Fuzzy Mediation in Shared Control and Online Learning

Abstract

This chapter presents an innovative approach to the field of information fusion. Fuzzy mediation differentiates itself from other algorithms, as this approach is dynamic in nature. The experiments reported in this work analyze the interaction of two distinct controllers as they try to maneuver an artificial agent through a path. Fuzzy mediation functions as a fusion engine to integrate the two inputs to produce a single output. Results show that fuzzy mediation is a valid method to mediate between two distinct controllers. The work reported in this chapter lays the foundation for the creation of an effective tool that uses positive feedback systems instead of negative ones to train human and nonhuman agents in the performance of control tasks.

Adaptive Fuzzy Mediation for Multimodal Control of Mobile Robots in Navigation-Based Tasks

“…The mediation can be implemented in several forms, and one of them is based on fuzzy set theory [36]. It is worth noting that several mediation engines can be used in the process, as well as several decision functions based on which the mediator infers the final decision and thus adapts the robot's behavior [18].…”

“…This implies that the used mediation had a linear mediation engine, but other mediation engines (like exponential ones) can be used as is pointed out in Ref. [18]. Thus, the shift percentage is computed as…”

“…In the field of control theory there have been approaches where more complex behavior is achieved through mediation between expert and novice controllers [18]. The ultimate goal of the mediation is to "help the autonomous capabilities of an individual .…”