Institution profile

University of Genoa

Academic institutioneurope · it
Official website
Research library217linked papers
Opportunities0open roles
Selected work

Representative Papers

Information-Theoretic Detection of Bimanual Interactions for Dual-Arm Robot Plan Generation

May 01, 2025IEEE Robotics and Automation Letters

This work addresses the challenge of efficiently generating executable plans for dual-arm robotic tasks from human demonstrations, where bimanual coordination strategies are often complex and difficult to model. The authors propose a novel approach that leverages a single RGB video demonstration to synthesize structured, modular behavior tree plans. Their method uniquely integrates Shannon information theory to analyze information flow between hands, scene graph parsing to extract action semantics, and one-shot learning to enable generalization. By unifying these components within a behavior tree framework, the approach produces adaptable execution plans without requiring extensive training data. Evaluated on both a newly curated dataset and existing public benchmarks, the method demonstrates significant performance gains over current state-of-the-art techniques, marking a notable advance in centralized bimanual coordination planning.

4 citationsRead paper

Ice-Breakers, Turn-Takers and Fun-Makers: Exploring Robots for Groups with Teenagers

Aug 29, 2022IEEE International Symposium on Robot and Human Interactive Communication

This study investigates how social robots can support adolescent group interactions to foster identity development and self-esteem. We conducted a two-week summer camp employing participatory methods—including focus groups, in-depth interviews, adolescent-led co-design sessions (10+ hours), and Wizard-of-Oz prototype testing—to systematically uncover dynamic interaction needs across ice-breaking, turn-taking, and engagement-fostering scenarios. To our knowledge, this is the first long-term, adolescent-centered co-design study of social robots for group settings. Findings reveal adolescents’ expectations of robot roles form a dynamic spectrum, necessitating adaptive functionality aligned with group developmental stages (forming → norming → performing). We identify three context-dependent core assistive functions, empirically demonstrate adolescents’ capacity to actively reinterpret and reconfigure robot roles, and propose a transferable “group–robot interaction stage model” alongside four evidence-based design principles.

4 citationsRead paper

Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis

Jun 14, 2024arXiv.org

Prior studies report contradictory findings on how over-parameterization affects neural network adversarial robustness, partly due to inconsistent attack evaluation protocols. Method: We propose a unified empirical framework that jointly assesses both the reliability of mainstream adversarial attacks (e.g., PGD, FGSM) and model robustness under controlled experimental conditions, incorporating attack effectiveness diagnostics and rigorous ablation via controlled variables. Contribution/Results: Our analysis reveals—empirically for the first time—that prior conclusions attributing reduced robustness to over-parameterization are partially confounded by unreliable attacks. When validated, effective attacks are employed, over-parameterized networks consistently exhibit significantly enhanced adversarial robustness, with statistically significant and reproducible gains across diverse settings. This work resolves a key conceptual controversy and establishes a robust empirical foundation confirming over-parameterization as a genuine robustness-enhancing factor.

2 citationsRead paper

Probabilistic NDVI Forecasting from Sparse Satellite Time Series and Weather Covariates

Feb 04, 2026arXiv.org

This study addresses the challenges of sparse and irregular satellite NDVI observations caused by cloud cover and the difficulty of short-term forecasting of crop vegetation dynamics under heterogeneous climatic conditions. The authors propose a probabilistic forecasting framework that employs a deep learning architecture to separately encode historical NDVI and meteorological observations along with future exogenous covariates, fusing multimodal information for multi-step quantile prediction. A novel temporally distance-weighted quantile loss function is introduced, complemented by feature engineering that incorporates both cumulative and extreme weather metrics, effectively capturing the delayed vegetation response to meteorological drivers and temporal uncertainty. Experiments on European satellite data demonstrate that the proposed method outperforms existing statistical, deep learning, and time series baselines in both point and probabilistic forecasting metrics, with ablation studies confirming historical NDVI as the dominant predictor and meteorological covariates providing significant performance gains.

1 citationsRead paper

On the Generalization Gap in LLM Planning: Tests and Verifier-Reward RL

Jan 20, 2026

This study investigates whether large language models (LLMs) possess transferable planning capabilities for PDDL-based tasks or merely rely on domain-specific memorization. We fine-tune a 1.7B-parameter LLM on ten IPC 2023 domains and evaluate its generalization through both in-domain and cross-domain settings. To diagnose the causes of generalization failure, we introduce three interventions: symbolic anonymization, compact plan serialization, and a verifier-reward reinforcement learning scheme leveraging the VAL validator as a reward signal—a novel contribution of this work. Experimental results show an in-domain planning success rate of 82.9%, yet performance collapses to 0% in cross-domain scenarios. Although the verifier-based reward accelerates convergence, it fails to enhance cross-domain generalization, revealing that LLMs remain highly sensitive to surface-level syntactic forms and lack genuine planning abstraction.

1 citationsRead paper
Recent publications

Latest Papers