EMERGE’s findings will be communicated at scientific conferences and published in open-access journals. Find below the current list of publications.
Access all publication on the project's Zenodo community clicking here.
A Data-Driven Method to Identify Fault Mitigation Strategies in Robot Swarms
In this paper, the authors present a data-driven method to identify effective local actions available to faulty robots in the swarm.
Lee, S., Hauert, S. (2024). Swarm Intelligence. ANTS 2024. Lecture Notes in Computer Science, vol 14987. DOI: 10.1007/978-3-031-70932-6_2
A Hybrid Control Approach for a Pneumatic-Actuated Soft Robot
This paper proposes a hybrid controller for a pneumatic-actuated soft robot.
Tavio y Cabrera, E., Santina, C.D., Borja, P. (2024). In Proceedings in Advanced Robotics, vol 29. doi: 10.1007/978-3-031-55000-3_2
A memristive computational neural network model for time-series processing
In this work, the authors introduce a novel computational framework inspired by the physics of memristive devices and systems, which is embed into the context of Recurrent Neural Networks (RNNs) for time-series processing.
Veronica Pistolesi, Andrea Ceni, Gianluca Milano, Carlo Ricciardi, Claudio Gallicchio; APL Mach. Learn. 1 March 2025; 3 (1): 016117. DOI: 10.1063/5.0255168
A Protocol for Continual Explanation of SHAP
In this work, the authors study the behavior of SHAP values explanations in Continual Learning and propose an evaluation protocol to robustly assess the change of explanations in Class-Incremental scenarios.
Andrea Cossu, Francesco Spinnato, Riccardo Guidotti and Davide Bacciu, in ESANN 2023 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), doi: 10.14428/esann/2023.ES2023-41
A Provably Stable Iterative Learning Controller for Continuum Soft Robots
This letter proposes a purely feedforward iterative learning control algorithm that refines the torque action by leveraging both the knowledge of the model and data obtained from past experience.
M. Pierallini et al., IEEE Robotics and Automation Letters, vol. 8, no. 10, pp. 6427-6434, 2023, DOI: 10.1109/LRA.2023.3307007.
Adaptive LoRA Merging for Efficient Domain Incremental Learning
This paper addresses a key limitation of current merging algorithms: their overreliance on fixed weights that usually assume equal importance across tasks.
Eric Nuertey Coleman, Luigi Quarantiello, Julio Hurtado, Vincenzo Lomonaco, NeuroIPS 2024, Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning, 2024.
An Empirical Investigation on Variational Autoencoder-Based Dynamic Modeling of Deformable Objects from RGB Data
This paper explores the use of deep learning techniques to solve the nonlinear identification problem of the dynamics of continuously deformable objects and other mechanical systems analytically from first principles.
T. Coleman, R. Babuška, J. Kober and C. D. Santina, 2024 32nd Mediterranean Conference on Control and Automation (MED), Chania - Crete, Greece, 2024, pp. 921-928, doi: 10.1109/MED61351.2024.10566173.
An Experimental Study of Model-Based Control for Planar Handed Shearing Auxetics Robots
This paper presents a model-based control strategy for planar HSA robots enabling regulation in task space.
Stölzle, M., Rus, D., Della Santina, C. (2024). In Experimental Robotics. ISER 2023. Springer Proceedings in Advanced Robotics, vol 30. doi:10.1007/978-3-031-63596-0_14
An Untrained Neural Model for Fast and Accurate Graph Classification
This paper aims to explore a simple form of a randomized graph neural network inspired by the success of randomized convolutions in the 1-dimensional domain. Our idea is pretty simple: implement a no-frills convolutional graph neural network and leave its weights untrained.
Navarin, N., Pasa, L., Gallicchio, C., Sperduti, A. (2023). In Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14257. Springer, Cham. doi: 10.1007/978-3-031-44216-2_23
Anti-Symmetric DGN: a stable architecture for Deep Graph Networks
In this work, the authors present Anti-Symmetric Deep Graph Networks (A-DGNs), a framework for stable and non-dissipative DGN design, conceived through the lens of ordinary differential equations.
Gravina, A., Bacciu, D., & Gallicchio, C. (2022). Proceedings of the 11th International Conference on Learning Representations (ICLR). doi: 10.48550/arXiv.2210.09789.
Automating the Evaluation of the Scalability, Flexibility, and Robustness of Collective Behaviors for Robot Swarms
In this paper, the authors use recently proposed experimental protocols to evaluate these properties in various typical collective behaviors for robot swarms.
G. M. Madroñero Pachajoa, W. Achicanoy and D. G. Ramos, 2024 Brazilian Symposium on Robotics (SBR) and 2024 Workshop on Robotics in Education (WRE), Goiania, Brazil, 2024, pp. 144-149, doi: 10.1109/SBR/WRE63066.2024.10837963.
