User profile-driven large-scale multi-agent learning from demonstration in federated human-robot collaborative environments

TL;DR

This paper introduces a novel user profile-driven approach for large-scale multi-agent learning from demonstration in federated human-robot environments, leveraging deep learning to model and interpret human behavior for improved collaboration.

Contribution

It extends federated learning for multi-agent systems by integrating a hierarchical user profile with deep learning models to enhance behavior understanding and adaptation.

Findings

Enhanced modeling of human behavior using LSTM and autoencoders.

Improved adaptation to human feedback in federated learning.

Effective long-term analysis of human states and psychophysiological data.

Abstract

Learning from Demonstration (LfD) has been established as the dominant paradigm for efficiently transferring skills from human teachers to robots. In this context, the Federated Learning (FL) conceptualization has very recently been introduced for developing large-scale human-robot collaborative environments, targeting to robustly address, among others, the critical challenges of multi-agent learning and long-term autonomy. In the current work, the latter scheme is further extended and enhanced, by designing and integrating a novel user profile formulation for providing a fine-grained representation of the exhibited human behavior, adopting a Deep Learning (DL)-based formalism. In particular, a hierarchically organized set of key information sources is considered, including: a) User attributes (e.g. demographic, anthropomorphic, educational, etc.), b) User state (e.g. fatigue detection, stress detection, emotion recognition, etc.) and c) Psychophysiological measurements (e.g. gaze, electrodermal activity, heart rate, etc.) related data. Then, a combination of Long Short-Term Memory (LSTM) and stacked autoencoders, with appropriately defined neural network architectures, is employed for the modelling step. The overall designed scheme enables both short- and long-term analysis/interpretation of the human behavior (as observed during the feedback capturing sessions), so as to adaptively adjust the importance of the collected feedback samples when aggregating information originating from the same and different human teachers, respectively.