I am a research fellow and PhD candidate in Advanced and Humanoid Robotics at iCub Facility (Humanoid Sensing and Perception research line) at the Istituto Italiano di Tecnologia in Genova. The goal of my research is to improve perception and manipulation skills for humanoid robots, by exploiting both visual and tactile information. All my main achievements have been implemented in C++ and tested on the humanoid robot iCub. Recently, I got interested in Artificial Intelligence and, in particular, Deep Reinforcement Learning for robotics. I strongly believe that robots autonomous skills can be improved by combining model-based and learning techniques.
Improving Superquadric Modeling and Grasping with Prior on Object Shapes [ICRA 2018]
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 use our previous method for the computation of grasping pose to obtain pose candidates for both the robot hands and, then, we automatically choose the best candidate for grasping the object according to a given quality index.
More information are available at this link.
A Grasping Approach Based on Superquadric Models [ICRA 2017]
We propose a novel approach in which the grasping problem is solved by modeling the object and the volume graspable by the hand with superquadric functions. The object model is computed in real-time using stereo vision. Pose computation is formulated as a nonlinear constrained optimization problem, which is solved in real-time using the Ipopt software package. Notably, our method finds solutions in which the fingers are located on portions of the object that are occluded by vision.
A Novel Pipeline for Bi-manual Handover Task [Advanced Robotics 2017]
This paper addresses the problem of bi-manual object handover with a humanoid robot, i.e. the task of passing objects from one hand to the other. We propose a novel and effective pipeline that tackles the problem by using visual and tactile information. Given the object in one of the robot hand (first hand), the object in-hand pose is estimated by a localization algorithm, which makes use of vision and tactile information. Then, the estimated pose is used in order to automatically choose a suitable pose for the second hand among a set of candidates a-priori annotated on the object model. The selected pose is finally used to accomplish the handover task.
Memory Unscented Particle Filter for 6-DOF Tactile Localization [TRO 2017]
This paper addresses 6-DOF (degree-of-freedom) tactile localization, i.e. the pose estimation of tridimensional objects given tactile measurements.The nature of tactile measurements, the strict time requirements for real-time operation and the multimodality of the involved probability distributions pose remarkable challenges and call for advanced nonlinear filtering techniques. Following a Bayesian approach, this paper proposes a novel and effective algorithm, named Memory Unscented Particle Filter (MUPF), which solves 6-DOF localization recursively in real-time by only exploiting contact point measurements. MUPF combines a modified particle filter that incorporates a sliding memory of past measurements to better handle multimodal distributions, along with the unscented Kalman filter that moves the particles towards regions of the search space that are more likely with the measurements.
Application: A Novel Bayesian Filtering Approach to Tactile Object Recognition [Humanoids 2016]
RAS Travel Grant, at IEEE International Conference on Robotics and Automation (ICRA), Singapore, May- June 2017
Travel grants supported by the IEEE Robotics and Automation Society are available for selected students travelling to the conference with one accepted paper at ICRA 2017.
Dr. Kanako Miura Travel Support Award, at IEEE International Conference on Humanoids Robotics, Cancun, Mexico, November 2016
In recognition of Dr. Kanako Miura's contributions to Humanoid Robotics, the Miura Memorial Award was initiated in 2013 and supported by the IEEE RAS Technical Committee on Humanoid Robotics. The goal is to assist PhD and MS female students entering the field with a travel support to Humanoid 2016.
Renato Mariani Award 2015, provided by AEIT, sezione Toscana e Umbria
Renato Marian Award gives credit to the studies and efforts of one of the students graduated in Engineering at the University of Florence.