Awareness in Robotics: An Early Perspective from the Viewpoint of the EIC Pathfinder Challenge “Awareness Inside”
This paper summarizes and discusses the projects funded by the EIC Pathfinder Challenge “Awareness Inside” call within Horizon Europe, designed specifically for fostering research on natural and synthetic awareness.
Della Santina, C. et al. (2024). In European Robotics Forum 2024. ERF 2024. Springer Proceedings in Advanced Robotics, vol 32. doi: 10.1007/978-3-031-76424-0_20
BerryTwist: A Twisting-Tube Soft Robotic Gripper for Blackberry Harvesting
This paper introduces BerryTwist, a prototype robotic gripper specifically designed for blackberry harvesting.
J. F. Elfferich, E. Shahabi, C. D. Santina and D. Dodou, in IEEE Robotics and Automation Letters, vol. 10, no. 1, pp. 429-435, Jan. 2025, doi: 10.1109/LRA.2024.3505813.
Building Trustworthiness by Minimizing the Sim-to-Real Gap in Fault Detection for Robot Swarms
In this work, the authors implement metric extraction in a real-world environment and evaluate whether the extracted metrics can overcome the “sim-to-real gap”
Suet Lee and Sabine Hauert. 2023. In Proceedings of the First International Symposium on Trustworthy Autonomous Systems (TAS '23). Association for Computing Machinery, New York, NY, USA, Article 47, 1–3. doi: 10.1145/3597512.3597527
Calibration of Continual Learning Models
This paper provides the first empirical study of the behavior of calibration approaches in CL, showing that CL strategies do not inherently learn calibrated models.
L. Li, E. Piccoli, A. Cossu, D. Bacciu and V. Lomonaco, 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA, 2024, pp. 4160-4169, doi: 10.1109/CVPRW63382.2024.00419.
Co-perceiving: Bringing the social into perception
In this comprehensive review, the authors advocate for a broader and more mechanistic understanding of the phenomenon called co-perception.
Deroy, O., Longin, L., & Bahrami, B. (2024). WIREs Cognitive Science, e1681. doi: 10.1002/wcs.1681
Continual pre-training mitigates forgetting in language and vision
This paper investigates the characteristics of the Continual Pre-Training scenario, where a model is continually pre-trained on a stream of incoming data and only later fine-tuned to different downstream tasks.
<>br
Andrea Cossu, Antonio Carta, Lucia Passaro, Vincenzo Lomonaco, Tinne Tuytelaars, Davide Bacciu, Neural Networks, 179, 2024, 106492, doi: 10.1016/j.neunet.2024.106492.
Continuously Deep Recurrent Neural Networks
This paper introduces a new class of recurrent neural models based on a fundamentally different type of topological organization than the conventionally used deep recurrent networks, and directly inspired by the way cortical networks in the brain process information at multiple temporal scales.
Ceni, A., Dominey, P.F., Gallicchio, C., Micheli, A., Pedrelli, L., Tortorella, D. (2024). In Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2024. Lecture Notes in Computer Science(), vol 14947. doi: 10.1007/978-3-031-70368-3_4
Decentralized Incremental Federated Learning with Echo State Networks
This work broadens the applicability of Federated Echo State Networks to a decentralized setting, where we have a set of peers connected through a logical communication topology and cannot rely on a centralized aggregation entity.
G. Pompei, P. Dazzi, V. De Caro and C. Gallicchio, 2024 International Joint Conference on Neural Networks (IJCNN), Yokohama, Japan, 2024, pp. 1-8, doi: 10.1109/IJCNN60899.2024.10650756.
Deep Echo State Networks for Modelling of Industrial Systems
This paper works with an industrial plant with four water tanks, focusing on estimating the levels of two sequentially connected tanks. For this purpose, Deep Echo State Networks (Deep ESNs), within the framework of Reservoir Computing (RC), are used, representing an increasingly popular methodology for efficient learning to modelling systems with diverse time-scale dynamics.
Rodríguez-Ossorio, J.R., Gallicchio, C., Morán, A., Díaz, I., Fuertes, J.J., Domínguez, M. (2024). In Engineering Applications of Neural Networks. EANN 2024. Communications in Computer and Information Science, vol 2141. doi: 10.1007/978-3-031-62495-7_9
Deep Learning for Dynamic Graphs: Models and Benchmarks
With the aim of fostering research in the domain of dynamic graphs, this work surveys recent advantages in learning both temporal and spatial information, providing a comprehensive overview of the current state-of-the-art in the domain of representation learning for dynamic graphs.
