Gated Recurrent Unit Based Short-Term Network for Robot Swarm Motion Forecasting

Belkacem Khaldi, Fouzi Harrou, Dairi Abdelkader, Ying Sun

Research output: Chapter in Book/Report/Conference proceedingConference contribution


This work introduces a short term forecasting gated recurrent unites framework for swarm motion speed forecasting. This is motivated by the growing need of addressing such forecasting challenges in order to keep swarm robotic systems executing daily collective operations and accomplishing tasks more successfully in groups. The framework is based on the BiGRU model and its performances is compared to its base GRU model. The framework is built upon sensor measurements collected using a simulated swarm of e-puck robots performing a simple pattern formation task in a free/no-free obstacles scenarios. Findings show how accurate BiGRU is in forecasting swarm motion speed while compared to GRU.
Original languageEnglish (US)
Title of host publication2022 IEEE 7th Forum on Research and Technologies for Society and Industry Innovation (RTSI)
ISBN (Print)978-1-6654-9740-4
StatePublished - Oct 4 2022


Dive into the research topics of 'Gated Recurrent Unit Based Short-Term Network for Robot Swarm Motion Forecasting'. Together they form a unique fingerprint.

Cite this