arXiv subjects

Giovanni Fusco

Publications and source records attributed to Giovanni Fusco.

11 recordsLinked to original sources

arXiv2026

From Street View Imagery to Street Quality Indicators: Vision Language Inference for the Suburban 15-minute City

Streetscape quality has become a central concern in contemporary urban planning, particularly within the framework of the pedestrian-friendly 15-minute city, where walkability and public-space quality are increasingly recognized as key determinants of urban performance. However, assessing streetscape qualities across large suburban and peri-urban territories remains challenging due to the time and resource demands of conventional field surveys. This paper presents a planning-oriented assessment of streetscape qualities in the north-eastern periphery of Nice (France) using the latest release of SAGAI (Streetscape Analysis with Generative AI), an open-source workflow that leverages vision-language models (VLMs) for large-scale streetscape analysis from Google Street View imagery. The new release addresses limitations of the original framework through improved image acquisition, geographically consistent view generation, support for multiple VLM architectures, consensus-based inference, and an integrated analytical environment. The workflow is applied to several thousand street-level observations to evaluate qualities relevant to pedestrian-friendly urban environments: sidewalk presence, pedestrian entrance density, and vegetation. The resulting maps reveal that the desired streetscape qualities characterize only a fraction of today's suburban streetscapes, mainly in compact developments and traditional suburban faubourgs, while they are particularly lacking on residential hills. The analysis demonstrates the potential of contemporary VLMs to support urban diagnostics in extensive suburban territories where fieldwork would be prohibitively time-consuming. Beyond the case study, the paper illustrates how recent advances in vision-language models can contribute to evidence-based planning by enabling scalable, flexible, and interpretable assessments of urban public-space quality.

cs.CV↗

arXiv2026

UVLM: A Universal Vision-Language Model Loader for Reproducible Multimodal Benchmarking

Vision-Language Models (VLMs) have emerged as powerful tools for image understanding tasks, yet their practical deployment remains hindered by significant architectural heterogeneity across model families. This paper introduces UVLM (Universal Vision-Language Model Loader), a Google Colab-based framework that provides a unified interface for loading, configuring, and benchmarking multiple VLM architectures on custom image analysis tasks. UVLM currently supports two major model families -- LLaVA-NeXT and Qwen2.5-VL -- which differ fundamentally in their vision encoding, tokenization, and decoding strategies. The framework abstracts these differences behind a single inference function, enabling researchers to compare models using identical prompts and evaluation protocols. Key features include a multi-task prompt builder with support for four response types (numeric, category, boolean, text), a consensus validation mechanism based on majority voting across repeated inferences, a flexible token budget (up to 1,500 tokens) enabling users to design custom reasoning strategies through prompt engineering, and a built-in chain-of-thought reference mode for benchmarking. UVLM is designed for reproducibility, accessibility, and extensibility and as such is freely deployable on Google Colab using consumer-grade GPU resources. The paper also presents the first benchmarking of different VLMs on tasks of increasing reasoning complexity using a corpus of 120 street-view images.

cs.LG↗

arXiv2025

Streetscape Analysis with Generative AI (SAGAI): Vision-Language Assessment and Mapping of Urban Scenes

Streetscapes are an essential component of urban space. Their assessment is presently either limited to morphometric properties of their mass skeleton or requires labor-intensive qualitative evaluations of visually perceived qualities. This paper introduces SAGAI: Streetscape Analysis with Generative Artificial Intelligence, a modular workflow for scoring street-level urban scenes using open-access data and vision-language models. SAGAI integrates OpenStreetMap geometries, Google Street View imagery, and a lightweight version of the LLaVA model to generate structured spatial indicators from images via customizable natural language prompts. The pipeline includes an automated mapping module that aggregates visual scores at both the point and street levels, enabling direct cartographic interpretation. It operates without task-specific training or proprietary software dependencies, supporting scalable and interpretable analysis of urban environments. Two exploratory case studies in Nice and Vienna illustrate SAGAI's capacity to produce geospatial outputs from vision-language inference. The initial results show strong performance for binary urban-rural scene classification, moderate precision in commercial feature detection, and lower estimates, but still informative, of sidewalk width. Fully deployable by any user, SAGAI can be easily adapted to a wide range of urban research themes, such as walkability, safety, or urban design, through prompt modification alone.

cs.CV↗

arXiv2024

Optimal Control Problems with Vector-Valued Impulse Controls and Time Delays

We consider a nonlinear control system with vector-valued measures as controls and with dynamics depending on time delayed states. First, we introduce a notion of discontinuous, bounded variation solution associated with this system and establish an equivalent representation formula for it, inspired by the approach known in delay-free impulsive control as the `graph completions' method. Then, thanks to this equivalent formulation, we prove well-posedness properties of these solutions and also derive necessary optimality conditions in the form of a Maximum Principle for an associated minimization problem.