A. Gravina and D. Bacciu, in IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2024.3379735.
Designing for Children’s Digital Well-being: An Agenda for Research, Policy and Practice
This work aims to co-create an agenda for future actions by mapping the current state-of-the-art research about children’s digital well-being.
Vicky Charisi, Nikoleta Yiannoutsou, Shuli and Gilutz, Matthew and Dennis and Shyamli Suneesh, in Proceedings of the 23rd Annual ACM Interaction Design and Children Conference, 1026–1028, 2024, doi:10.1145/3628516.3661154.
Diversifying Non-dissipative Reservoir Computing Dynamics
In this paper, the authors propose alternative formulations of the reservoirs for EuSNs, aiming at improving the diversity of the resulting dynamics.
Gallicchio, C. (2023). In Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14261. Springer, Cham. doi: 10.1007/978-3-031-44198-1_15
Drifting explanations in continual learning
This paper studies 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.
Andrea Cossu, Francesco Spinnato, Riccardo Guidotti, Davide Bacciu, Neurocomputing, 597, 2024, 127960, doi: 10.1016/j.neucom.2024.127960.
Edge of Stability Echo State Network
This paper introduces a new ESN architecture called the Edge of Stability (ESN). The introduced model is based on defining the reservoir layer as a convex combination of a nonlinear reservoir (as in the standard ESN), and a linear reservoir that implements an orthogonal transformation.
A. Ceni and C. Gallicchio, in IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2024.3400045.
EMERGE - Emergent Awareness from Minimal Collectives
This paper introduces the concept of collaborative awareness as a means to enhance interoperability, resilience and self regulation in synthetic agent collectives.
Bacciu, D. et al. (2024). In European Robotics Forum 2024. ERF 2024. Springer Proceedings in Advanced Robotics, vol 32. Springer, Cham. doi: 10.1007/978-3-031-76424-0_16
Enhancing Echo State Networks with Gradient-based Explainability Methods
This work assesses whether a weighted average of hidden states can enhance the Echo State Network performance.
Francesco Spinnato, Andrea Cossu, Riccardo Guidotti, Andrea Ceni, Claudio Gallicchio, and Davide Bacciu, SANN 2024 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium) and online event, 9-11 October 2024.
Euler State Networks: Non-dissipative Reservoir Computing
Inspired by the numerical solution of ordinary differential equations, this paper proposes a novel Reservoir Computing (RC) model, called the Euler State Network (EuSN).
Claudio Gallicchio, Neurocomputing, 579, 127411, 2024, doi: 10.1016/j.neucom.2024.127411.
Evolving and generalising morphologies for locomoting micro-scale robotic agents
This paper explores how the morphology of a multi-cellular micro-robotic agent can be optimised for reliable locomotion using artificial evolution in a stochastic environment.
Uppington, M., Gobbo, P., Hauert, S., & Hauser, H. Journal of Micro and Bio Robotics, 1-11, 2023. DOI: 10.1007/s12213-023-00155-8
Evolving Dynamic Fault Mitigation Strategies in a Robot Swarm for Collective Transportation
This paper presents a novel approach to learning dynamic fault mitigation via neuroevolution, where mitigation actions are implemented by both faulty and non-faulty robots in a collective transport scenario.
Lee, S., Hauert, S. (2025). Lecture Notes in Computer Science, vol 15612.
FinFix: A Soft Gripper With Contact-Reactive Reflex for High-Speed Pick and Place of Fragile Objects
This paper investigates using soft technology to solve the challenge of industrial automation calling for precise tasks with cycle times reduced to the minimum while maintaining accelerations low to keep interaction forces under a certain threshold to avoid damage when handling delicate products.
W. Heeringa, C. D. Santina and G. Smit, 2023 IEEE International Conference on Soft Robotics (RoboSoft), Singapore, Singapore, 2023, pp. 1-7, DOI: 10.1109/RoboSoft55895.2023.10122107.
Frappe: fast fiducial detection on low cost hardware
This paper introduces the Frappe (Fiducial Recognition Accelerated with Parallel Processing Elements) algorithm for detecting and decoding the popular ArUco tags.
Jones, S., & Hauert, S., Journal of Real-time Image Processing, 20, 119, 2023. DOI: 10.1007/s11554-023-01373-w
Gaussian Belief Propagation for Distributed Swarm Sensing
Thi paper presents how the Gaussian Belief Propagation (GBP) shows great potential as a general distributed knowledge inference algorithm for use within swarms of robots.
Simon Jones and Sabine Hauert, Gaussian Belief Propagation for Distributed Swarm Sensing, in ICRA2023 - Workshop on Distrbuted Graph Algorithms for Robotics.
