Sayonara interviews: android-human theatre

Featuring a life-like humanoid robot, Seinendan Theatre Company (Japan) brought their performance Sayonara: Android-Human Theatre to Melbourne in August 2012. Geminoid F, an android, starred alongside Canadian actress Bryerly Long, in a performance that asks the question: What does life and death mean for humans as opposed to robots?

Performance analysis using subsuming methods: an industrial case study

Large-scale object-oriented applications consist of tens of thousands of methods and exhibit highly complex runtime behaviour that is difficult to analyse for performance. Typical performance analysis approaches that aggregate performance measures in a method-centric manner result in thinly distributed costs and few easily identifiable optimisation opportunities. Subsuming methods analysis is a new approach that aggregates performance costs across repeated patterns of method calls that occur in the application's runtime behaviour. This allows automatic identification of patterns that are expensive and represent practical optimisation opportunities. To evaluate the practicality of this analysis with a real world large-scale object-oriented application we completed a case study with the developers of letterboxd.com - a social network website for movie goers. Using the results of the analysis we were able to rapidly implement changes resulting in a 54.8% reduction in CPU load and an 49.6% reduction in average response time.

Modelling human preferences for ranking and collaborative filtering: a probabilistic ordered partition approach

Learning preference models from human generated data is an important task in modern information processing systems. Its popular setting consists of simple input ratings, assigned with numerical values to indicate their relevancy with respect to a specific query. Since ratings are often specified within a small range, several objects may have the same ratings, thus creating ties among objects for a given query. Dealing with this phenomena presents a general problem of modelling preferences in the presence of ties and being query-specific. To this end, we present in this paper a novel approach by constructing probabilistic models directly on the collection of objects exploiting the combinatorial structure induced by the ties among them. The proposed probabilistic setting allows exploration of a super-exponential combinatorial state-space with unknown numbers of partitions and unknown order among them. Learning and inference in such a large state-space are challenging, and yet we present in this paper efficient algorithms to perform these tasks. Our approach exploits discrete choice theory, imposing generative process such that the finite set of objects is partitioned into subsets in a stagewise procedure, and thus reducing the state-space at each stage significantly. Efficient Markov chain Monte Carlo algorithms are then presented for the proposed models. We demonstrate that the model can potentially be trained in a large-scale setting of hundreds of thousands objects using an ordinary computer. In fact, in some special cases with appropriate model specification, our models can be learned in linear time. We evaluate the models on two application areas: (i) document ranking with the data from the Yahoo! challenge and (ii) collaborative filtering with movie data. We demonstrate that the models are competitive against state-of-the-arts.

Countering Improvised explosive devices through a multi-point haptic teleoperation system

Improvised Explosive Devices (IEDs) are reported as the number one cause of injury and death for allied troops in the current theater of operation. Current stand-off technologies for Counter IED (CIED) tasks rely on robotic platforms that have not improved in capability over the past decade to combat the ever increasing threat of IEDs. While they provide operational capability, the effectiveness of these platforms is limited. This is because they primarily utilise video and audio feedback, and require extensive training and specialist operators. Recent operational experience has demonstrated the need for robotic systems that are highly capable, yet easily operable for high fidelity manipulation. Force feedback provides an operator with more intuitive control of a robotic system. This sense of touch allows an operator to obtain a sense of feel from a stand-off location of what the robot touches or grasps through a human-robot interface. This paper reports the design and development of a Haptically-Enabled Counter IED robotic system that was funded by the Australian Defence Force. The presented work focuses on the design methodology for the system, and provides the results of the manipulator analysis and trial outcomes.