math.OC↗

arXiv2024

Optimal impulsive control for time delay systems

We introduce discontinuous solutions to nonlinear impulsive control systems with state time delays in the dynamics and derive necessary optimality conditions in the form of a Maximum Principle for associated optimal control problems. In the case without delays, if the measure control is scalar valued, the corresponding discontinuous state trajectory, understood as a limit of classical state trajectories for absolutely continuous controls approximating the measure, is unique. For vector valued measure controls however, the limiting trajectory is not unique and a full description of the control must include additional `attached' controls affecting instantaneous state evolution at a discontinuity. For impulsive control systems with time delays we reveal a new phenomenon, namely that the limiting state trajectory resulting from different approximations of a given measure control needs not to be unique, even in the scalar case. Correspondingly, our framework allows for additional attached controls, even though the measure control is scalar valued.

math.OC↗

arXiv2023

Impulsive optimal control problems with time delays in the drift term

We introduce a notion of bounded variation solution for a new class of nonlinear control systems with ordinary and impulsive controls, in which the drift function depends not only on the state, but also on its past history, through a finite number of time delays. After proving the well posedness of such solutions and the continuity of the corresponding input output map with respect to suitable topologies, we establish necessary optimality conditions for an associated optimal control problem. The approach, which involves approximating the problem by a non impulsive optimal control problem with time delays and using Ekeland principle combined with a recent, nonsmooth version of the Maximum Principle for conventional delayed systems, allows us to deal with mild regularity assumptions and a general endpoint constraint.

math.OC↗

arXiv2023

A Lie-bracket-based notion of stabilizing feedback in optimal control

For a control system two major issues can be considered: the stabilizability with respect to a given target, and the minimization of an integral functional (while the trajectories reach this target). Here we consider a problem where stabilizability or controllability are investigated together with the further aim of a "cost regulation", namely a state-dependent upper bounding of the functional. This paper is devoted to a crucial step in the program of establishing a chain of equivalences among degree-k stabilizability with regulated cost, asymptotic controllability with regulated cost, and the existence of a degree-k Minimum Restraint Function (which is a special kind of Control Lyapunov Function). Besides the presence of a cost we allow the stabilizing "feedback" to give rise to directions that range in the union of original directions and the family of iterated Lie bracket of length less or equal to $k$. In the main result asymptotic controllability [resp. with regulated cost] is proved to be necessary for degree-k stabilizability [resp. with regulated cost]. Further steps of the above-mentioned logical chain are proved in companion papers, so that also a Lyapunov-type inverse theorem -- i.e. the possibility of deriving existence of a Minimum Restraint Function from stabilizability -- appears as quite likely.

math.OC↗

arXiv2023

HJ inequalities involving Lie brackets and feedback stabilizability with cost regulation

With reference to an optimal control problem where the state has to approach asymptotically a closed target while paying a non-negative integral cost, we propose a generalization of the classical dissipative relation that defines a Control Lyapunov Function to a weaker differential inequality. The latter involves both the cost and the iterated Lie brackets of the vector fields in the dynamics up to a certain degree k greater than or equal to 1, and we call any of its (suitably defined) solutions a degree-k Minimum Restraint Function. We prove that the existence of a degree-k Minimum Restraint Function allows us to build a Lie-bracket-based feedback which sample stabilizes the system to the target while regulating (i.e., uniformly bounding) the cost.

math.OC↗

arXiv2021

Configurational Approaches to Urban Form: Empirical Test on the City of Nice (France)

Configurational analysis can be seen as the adaptation to urban space of complex network approaches already developed in social network analysis (Freeman 1979). Its central idea is that elements of urban form should be analysed with respect to the relationships that they establish with all other form elements within a given scale of analysis. In twenty years of research on urban form using configurational analysis, a certain variety of approaches and of more specific techniques has been developed. The main goal of this paper is to give a systematic overview of the different techniques and approaches and to test selected techniques in their ability to recognise different urban forms within the city of Nice, France.

physics.soc-ph↗

arXiv2021

Nondegenerate abnormality, controllability, and gap phenomena in optimal control with state constraints

In optimal control theory, infimum gap means that there is a gap between the infimum values of a given minimum problem and an extended problem, obtained by enlarging the set of original solutions and controls. The gap phenomenon is somewhat "dual" to the problem of the controllability of the original control system to an extended solution. In this paper we present sufficient conditions for the absence of an infimum gap and for controllability for a wide class of optimal control problems subject to endpoint and state constraints. These conditions are based on a nondegenerate version of the nonsmooth constrained maximum principle, expressed in terms of subdifferentials. In particular, under some new constraint qualification conditions, we prove that: (i) if an extended minimizer is a nondegenerate normal extremal, then no gap shows up; (ii) given an extended solution verifying the constraints, either it is a nondegenerate abnormal extremal, or the original system is controllable to it. An application to the impulsive extension of a free end-time, non-convex optimization problem with control-polynomial dynamics illustrates the results.

math.OC↗

arXiv2020

No infimum gap and normality in optimal impulsive control under state constraints

In this paper we consider an impulsive extension of an optimal control problem with unbounded controls, subject to endpoint and state constraints. We show that the existence of an extended-sense minimizer that is a normal extremal for a constrained Maximum Principle ensures that there is no gap between the infima of the original problem and of its extension. Furthermore, we translate such relation into verifiable sufficient conditions for normality in the form of constraint and endpoint qualifications. Links between existence of an infimum gap and normality in impulsive control have previously been explored for problems without state constraints. This paper establishes such links in the presence of state constraints and of an additional ordinary control, for locally Lipschitz continuous data.

math.OC↗