Guiding Soft Robots with Motor-Imagery Brain Signals and Impedance Control
This work presents an alternative pathway towards safe and effective operation by combining wearable EEG with physically embodied safety in soft robots.
M. Stölzle, S. S. Baberwal, D. Rus, S. Coyle and C. D. Santina, in 2024 IEEE 7th International Conference on Soft Robotics (RoboSoft), San Diego, CA, USA, 2024, pp. 276-283, doi: 10.1109/RoboSoft60065.2024.10522005.
Hedonic valence at the core of consciousness: A review of “A philosophy for the science of animal consciousness” by Walter Veit
A book review of “A philosophy for the science of animal consciousness” by Walter Veit Routledge.
Meertens, N. (2024). Philosophy and the Mind Sciences, 5. doi: 10.33735/phimisci.2024.11472
Heterogeneity of Faults in a Robot Swarm: Identifying Discriminatory Metrics
This paper presents an approach to faulty state discrimination through the lens of measuring diversity: can diversity be evaluated through discrimination of states of a system, and can we identify discriminatory metrics to apply to real-time diversity evaluation?
Suet Lee and Sabine Hauert, Heterogeneity of Faults in a Robot Swarm: Identifying Discriminatory Metrics, in ICRA 2023 - Heterogeneity in Multi-Robot Systems Workshop
Human cooperation with artificial agents varies across countries
This paper examined people’s willingness to cooperate with artificial agents and humans in two classic economic games requiring a choice between self interest and mutual benefit.
Karpus, J., Shirai, R., Verba, J.T. et al. Sci Rep 15, 10000 (2025). DOI: 10.1038/s41598-025-92977-8
I Know How: Combining Prior Policies to Solve New Tasks
This paper proposes a new framework, I Know How (IKH), which provides a common formalization. Our methodology focuses on modularity and compositionality of knowledge in order to achieve and enhance agent’s ability to learn and adapt efficiently to dynamic environments.
M. Li, E. Piccoli, V. Lomonaco and D. Bacciu, 2024 IEEE Conference on Games (CoG), Milan, Italy, 2024, pp. 1-4, doi: 10.1109/CoG60054.2024.10645586.
Improving Fairness via Intrinsic Plasticity in Echo State Networks
This paper addresses the problem of algorithmic fairness in Machine Learning for temporal data, focusing on ensuring that sensitive time-dependent information does not unfairly influence the outcome of a classifier.
Andrea Ceni, Davide Bacciu, Valerio De Caro, Claudio Gallicchio, and Luca Oneto, in ESANN 2023 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), doi: 10.14428/esann/2023.ES2023-90
In-Context Interference In Chat-Based Large Language Models
This paper focuses on interference in in-context learning, examining how new knowledge affects performance in self-aware robots.
Coleman, E.N., Hurtado, J., Lomonaco, V. (2024). European Robotics Forum 2024. ERF 2024. Springer Proceedings in Advanced Robotics, vol 32. DOI: 10.1007/978-3-031-76424-0_21
Informed Machine Learning for Complex Data
This paper gathers valuable contributions and early findings in the field of Informed ML for Complex Data. Our main objective is to showcase the potential and limitations of new ideas, improvements, or the blending of ML and other research areas in solving real-world problems.
Luca Oneto, Nicolo Navarin, Alessio Micheli, Luca Pasa, Claudio Gallicchio, Davide Bacciu, Davide Anguita, Informed Machine Learning for Complex Data, in ESANN 2024 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium) and online event, 9-11 October 2024.
Input Decoupling of Lagrangian Systems via Coordinate Transformation: General Characterization and Its Application to Soft Robotics
Tthis article aims to answer the following question: Can a transformation of the generalized coordinates under which the actuators directly perform work on a subset of the configuration variables be found?
P. Pustina, C. D. Santina, F. Boyer, A. De Luca and F. Renda, in IEEE Transactions on Robotics, vol. 40, pp. 2098-2110, 2024, doi: 10.1109/TRO.2024.3370089.
Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Space
In this paper, the authors argue that a promising avenue to the efficient and effective latent-space control (i.e., control in a learned low-dimensional space) of physical systems by leveraging powerful and well-understood closed-form strategies from control theory literature in combination with learned dynamics, such as potential-energy shaping.
Maximilian Stölzle, Cosimo Della Santina. Advances in Neural Information Processing Systems 37 (NeurIPS 2024), pp. 82010-82059, 2024.
Intelligence brings responsibility - Even smart AI assistants are held responsible
This paper examines whether purely instrumental AI systems stay clear of responsibility by comparing AI-powered with non-AI-powered car warning systems and measured their responsibility rating alongside their human users.
