RESEARCH

CURRENT RESEARCH PROJECTS

Developing Responsive and Adaptive Artificial-Agents for Team Training.

Human Performance Research Network (HPRnet) Project, Australian Department of Defence

Teams form the fundamental structure of military forces and effective team training is therefore critical for mission success. Such training requires that training scenarios include intact teams and promote self-guided learning via simulated mission contexts. A major challenge to engaging in such training is ensuring that sufficient numbers of active duty personnel are able to participate, and team training programs are tailored to the individual needs of trainees. One way to overcome these challenges is to incorporate artificial agents (AAs) within the training context.

The effectiveness of human-AA team training depends on the ability of AAs to adapt to human co-actors in a seamless manner. In order to enhance real-world outcomes, AAs must also incorporate natural, human-like patterns of behavioural action, decision-making, and communication. As such, ensuring effective human-AA team training requires modelling the behavioural dynamics of successful human performance and then implementing these models within the control architecture of AAs.

According, the proposed project has two primary research AIMS:

AIM 1: Demonstrate how human performance and communication within complex team settings can be modelled using a hierarchical framework of dynamical action and decision-making primitives and generative deep-learning based NLP methods.

AIM 2: Demonstrate how hierarchical models of complex human performance and communication (composed of dynamical action and decision-making primitives, and deep-learning based NLP methods) can be employed to develop AAs capable of effective team training within tactical action and command-and-control task contexts.

COLLABORATORS: Rachel Kallen (Macquarie University), Mark Dras (Macquarie University, Computing), Erik Reichle (Macquarie University), Patrick Nalepka (Macquarie University), Chris Best (DST), Simon Hosking (DST)

HDR STUDENTS and RAs: Fred Amouzgar, Matt Prants, Lillian Rigoli, James Simpson.

Modelling human perceptual-motor interaction for human-machine applications.

ARC Future Fellowship Project

The project aims to develop a new modelling framework for identifying the perceptual-motor processes that underlie cooperative and competitive human interaction. The project will also determine whether this modelling framework can be combined with modern machine-learning methods to develop artificial agents capable of human level performance. Expected outcomes will include a practical methodology for rapidly generating models of effective human interaction that can be easily implemented in human-machine systems. Benefits will include a richer understanding of the fundamental perceptual-motor processes that support robust human interaction and enhanced the effectiveness of human-machine collaboration and training technologies.

Advances in cyber-technology have created new opportunities for human-machine interaction. Developing artificial agents that can naturally respond to the movements and actions of human actors is essential for the success of such systems and requires identifying and modelling the perceptual-motor processes that underlie cooperative and competitive social activity. This project will identify these processes and produce a practical methodology for implementing them in interactive artificial agents. The project outcomes will be applicable across a range of research and industrial settings, and will therefore have social and economic benefits and strengthen Australia’s international standing in human-machine interaction research and development.

COLLABORATORS: Rachel Kallen (Macquarie University), Gaurav Patil (Macquarie University), Patrick Nalepka (Macquarie University), Mario di Bernardo (University of Naples Federico II, Itlay), Elliot Salztman (Boston University), Maurice Lamb (University of Skovde, Sweden), Tamara Lorenz (University of Cincinnati)

HDR STUDENTS and RAs: Lillian Rigoli, James Simpson, Cassandra Crone

Self-Organized Interpersonal Anticipation and Anticipatory Synchronization

Time-Delay Coupling and Temporal Feedback delays can Enhance Joint-Action Anticipatory Coordination

Recent research in physics has uncovered evidence to suggest that small temporal feedback delays may actually enhance (rather than hinder) an individual’s ability to synchronize with unpredictable, chaotic events. This counter intuitive phenomenon is referred to as self-organized anticipatory coordination. We have been exploring whether the lawful process of self-organized anticipatory coordination might also underlie the ability of individuals to anticipate the complex and seemingly unpredictable behaviors of co-actors during social interaction. We are also exploring whether dynamical and computational models that incorporate small time-delay coupling functions are able to foster and enhance anticipatory behavior during human-machine interaction.

