Giulia Vezzani — accepted AI-conference papers

2022

Learning transferable motor skills with hierarchical latent mixture policies

Dushyant Rao, Fereshteh Sadeghi, Leonard Hasenclever, Markus Wulfmeier, Martina Zambelli, Giulia Vezzani +5

ICLR 2022spotlight

For robots operating in the real world, it is desirable to learn reusable abstract behaviours that can effectively be transferred across numerous tasks and scenarios. We propose an approach to learn skills from data using a hierarchical mixture latent variable model. Our method exploits a multi-leve…

Cited by 38 Source ↗PDF ↗Scholar ↗

2021

A Constrained Multi-Objective Reinforcement Learning Framework

Sandy Huang, Abbas Abdolmaleki, Giulia Vezzani, Philemon Brakel, Daniel J Mankowitz, Michael Neunert +5

CoRL 2021poster

Many real-world problems, especially in robotics, require that reinforcement learning (RL) agents learn policies that not only maximize an environment reward, but also satisfy constraints. We propose a high-level framework for solving such problems, that treats the environment reward and costs as se…

Cited by 34 Source ↗Scholar ↗

2020

GRASPA 1.0: GRASPA is a Robot Arm graSping Performance BenchmArk

Fabrizio Bottarel, Giulia Vezzani, Ugo Pattacini, Lorenzo Natale

RA-L 2020

The use of benchmarks is a widespread and scientifically meaningful practice to validate performance of different approaches to the same task. In the context of robot grasping the use of common object sets has emerged in recent years, however no dominant protocols and metrics to test grasping pipeli

Cited by 36 Source ↗code ↗Scholar ↗

2018

Improving Superquadric Modeling and Grasping with Prior on Object Shapes

Giulia Vezzani, Ugo Pattacini, Giulia Pasquale, Lorenzo Natale

ICRA 2018poster

This paper proposes an object modeling and grasping pipeline for humanoid robots. This work improves our previous approach based on superquadric functions. In particular, we speed up and refine the modeling process by using prior information on the object shape provided by an object classifier. We u…

Cited by 23 Source ↗Scholar ↗

2018

Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations

Aravind Rajeswaran, Vikash Kumar, Abhishek Gupta, Giulia Vezzani, John Schulman, Emanuel Todorov +1

RSS 2018poster

Dexterous multi-fingered hands are extremely versatile and provide a generic way to perform a multitude of tasks in human-centric environments. However, effectively controlling them remains challenging due to their high dimensionality and large number of potential contacts. Deep reinforcement learni…

Cited by 1325 Source ↗PDF ↗Scholar ↗

2018

Markerless Visual Servoing on Unknown Objects for Humanoid Robot Platforms

Claudio Fantacci, Giulia Vezzani, Ugo Pattacini, Vadim Tikhanoff, Lorenzo Natale

ICRA 2018poster

To precisely reach for an object with a humanoid robot, it is of central importance to have good knowledge of both end-effector, object pose and shape. In this work we propose a framework for markerless visual servoing on unknown objects, which is divided in four main parts: I) a leastsquares minimi…

Cited by 10 Source ↗code ↗Scholar ↗

2017

A grasping approach based on superquadric models

Giulia Vezzani, Ugo Pattacini, Lorenzo Natale

ICRA 2017poster

This paper addresses the problem of grasping unknown objects with a humanoid robot. Conventional approaches fail when the shape, dimension or pose of the objects are missing. We propose a novel approach in which the grasping problem is solved by modeling the object and the volume graspable by the ha…

Cited by 82 Source ↗Scholar ↗