Press Start to Play: Classifying Multi-Robot Operators and Predicting Their Strategies through a Videogame

Abstract

One of the active challenges in multi-robot missions is related to managing operator workload and situational awareness. Currently, the operators are trained to use interfaces, but in the near future this can be turned inside out: the interfaces will adapt to operators so as to facilitate their tasks. To this end, the interfaces should manage models of operators and adapt the information to their states and preferences. This work proposes a videogame-based approach to classify operator behavior and predict their actions in order to improve teleoperated multi-robot missions. First, groups of operators are generated according to their strategies by means of clustering algorithms. Second, the operators’ strategies are predicted, taking into account their models. Multiple information sources and modeling methods are used to determine the approach that maximizes the mission goal. The results demonstrate that predictions based on previous data from single operators increase the probability of success in teleoperated multi-robot missions by 19%, whereas predictions based on operator clusters increase this probability of success by 28%.

Scheduling and Path-Planning for Operator Oversight of Multiple Robots

“…For the teleoperation of multiple agents, Farkhatdinov et al [23] proposed a discrete switching control algorithm where an operator can trigger a switch to control different robots or different inputs, i.e., position, velocity of the same agent. In [24], the authors propose modeling operator behavior in a multi-robot control task and hypothesize that these models can be used to improve the teleoperation control strategies. Alternatively, for more complex systems, the introduction of a degree of autonomy in the robots' behavior, often denoted as shared control, can enable operators to control multi-agent or complex systems [25].…”

Una revisión de los sistemas multi-robot: desafíos actuales para los operadores y nuevos desarrollos de interfaces

“…Los modelos obtenidos pueden servir para seguir el estado de la misión (redes de Petri) o para predecir su evolución futura (árboles de decisión). Por su parte, el modelado de los operadores teniendo en cuenta las misiones pasadas hace posible la predicción de sus preferencias en las misiones futuras (Roldán et al, 2019C). Cuando un operador es frecuente, el sistema dispone de suficiente información y las predicciones son más sencillas.…”