors, Canny edges, and random pixel selection for the purpose of frame-by-frame tracking using a pyramidical Lucas-Kanade algorithm is investigated. The evaluation considers the important factors of processing time, feature count, and feature trackability in indoor and outdoor scenarios using ground vehicles and unmanned aerial vehicles, and for the purpose of visual odometry estimation.

Design for creative activity : a framework for analyzing the creative potential of computer games

This paper describes a design framework intended to conceptually map the influence that game design has on the creative activity people engage in during gameplay. The framework builds on behavioral and verbal analysis of people playing puzzle games. The analysis was designed to better understand the extent to which gameplay activities within different games facilitate creative problem solving. We have used an expert review process to evaluate these games in terms of their game design elements and have taken a cognitive action approach to this process to investigate how particular elements produce the potential for creative activity. This paper proposes guidelines that build upon our understanding of the relationship between the creative processes that players undertake during a game and the components of the game that allow these processes to occur. These guidelines may be used in the game design process to better facilitate creative gameplay activity.

Selection procedures for module discovery : exploring evolutionary algorithms for cognitive science

Evolutionary algorithms are playing an increasingly important role as search methods in cognitive science domains. In this study, methodological issues in the use of evolutionary algorithms were investigated via simulations in which procedures were systematically varied to modify the selection pressures on populations of evolving agents. Traditional roulette wheel, tournament, and variations of these selection algorithms were compared on the “needle-in-a-haystack” problem developed by Hinton and Nowlan in their 1987 study of the Baldwin effect. The task is an important one for cognitive science, as it demonstrates the power of learning as a local search technique in smoothing a fitness landscape that lacks gradient information. One aspect that has continued to foster interest in the problem is the observation of residual learning ability in simulated populations even after long periods of time. Effective evolutionary algorithms balance their search effort between broad exploration of the search space and in-depth exploitation of promising solutions already found. Issues discussed include the differential effects of rank and proportional selection, the tradeoff between migration of populations towards good solutions and maintenance of diversity, and the development of measures that illustrate how each selection algorithm affects the search process over generations. We show that both roulette wheel and tournament algorithms can be modified to appropriately balance search between exploration and exploitation, and effectively eliminate residual learning in this problem.

Real-time and interactive attacks on DNP3 critical infrastructure using Scapy

The Distributed Network Protocol v3.0 (DNP3) is one of the most widely used protocols, to control national infrastructure. Widely used interactive packet manipulation tools, such as Scapy, have not yet been augmented to parse and create DNP3 frames (Biondi 2014). In this paper we extend Scapy to include DNP3, thus allowing us to perform attacks on DNP3 in real-time. Our contribution builds on East et al. (2009), who proposed a range of possible attacks on DNP3. We implement several of these attacks to validate our DNP3 extension to Scapy, then executed the attacks on real world equipment. We present our results, showing that many of these theoretical attacks would be unsuccessful in an Ethernet-based network.

Creating good lives through computer games

In this chapter we aim to explore how videogames can lead to improvements in wellbeing. Following Keyes (2007) and Huppert and So (2012) we view wellbeing as a multidimensional concept with both hedonic and eudaimonic aspects. In this chapter we take a broad approach in terms of exploring the impact of videogames on the psychological, social, and physical components of wellbeing. We explore how videogames have been shown to have an impact in each of these domains. Although there is a great deal of evidence for the actual and potential positive impacts of videogames, there are many unanswered questions regarding the situations in which there is likely to be an impact of videogame play on wellbeing, as well as the aspects of wellbeing that are likely to be impacted by videogame play. We conclude the chapter by outlining the key questions for future research. Our focus in this chapter is on the positive influences of videogames. We do not explore research on contexts in which negative impacts are possible or subgroups for which videogames could cause harm. However, these questions are obviously important and we see balanced engagement with age-appropriate videogames as a key prerequisite for any of the wellbeing benefits discussed below.

Phobos and deimos on Mars - two autonomous robots for the DLR SpaceBot Cup

In 2013, ten teams from German universities and research institutes participated in a national robot competition called SpaceBot Cup organized by the DLR Space Administration. The robots had one hour to autonomously explore and map a challenging Mars-like environment, find, transport, and manipulate two objects, and navigate back to the landing site. Localization without GPS in an unstructured environment was a major issue as was mobile manipulation and very restricted communication. This paper describes our system of two rovers operating on the ground plus a quadrotor UAV simulating an observing orbiting satellite. We relied on ROS (robot operating system) as the software infrastructure and describe the main ROS components utilized in performing the tasks. Despite (or because of) faults, communication loss and breakdowns, it was a valuable experience with many lessons learned.

Improving robot vision models for object detection through interaction

We propose a method for learning specific object representations that can be applied (and reused) in visual detection and identification tasks. A machine learning technique called Cartesian Genetic Programming (CGP) is used to create these models based on a series of images. Our research investigates how manipulation actions might allow for the development of better visual models and therefore better robot vision. This paper describes how visual object representations can be learned and improved by performing object manipulation actions, such as, poke, push and pick-up with a humanoid robot. The improvement can be measured and allows for the robot to select and perform the `right' action, i.e. the action with the best possible improvement of the detector.

An autonomous mobile manipulator for collecting sample containers

In this work we present an autonomous mobile ma- nipulator that is used to collect sample containers in an unknown environment. The manipulator is part of a team of heterogeneous mobile robots that are to search and identify sample containers in an unknown environment. A map of the environment along with possible positions of sample containers are shared between the robots in the team by using a cloud-based communication interface. To grasp a container with its manipulator arm the robot has to place itself in a position suitable for the manipulation task. This optimal base placement pose is selected by querying a precomputed inverse reachability database.

Art and science as creative catalysts

Science, Art and Science Art collaborations are generally presented and understood in terms of their products. We argue that the process of Science art can be a significant, even principal benefit of these collaborations, even though it may be largely invisible to anyone other than the collaborators. Hosting the Centenary of Canberra Science Art Commission at the Commonwealth Scientific and Industrial Research Organisation (CSIRO) has shown us that while Science and Art pursue orthogonal dimensions of creativity and innovation, collaborators can combine these directions to access new areas of imagination and ideas.

What can game AI teach us?

Artificial intelligence (AI) applications typically involve encoding expert knowledge in machine form to find optimal solutions for a given problem. However, this paper deals with the opposite process of extracting new and human-comprehensible insights from emergent AI behaviour. Some examples of useful game-related insights drawn from observing AI players in action are presented.