Deroy, O., Longin, L., & Bahrami, B., Iscience, 26(8), 107494, 2023. DOI: 10.1016/j.isci. 2023.107494
Interacting with agents without a mind: the case for artificial agents
Do people attribute human traits to non-human entities without a mind, such as AI? Perceived humanness is based on the assumption that the other can act (has agency) and has experiences (thoughts and feelings). This review shows how AI fails to fully elicit these two dimensions of mind perception.
Geiselmann, R., Tsourgianni, A., Deroy, O., & Harris, L. T. (2023). Opinion in Behavioral Sciences, 51, 101282.. DOI: 10.1016/j.cobeha.2023.101282
Investigating over-parameterized randomized graph networks
This paper investigates neural models based on graph random features for classification tasks.
Giovanni Donghi, Luca Pasa, Luca Oneto, Claudio Gallicchio, Alessio Micheli, Davide Anguita, Alessandro Sperduti, Nicolò Navarin, Neurocomputing, 606, 2024, 128281, doi: 10.1016/j.neucom.2024.128281.
Learning 3D shape proprioception for continuum soft robots with multiple magnetic sensors
This letter proposes to use magnetic sensors fully integrated into the robot to achieve proprioception, and a neural architecture to make sense of the highly nonlinear relationship between the perceived intensity of the magnetic field and the shape of the robot.
T. Baaij et al., Soft Matter, vol. 19, no. 1, pp. 44–56, 2023, DOI: 10.1039/D2SM00914E.
Learning causal abstractions of linear structural causal models
This work tackles the issues of modelling causal knowledge for linear causal models with linear abstraction functions.
Riccardo Massidda, Sara Magliacane and Davide Bacciu, 2025, Learning causal abstractions of linear structural causal models, in Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence, 118, 30.
Learning Low-Dimensional Strain Models of Soft Robots by Looking at the Evolution of Their Shape with Application to Model-Based Control
This paper introduces a streamlined method for learning low-dimensional, physicsbased models that are both accurate and easy to interpret.
R. Valadas, M. Stölzle, J. Liu and C. D. Santina, 2025 IEEE 8th International Conference on Soft Robotics (RoboSoft), Lausanne, Switzerland, 2025, pp. 1-8.
Learning Multi-Reference Frame Skills from Demonstration with Task-Parameterized Gaussian Processes
This work proposes to learn such a representation without using task-specific heuristics within the context of multi-reference frame skill learning by superimposing local skills in the global frame.
M. R. Montero, G. Franzese, J. Kober and C. D. Santina, 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Abu Dhabi, United Arab Emirates, 2024, pp. 2832-2839, doi: 10.1109/IROS58592.2024.10803060.
Model-Based Control for Soft Robots With System Uncertainties and Input Saturation
This article aims at solving challenges regarding accuracy and actuation by proposing a robust model-based strategy for the shape control of soft robots with system uncertainty and input saturation.
Shao, X., Pustina, P., Stölzle, M., Sun, G., De Luca, A., Wu, L., & Della Santina, C., IEEE Transactions on Industrial Electronics, 1–10, 2023. DOI: 10.1109/TIE.2023.3303636
Model-Based Control of Soft Robots: A Survey of the State of the Art and Open Challenges
In continuum soft robotics, softness is not concentrated at the joint level but instead distributed across the whole structure. As a result, soft robots (henceforth, omitting the adjective continuum) are entirely made of continuously deformable elements.
C. Della Santina, C. Duriez and D. Rus, IEEE Control Systems Magazine, vol. 43, no. 3, pp. 30-65, 2023, DOI: 10.1109/MCS.2023.3253419.
Modelling Handed Shearing Auxetics: Selective Piecewise Constant Strain Kinematics and Dynamic Simulation
This paper proposes two key components extending discrete Cosserat rod model (DCM) to allow for modeling Handed Shearing Auxetics (HSAs) for electrically-actuated continuum soft robots.
M. Stölzle, L. Chin, R. L. Truby, D. Rus and C. D. Santina, 2023 IEEE International Conference on Soft Robotics (RoboSoft), 2023, pp. 1-8, DOI: 10.1109/RoboSoft55895.2023.10121989.
Modular Wavelength Adaptation of the Dynamic Optical MicroEnvironment
In this paper, the authors present a modular solution to allow general light sources to be used with the DOME. By switching to a high-powered near-UV light source, we show that DNA damage can be caused by the Epi-DOME's projection system at a targeted location.
N. Wijewardhane, M. Uppington, M. How, H. Hauser, E. Piddini and S. Hauert, 2023 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS), Abu Dhabi, United Arab Emirates, 2023, pp. 1-6, doi: 10.1109/MARSS58567.2023.10294114.
