Find below EMERGE’s news articles, press releases, digests of scientific publications, as well as other outreach materials.
EMERGE partner awarded a best poster at ANTS 2024
11 October 2024
The work presents a data-driven method to identify effective local actions available to faulty robots in a robotic swarm.
EMERGE partners present their work at ICRA 2024
27 September 2024
The 40th IEEE International Conference on Robotics took place in Rotterdam (NL) on September 23-26, 2024.
Publication: Safe Control of Soft Robots: Bridging Physics and Learned Models
26 September 2024
In this work, EMERGE partners from the Delft University of Technology propose that integrating learned models with model-based controllers presents a compelling alternative approach.
Publication: Designing robot swarms: a puzzle, a problem, and a mess
24 September 2024
In this work, EMERGE partners from the University of Bristol illustrate the varying complexity of designing robot swarms using a conceptual framework borrowed from organizational theory and systems thinking.
Publication: Non-dissipative Reservoir Computing Approaches for Time-Series Classification
18 September 2024
In this work, EMERGE partners from the University of Pisa study the behavior of a recently introduced class of alternative RC approaches in which the fixed dynamical component implements a stable but non-dissipative system, so that the driving temporal signal can be propagated through multiple time steps effectively.
Publication: A Data-Driven Method to Identify Fault Mitigation Strategies in Robot Swarms
15 September 2024
In this work, EMERGE partners from the University of Bristol present a data-driven method to identify effective local actions available to faulty robots in the swarm.
Publication: Decentralized Incremental Federated Learning with Echo State Networks
09 September 2024
In this work, EMERGE partners from the University of Pisa broaden the applicability of this machine learning approach to a decentralized setting, where a set of peers is connected through a logical communication topology and cannot rely on a centralized aggregation entity.
Publication: Residual Echo State Networks: Residual recurrent neural networks with stable dynamics and fast learning
07 September 2024
In this work, EMERGE partners from the University of Pisa study the architectural bias of residual connections in the context of recurrent neural networks (RNNs), specifically in the temporal dimension.
Publication: Drifting explanations in continual learning
07 September 2024
In this work, EMERGE partners from the University of Pisa and collaborators study the behavior of different explanation methods in CL and propose CLEX (ContinuaL EXplanations), an evaluation protocol to robustly assess the change of explanations in Class-Incremental scenarios, where forgetting is pronounced.
