Brian R. Duffy

Anthropomorphism and the social robot

This paper discusses the issues pertinent to the development of a meaningful social interaction between robots and people through employing degrees of anthropomorphism in a robot’s physical design and behaviour. As robots enter our social space, we will inherently project/impose our interpretation on their actions similar to the techniques we employ in rationalising, for example, a pet’s behaviour. This propensity to anthropomorphise is not seen as a hindrance to social robot development, but rather a useful mechanism that requires judicious examination and employment in social robot research.

Revisiting Histograms and Isosurface Statistics

Recent results have shown a link between geometric properties of isosurfaces and statistical properties of the underlying sampled data. However, this has two defects: not all of the properties described converge to the same solution, and the statistics computed are not always invariant under isosurface-preserving transformations. We apply Federers Coarea Formula from geometric measure theory to explain these discrepancies. We describe an improved substitute for histograms based on weighting with the inverse gradient magnitude, develop a statistical model that is invariant under isosurface-preserving transformations, and argue that this provides a consistent method for algorithm evaluation across multiple datasets based on histogram equalization. We use our corrected formulation to reevaluate recent results on average isosurface complexity, and show evidence that noise is one cause of the discrepancy between the expected figure and the observed one.

On Histograms and Isosurface Statistics

In this paper, we show that histograms represent spatial function distributions with a nearest neighbour interpolation. We confirm that this results in systematic underrepresentation of transitional features of the data, and provide new insight why this occurs. We further show that isosurface statistics, which use higher quality interpolation, give better representations of the function distribution. We also use our experimentally collected isosurface statistics to resolve some questions as to the formal complexity of isosurfaces

Agent chameleons: agent minds and bodies

Agent design has to date concerned itself with the issues pertaining to a single body embedded in a single environment, whether virtual or real. This paper discusses the notion of an agent capable of migrating between information spaces (physical worlds, virtual reality, and digital information spaces). An architecture is presented that facilitates agent migration and mutation within such environments. This will in turn support agent evolution the ultimate in agent adaptivity.

Robots Social Embodiment in Autonomous Mobile Robotics

This work aims at demonstrating the inherent advantages of embracing a strong notion of social embodiment in designing a real-world robot control architecture with explicit “intelligent” social behaviour between a collective of robots. It develops the current thinking on embodiment beyond the physical by demonstrating the importance of social embodiment. A social framework develops the fundamental social attributes found when more than one robot co-inhabit a physical space. The social metaphors of identity, character, stereotypes and roles are presented and implemented within a real-world social robot paradigm in order to facilitate the realisation of explicit social goals.

Maintaining the identity of dynamically embodied agents

Virtual agents are traditionally constrained in their embodiment, as they are restricted to one form of body. We propose allowing them to change their embodiment in order to expand their capabilities. This presents users with a number of difficulties in maintaining the identity of the agents, but these can be overcome by using identity cues, certain features that remain constant across embodiment forms. This paper outlines an experiment that examines these identity cues, and shows that they can be used to help address this identity problem.

Social interaction between robots, avatars & humans

With the recent development of the field of social robotics and in particular the need to negotiate explicit social interaction and behaviour between both socially capable robots and between robots and humans, this work presents the development of a framework which supports coherent social interaction between real and artificial systems. The social robot architecture is implemented in conjunction with the virtual robotic workbench, a cohesive framework which integrates physical robots, virtual robot avatars and humans in a shared social space.

Agent Chameleons: Virtual Agents Real Intelligence

Agent Chameleons provides virtual agents powered by real intelligence, delivering next generation autonomic entities that can seamlessly migrate, mutate and evolve on their journey between and within physical and digital information spaces.

Social situated agents in virtual, real and mixed reality environments

This paper details a framework for explicit deliberative control of socially and physically situated agents in virtual, real and mixed reality environments. The objective is to blur the traditional boundaries between the real and the virtual and provide a standardized methodology for intelligent agent control specifically designed for social interaction. The architecture presented in this paper embraces the fusion between deliberative social reasoning mechanisms and explicit tangible behavioural mechanisms for human-agent social interaction.

Future reasoning machines: mind and body

Purpose – In investing energy in developing reasoning machines of the future, one must abstract away from the specific solutions to specific problems and ask what are the fundamental research questions that should be addressed. This paper aims to revisit some fundamental perspectives and promote new approaches to reasoning machines and their associated form and function.Design/methodology/approach – Core aspects are discussed, namely the one‐mind‐many‐bodies metaphor as introduced in the agent Chameleon work. Within this metaphor the agents embodiment form may take many guises with the artificial mind or agent potentially exhibiting a nomadic existence opportunistically migrating between a myriad of instantiated embodiments. The paper animates these concepts with reference to two case studies.Findings – The two case studies illustrate how a machine can have fundamentally different capabilities than a human which allows us to exploit, rather than be constrained, by these important differences.Originality/...