Flow-FL: Data-Driven Federated Learning for Spatio-Temporal Predictions in Multi-Robot Systems

Abstract

In this paper, we show how the Federated Learning (FL) framework enables learning collectively from distributed data in connected robot teams. This framework typically works with clients collecting data locally, updating neural network weights of their model, and sending updates to a server for aggregation into a global model. We explore the design space of FL by comparing two variants of this concept. The first variant follows the traditional FL approach in which a server aggregates the local models. In the second variant, that we call Flow-FL, the aggregation process is serverless thanks to the use of a gossip-based shared data structure. In both variants, we use a data-driven mechanism to synchronize the learning process in which robots contribute model updates when they collect sufficient data. We validate our approach with an agent trajectory forecasting problem in a multi-agent setting. Using a centralized implementation as a baseline, we study the effects of staggered online data collection, and variations in dataflow, number of participating robots, and time delays introduced by the decentralization of the framework in a multi-robot setting.

An Overview of Federated Learning at the Edge and Distributed Ledger Technologies for Robotic and Autonomous Systems

“…Superior performance and robustness were then demonstrated in the Car Learning to Act (CARLA) simulation platform. In [87], trajectories forecasting (spatio-temporal predictions) has been performed in a multi-robot system through different FL variants: traditional FL approach where a cloud server aggregates the local models and serverless version. In the paper, the authors found that in a trajectories forecasting task, the results of the above methods are not notably different and they provided the first federated learning dataset obtained from multi-robot behaviors.…”