MultiSTOP: Solving Functional Equations with Reinforcement Learning
This paper develops MultiSTOP, a Reinforcement Learning framework for solving functional equations in physics.
Alessandro Trenta, Davide Bacciu, Andrea Cossu, Pietro Ferrero. ICLR 2024 Workshop on AI4DifferentialEquations In Science. DOI: 10.48550/arXiv.2404.14909
Nanowire Neural Networks for time-series processing
The authors introduce a novel computational framework inspired by the physics of nanowire memristive networks, which is embed into the context of Recurrent Neural Networks (RNNs) for time-series processing.
Veronica Pistolesi, Andrea Ceni, Claudio Gallicchio, Gianluca Milano, Carlo Ricciardi. NeurIPS 2024 Workshop Machine Learning with new Compute Paradigms.
Neural Autoencoder-Based Structure-Preserving Model Order Reduction and Control Design for High-Dimensional Physical Systems
This letter concerns control-oriented and structure-preserving learning of low-dimensional approximations of high-dimensional physical systems, with a focus on mechanical systems.
M. Lepri, D. Bacciu and C. D. Santina, "Neural Autoencoder-Based Structure-Preserving Model Order Reduction and Control Design for High-Dimensional Physical Systems," in IEEE Control Systems Letters, vol. 8, pp. 133-138, 2024, DOI: 10.1109/LCSYS.2023.3344286.
NiSNN-A: Noniterative Spiking Neural Network With Attention With Application to Motor Imagery EEG Classification
In this work, the authors combine spiking neural networks (SNNs) and the attention mechanisms for electroencephalogram (EEG) classification, aiming to improve precision and reduce energy consumption.
C. Zhang, W. Pan and C. D. Santina, in IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2025.3538335.
Non-dissipative Reservoir Computing Approaches for Time-Series Classification
This paper studies 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.
Gallicchio, C., Ceni, A. (2024). In Artificial Neural Networks and Machine Learning – ICANN 2024. ICANN 2024. Lecture Notes in Computer Science, vol 15025. doi: 10.1007/978-3-031-72359-9_8
Nonlinear Modes as a Tool for Comparing the Mathematical Structure of Dynamic Models of Soft Robots
This paper proposes to use the recent nonlinear extension in modal theory -called eigenmanifolds- as a means to evaluate control-oriented models for soft robots and compare them.
P. Pustina, D. Calzolari, A. Albu-Schäffer, A. D. Luca and C. D. Santina, 2024 IEEE 7th International Conference on Soft Robotics (RoboSoft), 2024, pp. 779-785, doi: 10.1109/RoboSoft60065.2024.10521987.
On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems
This paper introduces a novel perspective to address oversquashing, leveraging dynamical systems properties of global and local non-dissipativity, that enable the maintenance of a constant information flow rate.
Gravina, A., Eliasof, M., Gallicchio, C., Bacciu, D., & Schönlieb, C.-B. (2025). Proceedings of the AAAI Conference on Artificial Intelligence, 39(16), 16906-16914.
On the ethical governance of swarm robotic systems in the real world
In this paper, the authors address the question: what practices would be required for the responsible design and operation of real-world swarm robotic systems?
Alan F. T. Winfield, Matimba Swana, Jonathan Ives and Sabine Hauert. Phil. Trans. R. Soc. A.38320240142 DOI: 10.1098/rsta.2024.0142
Over-Parameterized Neural Models based on Graph Random Features for fast and accurate graph classification
This paper aims to explore a simple form of a randomized graph neural network.
Nicolò Navarin, Luca Pasa, Claudio Gallicchio, Luca Oneto, and Alessandro Sperduti, Over-Parameterized Neural Models based on Graph Random Features for fast and accurate graph classification, in "20th International Workshop on Mining and Learning with Graphs In conjunction with ECMLPKDD 2023"
Physics-Informed Neural Networks to Model and Control Robots: A Theoretical and Experimental Investigation
This work concerns the application of physics-informed neural networks to the modeling and control of complex robotic systems.
Liu, J., Borja, P. and Della Santina, C. (2024), Adv. Intell. Syst., 6: 2300385. doi: 10.1002/aisy.202300385
Piecewise Affine Curvature model: a Reduced-Order Model for Soft Robot-Environment Interaction Beyond PCC
In this work, the authors perform an analysis of the trade-off between computational treatability and modelling accuracy, and propose a new kinematic model, the Piecewise Affine Curvature (PAC).
F. Stella, Q. Guan, C. Della Santina and J. Hughes, in 2023 IEEE International Conference on Soft Robotics (RoboSoft), Singapore, Singapore, 2023, pp. 1-7, doi: 10.1109/RoboSoft55895.2023.10121939.