COLLABORATORS: Auriel Washburn (Stanford University), Rachel Kallen (Macquarie University), Kevin Shockley (USA, Psychology) and Nigel Stepp (HRL Laboratories, CA), Gaurav Patil (Macquarie University)

SELECT PUBLICATIONS:

Washburn, A., Kallen, R. W., Lamb, M., Stepp, N., Shockley, K., & Richardson, M. J. (2019). Feedback delays can enhance anticipatory synchronization in human-machine interaction. PloS one, 14(8).

Washburn, A., Kallen, R. W., Shockley, K., & Richardson, M. J. (2015). Harmony from Chaos: Anticipatory Synchronization and Complexity Matching in Aperiodic Interpersonal Coordination. Journal of Experimental Psychology: Human Perception and Performance. DOI:10.1037/xhp0000080

Embedded Multi-Agent Dynamics

Modeling the Behavioral Dynamics of Social Action and Coordination. NIH - National Institute of General Medical Sciences Project

A fundamental feature of social behavior is face-to-face, co-present interaction. The success of such interactions, whether measured in terms of social connection, goal achievement, or the ability of an individual or group of individuals to know and predict the meaningful intentions and behaviors of others, is not only dependent on the neural and representational processes of social cognition and perception, but also on the physical (environmental) and perceptual-motor processes that make such face-to-face and co-present interaction possible. A primary goal of my research program is to model the complex dynamics of such goal-directed social and multi-agent activity, in an attempt to explain how the dynamics of such behavioral activity is an emergent and self-organized consequence of the complex interactions that exist between physical, neural, informational, and social properties. This involves developing dynamical and computational models of the temporal and spatial patterns of social interaction and coordination across a wide range of prototypical social and multi-agent behaviors.

COLLABORATORS: Rachel Kallen (Macquarie University), R. C. Schmidt (College of the Holy Cross), Dr. Elliot Saltzman (Boston University), Steven J. Harrison (University of Connecticut), Maurice Lamb (); Patrick Nalpeka (Macquarie University); Anthony Chemero (University of Cincinnati)

HDR STUDENTS and RAs: Lillian Rigoli

SELECT PUBLICATIONS:

Nalepka, P., Lamb, M., Kallen, R. W., Shockley, K., Chemero, A., Saltzman, E., & Richardson, M. J. (2019). Human social motor solutions for human–machine interaction in dynamical task contexts. Proceedings of the National Academy of Sciences, 201813164.

Lamb, M., *Nalepka, P., Kallen, R. W., Lorenz, T., Harrison, S. J., Minai, A. A., & Richardson, M. J. (2019). A Hierarchical Behavioral Dynamic Approach for Naturally Adaptive Human-Agent Pick-and-Place Interactions. Complexity, p1-16, DOI: 10.1155/2019/5964632

Lamb, M., Kallen, R. W., Harrison, S. J., Di Bernardo, M., Minai, A., & Richardson, M. J. (2017). To Pass or Not to Pass: Modeling the Movement and Affordance Dynamics of a Pick and Place Task. Frontiers in Psychology, 8

Nalepka, P., Kallen, R. W., Chemero, A., Saltzman, E., & Richardson, M .J. (2017). Herd Those Sheep: Emergent multiagent coordination and behavioral mode switching. Psychological Science. DOI: 10.1177/0956797617692107.

Richardson, M., Kallen, R., Nalepka, P., Harrison, S., Lamb, M., Chemero, A., Saltzman, E. and Schmidt, R. (2016). Modeling Embedded Interpersonal and Multiagent Coordination. In Proceedings of the 1st International Conference on Complex Information Systems (COMPLEXIS 2016), pp.155-164.

Richardson, M. J., Harrison, S. J., Kallen, R. W., Walton, A., Eiler, B., & Schmidt, R. C. (2015). Self-Organized Complementary Coordination: Dynamics of an Interpersonal Collision-Avoidance Task. Journal of Experimental Psychology: Human Perception and Performance. 41, 665-79.