REXASI-PRO
  • About
    • Partners
    • Work Packages
    • Outcomes
  • Use Cases
  • Trustworthiness
  • Networks
  • News
Seleziona una pagina
Towards Reliable Predictions under Adversarial Attacks: Introducing Verifiably Robust Conformal Prediction (VRCP)

Towards Reliable Predictions under Adversarial Attacks: Introducing Verifiably Robust Conformal Prediction (VRCP)

da Benedetta Chicca | Giu 5, 2025 | Uncategorized

At NeurIPS 2024, we introduced Verifiably Robust Conformal Prediction (VRCP) — a new framework that brings statistical reliability and provable robustness to conformal prediction under adversarial attacks. Conformal Prediction (CP) is a widely-used technique for...
Formal Guarantees for Memoryful Neural Agents in Multi-Agent Systems

Formal Guarantees for Memoryful Neural Agents in Multi-Agent Systems

da Benedetta Chicca | Mag 29, 2025 | Uncategorized

A novel verification framework empowers formal reasoning over recurrent neural multi-agent systems under non-determinism and uncertainty. We recently presented a novel framework at AAMAS 2025 that enables the verification of neural multi-agent systems with memory,...
Cybersecurity for Safety: Risk Assessment of Autonomous Cyber-Physical Systems

Cybersecurity for Safety: Risk Assessment of Autonomous Cyber-Physical Systems

da Benedetta Chicca | Apr 7, 2025 | Uncategorized

Recent developments in Artificial Intelligence and Industry 4.0 have led to a new generation of autonomous Cyber-Physical Systems (CPSs), including self-driving cars, unmanned aerial vehicles, and multi-robot systems, possibly operating in critical environments. With...
Experimental Evaluation of Road-Crossing Decisions by Autonomous Wheelchairs against Environmental Factors

Experimental Evaluation of Road-Crossing Decisions by Autonomous Wheelchairs against Environmental Factors

da Benedetta Chicca | Mar 12, 2025 | Uncategorized

Safe road crossing by autonomous wheelchairs can be affected by several environmental factors such as adverse weather conditions influencing the accuracy of artificial vision. Previous studies have addressed experimental evaluation of multi-sensor information fusion...
The Orchestrator: how to manage different agents in a way that is useful for the end user

The Orchestrator: how to manage different agents in a way that is useful for the end user

da Benedetta Chicca | Feb 3, 2025 | Uncategorized

The REXASI-PRO project involves coordinating various agents to create a collaborative environment that is both efficient, safe and useful for the end user. A central orchestrator has been developed to manage information from the field and provide decision-making...
« Post precedenti
Post successivi »

Recent Posts

  • From the Demo Days to the General Assembly, last important steps towards the conclusion of the project
  • Multi-agent navigation: communication
  • Multi-agent navigation: learning
  • Multi-agent navigation: simulation
  • For a real-time person detection on resource-constrained robotic platforms and embedded systems

Recent Comments

Nessun commento da mostrare.

↗ HOME

↗ ABOUT THE PROJECT

↗ PARTNERS

↗ NEWS

↗ CONTACTS

↗ PRIVACY POLICY

info-rexasipro@spindox.it
  • Segui
  • Segui