Prescribing Cartesian Stiffness of Soft Robots by Co-Optimization of Shape and Segment-Level Stiffness
In this work, the authors propose a strategy to prescribe variations of the physical stiffness and the robot's posture so to implement a desired Cartesian stiffness and location of the contact point.
Francesco Stella, Josie Hughes, Daniela Rus, and Cosimo Della Santina. Soft Robotics. Aug 2023. 701-712. DOI: 10.1089/soro.2022.0025.
Proprioceptive Sensing of Soft Tentacles with Model Based Reconstruction for Controller Optimization
In this work, the authors propose a new sensing approach for soft underwater slender structures based on embedded pressure sensors and use a learning-based pipeline to link the sensor readings to the shape of the soft structure.
A. Vicari et al., 2023 IEEE International Conference on Soft Robotics (RoboSoft), Singapore, Singapore, 2023, pp. 1-6, doi: 10.1109/RoboSoft55895.2023.10121999.
Quasi-Metacognitive Machines: Why We Don’t Need Morally Trustworthy AI and Communicating Reliability is Enough
This paper argues that developing morally trustworthy AI is not only unethical, as it promotes trust in an entity that cannot be trustworthy, but it is also unnecessary for optimal calibration.
Dorsch, J., Deroy, O. Philos. Technol. 37, 62 (2024). doi: 10.1007/s13347-024-00752-w.
Random Orthogonal Additive Filters: A Solution to the Vanishing/Exploding Gradient of Deep Neural Networks
A. Ceni, in IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2025.3538924.
Random Oscillators Network for Time Series Processing
This paper introduces the Random Oscillators Network (RON), a physically-inspired recurrent model derived from a network of heterogeneous oscillators.
Andrea Ceni, Andrea Cossu, Maximilian W Stölzle, Jingyue Liu, Cosimo Della Santina, Davide Bacciu, Claudio Gallicchio Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:4807-4815, 2024.
Randomly Coupled Oscillators for Time Series Processing
This paper investigates a physically-inspired recurrent neural network derived from a continuous-time ODE modelling a network of coupled oscillators.
Andrea Ceni, Andrea Cossu, Jingyue Liu, Maximilian Stölzle, Cosimo Della Santina, Claudio Gallicchio and Davide Bacciu, ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems, 2023.
Reservoir Memory Networks
This paper introduces Reservoir Memory Networks (RMNs), a novel class of Reservoir Computing (RC) models that integrate a linear memory cell with a non-linear reservoir to enhance long-term information retention.
Claudio Gallicchio and Andrea Ceni, ESANN 2024 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium) and online event, 9-11 October 2024.
Residual Echo State Networks: Residual recurrent neural networks with stable dynamics and fast learning
This paper studies the architectural bias of residual connections in the context of recurrent neural networks (RNNs), specifically in the temporal dimension.
Andrea Ceni, Claudio Gallicchio, Neurocomputing, 597, 2024, 127966, doi: 10.1016/j.neucom.2024.127966.
Residual Reservoir Computing Neural Networks for Time-series Classification
In this paper, the authors augment standard Echo State Networks (ESNs) with linear reservoir-skip connections modulated by an untrained orthogonal weight matrix.
Andrea Ceni and Claudio Gallicchio, in ESANN 2023 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), doi: 10.14428/esann/2023.ES2023-112
Shared Awareness Across Domain-Specific Artificial Intelligence: An Alternative to Domain-General Intelligence and Artificial Consciousness
This paper argues that it will not require machines to be conscious and that simpler ways of sharing awareness are sufficient.
Deroy, O., Bacciu, D., Bahrami, B., Della Santina, C. and Hauert, S. (2024), Adv. Intell. Syst., 6: 2300740. doi: 10.1002/aisy.202300740.
Singular-Perturbation Control of a Tendon-Driven Soft Robot: Theory and Experiments
This work analyzes the influence of the actuation dynamics in tendon-driven continuum soft robots performing trajectory-tracking tasks.
L. N. Ribeiro, P. Borja, C. D. Santina and B. Deutschmann, in IEEE Transactions on Control Systems Technology, doi: 10.1109/TCST.2025.3546564.
Smell Driven Navigation for Soft Robotic Arms: Artificial Nose and Control
This work proposes an artificial nose on a soft robotic arm that ensures separate smell concentration readings.
F. Piqué, F. Stella, J. Hughes, E. Falotico and C. D. Santina, 2023 IEEE International Conference on Soft Robotics (RoboSoft), Singapore, Singapore, 2023, pp. 1-7, doi: 10.1109/RoboSoft55895.2023.10122116.
