Most human actions are composed of two fundamental movement types, discrete and rhythmic movements. These movement types, or primitives, are analogous to the two elemental behaviors of nonlinear dynamical systems, namely, fixed-point and limit cycle behavior, respectively. Furthermore, there is now a growing body of research demonstrating how various human actions and behaviors can be effectively modeled and understood using a small set of low-dimensional, fixed-point and limit cycle dynamical systems (differential equations). Here, we provide an overview of these dynamical motorprimitives and detail recent research demonstrating how these dynamical primitives can be used to model the task dynamics of complex multiagent behavior. More specifically, we review how a task-dynamic model of multiagent shepherding behavior, composed of rudimentary fixed-point and limit cycle dynamical primitives, can not only effectively model the behavior of cooperating human co-actors, but also reveals how the discovery and intentional use of optimal behavioral coordination during task learning is marked by a spontaneous, self-organized transition between fixed-point and limit cycle dynamics (i.e., via a Hopf bifurcation).
7 February 2018 in International Journal of Intelligent Robotics and Applications
Effective team performance often requires that individuals engage in team training exercises. However, organizing team-training scenarios presents economic and logistical challenges and can be prone to trainer bias and fatigue. Accordingly, a growing body of research is investigating the effectiveness of employing artificial agents (AAs) as synthetic teammates in team training simulations, and, relatedly, how to best develop AAs capable of robust, human-like behavioral interaction. Motivated by these challenges, the current study examined whether task dynamical models of expert human herding behavior could be embedded in the control architecture of AAs to train novice actors to perform a complex multiagent herding task. Training outcomes were compared to human-expert trainers, novice baseline performance, and AAs developed using deep reinforcement learning (DRL). Participants’ subjective preferences for the AAs developed using DRL or dynamical models of human performance were also investigated. The results revealed that AAs controlled by dynamical models of human expert performance could train novice actors at levels equivalent to expert human trainers and were also preferred over AAs developed using DRL. The implications for the development of AAs for robust human-AA interaction and training are discussed, including the potential benefits of employing hybrid Dynamical-DRL techniques for AA development.
Rapid advances in the field of Deep Reinforcement Learning (DRL) over the past several years have led to artificial agents (AAs) capable of producing behavior that meets or exceeds human-level performance in a wide variety of tasks. However, research on DRL frequently lacks adequate discussion of the low-level dynamics of the behavior itself and instead focuses on meta-level or global-level performance metrics. In doing so, the current literature lacks perspective on the qualitative nature of AA behavior, leaving questions regarding the spatiotemporal patterning of their behavior largely unanswered. The current study explored the degree to which the navigation and route selection trajectories of DRL agents (i.e., AAs trained using DRL) through simple obstacle ridden virtual environments were equivalent (and/or different) from those produced by human agents. The second and related aim was to determine whether a task-dynamical model of human route navigation could not only be used to capture both human and DRL navigational behavior, but also to help identify whether any observed differences in the navigational trajectories of humans and DRL agents were a function of differences in the dynamical environmental couplings.