Search Results for author: Paolo Fiorini

Found 15 papers, 7 papers with code

The Robotic Surgery Procedural Framebank

1 code implementation LREC 2022 Marco Bombieri, Marco Rospocher, Simone Paolo Ponzetto, Paolo Fiorini

Robot-Assisted minimally invasive robotic surgery is the gold standard for the surgical treatment of many pathological conditions, and several manuals and academic papers describe how to perform these interventions.

Natural Language Understanding Semantic Parsing +1

Do LLMs Dream of Ontologies?

1 code implementation26 Jan 2024 Marco Bombieri, Paolo Fiorini, Simone Paolo Ponzetto, Marco Rospocher

Large language models (LLMs) have recently revolutionized automated text understanding and generation.

Memorization

Challenges in Multi-centric Generalization: Phase and Step Recognition in Roux-en-Y Gastric Bypass Surgery

1 code implementation18 Dec 2023 Joel L. Lavanchy, Sanat Ramesh, Diego Dall'Alba, Cristians Gonzalez, Paolo Fiorini, Beat Muller-Stich, Philipp C. Nett, Jacques Marescaux, Didier Mutter, Nicolas Padoy

The use of multi-centric training data, experiments 6) and 7), improves the generalization capabilities of the models, bringing them beyond the level of independent mono-centric training and validation (experiments 1) and 2)).

Activity Recognition

Generalization of Auto-Regressive Hidden Markov Models to Non-Linear Dynamics and Unit Quaternion Observation Space

no code implementations23 Feb 2023 Michele Ginesi, Paolo Fiorini

Although this extension is proposed for the ARHMM, it can be easily extended to other latent variable models with AR dynamics in the observed space, such as Auto-Regressive Hidden semi-Markov Models.

speech-recognition Speech Recognition +2

Weakly Supervised Temporal Convolutional Networks for Fine-grained Surgical Activity Recognition

no code implementations21 Feb 2023 Sanat Ramesh, Diego Dall'Alba, Cristians Gonzalez, Tong Yu, Pietro Mascagni, Didier Mutter, Jacques Marescaux, Paolo Fiorini, Nicolas Padoy

In this work, we propose to use coarser and easier-to-annotate activity labels, namely phases, as weak supervision to learn step recognition with fewer step annotated videos.

Activity Recognition

Logic programming for deliberative robotic task planning

no code implementations18 Jan 2023 Daniele Meli, Hirenkumar Nakawala, Paolo Fiorini

In this manuscript, we present a survey on recent advances in the application of logic programming to the problem of task planning.

Computational Efficiency

Colonoscopy Navigation using End-to-End Deep Visuomotor Control: A User Study

1 code implementation30 Jun 2022 Ameya Pore, Martina Finocchiaro, Diego Dall'Alba, Albert Hernansanz, Gastone Ciuti, Alberto Arezzo, Arianna Menciassi, Alicia Casals, Paolo Fiorini

Flexible endoscopes for colonoscopy present several limitations due to their inherent complexity, resulting in patient discomfort and lack of intuitiveness for clinicians.

Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures

no code implementations24 Feb 2021 Sanat Ramesh, Diego Dall'Alba, Cristians Gonzalez, Tong Yu, Pietro Mascagni, Didier Mutter, Jacques Marescaux, Paolo Fiorini, Nicolas Padoy

Conclusion: In this work, we present a multi-task multi-stage temporal convolutional network for surgical activity recognition, which shows improved results compared to single-task models on the Bypass40 gastric bypass dataset with multi-level annotations.

Activity Recognition

Improving rigid 3D calibration for robotic surgery

no code implementations16 Jul 2020 Andrea Roberti, Nicola Piccinelli, Daniele Meli, Riccardo Muradore, Paolo Fiorini

Calibration of the camera and the robot is necessary for precise positioning of the tools in order to emulate the high performance surgeons.

Dynamic Movement Primitives: Volumetric Obstacle Avoidance Using Dynamic Potential Functions

1 code implementation1 Jul 2020 Michele Ginesi, Daniele Meli, Andrea Roberti, Nicola Sansonetto, Paolo Fiorini

In this work, we extend our previous work to include the velocity of the trajectory in the definition of the potential.

Robotics

Autonomous task planning and situation awareness in robotic surgery

no code implementations19 Apr 2020 Michele Ginesi, Daniele Meli, Andrea Roberti, Nicola Sansonetto, Paolo Fiorini

The framework consists of a task-level reasoning module based on answer set programming, a low-level motion planning module based on dynamic movement primitives, and a situation awareness module.

Motion Planning

Overcoming Some Drawbacks of Dynamic Movement Primitives

1 code implementation28 Aug 2019 Michele Ginesi, Nicola Sansonetto, Paolo Fiorini

In this work, we present and motivate a new set of basis functions to be used in the learning process, showing their ability to accurately approximate functions while having both analytical and numerical advantages w. r. t.

Robotics Numerical Analysis Systems and Control Systems and Control Numerical Analysis

Cannot find the paper you are looking for? You can Submit a new open access paper.