Soft Robot Shape Estimation With IMUs Leveraging PCC Kinematics for Drift Filtering
This letter proposes a method to eliminate this limitation by leveraging the Piecewise Constant Curvature model assumption.
F. Stella, C. D. Santina and J. Hughes, in IEEE Robotics and Automation Letters, vol. 9, no. 2, pp. 1945-1952, Feb. 2024, doi: 10.1109/LRA.2023.3339063.
Sparse Reservoir Topologies for Physical Implementations of Random Oscillators Networks
In this paper, the authors propose 6 sparse topologies for Random Oscillators Networks (RON) and study the performance of the model across different levels of sparsity and different numbers of hidden units.
Andrea Cossu, Andrea Ceni, Davide Bacciu, and Claudio Gallicchio. 2025. In Proceedings of the 4th International Conference on AI-ML Systems (AIMLSystems '24). DOI: 10.1145/3703412.3703413
Streaming Continual Learning for Unified Adaptive Intelligence in Dynamic Environments
This paper puts forward a unified setting that harnesses the benefits of both Continual learning (CL) and streaming machine learning (SML): their ability to quickly adapt to nonstationary data streams without forgetting previous knowledge.
F. Giannini, G. Ziffer, A. Cossu and V. Lomonaco, in IEEE Intelligent Systems, vol. 39, no. 6, pp. 81-85, Nov.-Dec. 2024, doi: 10.1109/MIS.2024.3479469.
Synergy-based robotic quadruped leveraging passivity for natural intelligence and behavioural diversity
This study shows a bioinspired approach to the design of quadrupeds that seeks to exploit the body and the passive properties of the robot while maintaining active controllability on the system through minimal actuation.
Stella, F., Achkar, M.M., Della Santina, C. et al. Nat Mach Intell 7, 386–399 (2025). DOI: 10.1038/s42256-025-00988-x
Temporal Graph ODEs for Irregularly-Sampled Time Series
This work introduces the Temporal Graph Ordinary Differential Equation (TG-ODE) framework, which learns both the temporal and spatial dynamics from graph streams where the intervals between observations are not regularly spaced.
Alessio Gravina, Daniele Zambon, Davide Bacciu and Cesare Alippi, in Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24, 4025-4034, doi: 10.24963/ijcai.2024/445.
The Ethics of Terminology: Can We Use Human Terms to Describe AI?
The article challenges the justifications for the linguistic practices of for assigning human-like characteristics observed in the field of AI ethics and AI science communication.
Deroy, O, Topoi, 2023. DOI: 10.1007/s11245-023-09934-1.
The impact of labeling automotive AI as trustworthy or reliable on user evaluation and technology acceptance
This study explores whether labeling AI as either “trustworthy” or “reliable” influences user perceptions and acceptance of automotive AI technologies.
Dorsch, J., Deroy, O. Sci Rep 15, 1481 (2025). DOI:10.1038/s41598-025-85558-2
Touching with the eyes: Oculomotor self-touch induces illusory body ownership
In this work, the authors hypothesise that proprioceptive information is not necessary for self-touch modulation of body-ownership.
Antonio Cataldo, Massimiliano Di Luca, Ophelia Deroy, Vincent Hayward, Cataldo et al., iScience 26, 106180, 2023. doi: 10.1016/j.isci.2023.106180
Towards Deep Continual Workspace Monitoring: Performance Evaluation of CL Strategies for Object Detection in Working Sites
This paper utilizes a dataset tailored for continual object detection in diverse working environments. Using this dataset, a task-incremental and task-agnostic continual learning scenario was established in which each experience, corresponding to object detection sub-datasets collected from different work sites.
Aslı Çelik¸ Oguzhan Urhan, Andrea Cossu, Vincenzo Lomonaco, ESANN 2024 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium) and online event, 9-11 October 2024.
Towards Fault Mitigation in a Robot Swarm Using Neuroevolution
This paper presents a mitigation strategy using neuroevolution in a fault-discriminatory metric space and demonstrate the strategy in a realistic intralogistics use-case.
Suet Lee and Sabine Hauert, Towards Fault Mitigation in a Robot Swarm Using Neuroevolution, in ICRA 2023 - Workshop on Robot Execution Failures and Failure Management Strategies
Trimmed helicoids: an architectured soft structure yielding soft robots with high precision, large workspace, and compliant interactions
In this work, the authors propose an architectured structure based on trimmed helicoids that allows for independent regulation of the bending and axial stiffness which facilitates tuneability of the resulting soft robot properties.
Guan, Q., Stella, F., Della Santina, C. et al. Trimmed helicoids: an architectured soft structure yielding soft robots with high precision, large workspace, and compliant interactions. npj Robot 1, 4 (2023). doi: 10.1038/s44182-023-00004-7.
