Research

This is the list of formalized projects in which I am currently involved:

Below follow a summary of the recent results of my research grouped in different themes (Tactile sensing, Vision and Software Engineering). For a complete list of papers see my publications list (Publications).

Object manipulation and grasping

The iCub is equipped with a system of about 4500 tactile sensors distributed on the torso, arms and legs. I have worked in particular on the control of interaction forces on the whole-body and on the design of the sensorized fingertips. At the moment my group is studying algorithms for object grasping and manipulation using visual and tactile feedback.

    References

  • Bottarel, F., Vezzani, G., Pattacini, U. and Natale, L., GRASPA 1.0: GRASPA is a Robot Arm graSping Performance benchmArk, IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 836-843, 2020. [online text] [preprint][bibtex]
  • Vezzani, G., Pattacini, U., Pasquale, G., and Natale, L., Improving Superquadric Modeling and Grasping with Prior on Object Shapes, in Proc. IEEE-RAS International Conference on Robotics and Automation, Brisbane, Australia, 2018, pp. 6875-6882. [pdf] [bibtex]
  • Fantacci, C., Vezzani, G., Pattacini, U., Tikhanoff, V., and Natale, L., Markerless visual servoing on unknown objects for humanoid robot platforms, in Proc. IEEE-RAS International Conference on Robotics and Automation, Brisbane, Australia, 2018, pp. 3099-3106.[pdf] [bibtex]
  • Regoli, M., Pattacini, U., Metta, G., and Natale, L., Hierarchical Grasp Controller Using Tactile Feedback, in IEEE-RAS International Conference on Humanoid Robots, Cancun, Mexico, 2016.[pdf] [bibtex]
  • Jamali, N., Maggiali, M., Giovannini, F., Metta, G., and Natale, L., A New Design of a Fingertip for the iCub Hand, in Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems, Hamburg, Germany, 2015, pp. 1799-1805. [pdf] [bibtex]
  • Maiolino, P., Maggiali, M., Cannata, G., Metta, G., Natale, L., A Flexible and Robust Large Scale Capacitive Tactile System for Robots, IEEE Sensors Journal, vol. 13, no. 10, pp. 3910-3917, 2013. [pdf] [bibtex]
  • Del Prete, A., Denei, S., Natale, L., Mastrogiovanni, F., Nori, F., Cannata, G., Metta, G., Skin Spatial Calibration Using Force/Torque Measurements, IEEE/RSJ International Conference on Intelligent Robots and Systems, San Francisco, California, September 25-30, 2011. [pdf]
  • Schmitz A., Maiolino P., Maggiali M., Natale L., Cannata G., Metta G., Methods and Technologies for the Implementation of Large Scale Robot Tactile Sensors, IEEE Transactions on Robotics, Volume 27, Issue 3, pp. 389-400, 2011. [pdf] [bibtex]

Vision

I am interested in the study of algorithms for visual perception of the scene. We are ingestigating algorithms for online learing with weak supervision, object detection and segmentation.

    References

  • Maiettini, E., Pasquale, G., Rosasco, L., and Natale, L., On-line Object Detection: a Robotics Challenge, Autonomous Robots, vol. 44, no. 5, pp. 739–757, 2020. [online text] [preprint][bibtex]
  • Maiettini, E., Pasquale, G., Rosasco, L., and Natale, L., Speeding-up Object Detection Training for Robotics with FALKON, in Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems, Madrid, Spain 2018, pp. 5770-5776.[pdf] [bibtex]
  • Pasquale, G., Ciliberto, C., Odone, F., Rosasco, L., and Natale, L., Are we done with object recognition? The iCub robot’s perspective, Robotics and Autonomous Systems, vol. 112, pp. 260-281, 2019. [online full text][preprint] [bibtex]
  • Abuhashim, T., and Natale, L., Robustness in View-Graph SLAM , in 19th International Conference on Information Fusion, Heidelberg, Germany, 2016, pp. 942-949. [pdf] [bibtex]
  • Roncone, A., Pattacini, U., Metta, G., and Natale, L., Cartesian 6-DoF gaze controller for humanoid robots, in Robotics: Science and Systems, Ann Arbor, Michigan, USA, 2016. [pdf] [bibtex]
  • Pasquale, G., Ciliberto, C., Odone, F., Rosasco, L., and Natale, L., Teaching iCub to recognize objects using deep Convolutional Neural Networks, in Proc. 4th Workshop on Machine Learning for Interactive Systems, 2015.
  • Mar, T., Tikhanoff, V., Metta, G., and Natale, L., Self-supervised learning of grasp dependent tool affordances on the iCub Humanoid robot, in Proc. IEEE International Conference on Robotics and Automation, Seattle, Washington, 2015.
  • Ciliberto, C., Smeraldi, F., Natale, L., Metta, G., Online Multiple Instance Learning Applied to Hand Detection in a Humanoid Robot, IEEE/RSJ International Conference on Intelligent Robots and Systems, San Francisco, California, September 25-30, 2011.
  • Fanello, S. R., Ciliberto C., Natale, L., Metta, G., Weakly Supervised Strategies for Natural Object Recognition in Robotics, in Proc. IEEE International Conference on Robotics and Automation, Karlsruhe, Germany, 2013, pp. 4223-4229.


Software engineering

Robotics is a system science. For this reason a large body of work has been devoted to the development and study of software archictures and software engineering techniques specifically tailored to robotics systems.

During the development of the iCub robot I led the engineering of the iCub software. We have developed YARP (www.yarp.it) an open source middleware that supports concurrent execution of components on a cluster of computers.

Because communication is a typical bottleneck in robotics systems we have extended YARP to provide support for channel prioritization and QoS. With my group I have also studied techniques for coordinating software components, supporting reactive bahaviors and behavior reusability. We studied behavior based architectures and behavior trees. More recently we have been looking at formal methods for static and runtime verification of robot behaviors.











    References

  • Colledanchise, M., and Natale, L., Analysis and Exploitation of Synchronized Parallel Executions in Behavior Trees, in Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems, Macau, China, 2019, pp. 6399-6406. [pdf] [bibtex]
  • Natale, L., Paikan, A., Randazzo, M., Domenichelli, D.E.,The iCub Software Architecture: Evolution and Lessons Learned, Frontiers in Robotics and AI, vol. 3, no.24, 2016, doi: 10.3389/frobt.2016.00024. [pdf] [bibtex]
  • Paikan, A., Pattacini, U., Domenichelli, D., Randazzo, M., Metta, G., and Natale, L.,A Best-Effort Approach for Run-Time Channel Prioritization in Real-Time Robotic Application, in Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems, Hamburg, Germany, 2015, pp. 498-503. [pdf] [bibtex]
  • Paikan, A., Traversaro, S., Nori, F., and Natale, L.,Generic Testing Framework for Test Driven Development of Robotic Systems, in Proc. Modelling and Simulation for Autonomous Systems Workshop, Prague, Czech Republic, 2015, pp. 216-225. [pdf] [bibtex]
  • Paikan, A., Domenichelli, D., and Natale, L., Communication channel prioritization in a publish-subscribe architecture, in Proc. Software Engineering and Architectures for Realtime Interactive Systems Workshop, Arles, France, 2015. [pdf]
  • Paikan, A., Tikhanoff, V., Metta, G., and Natale, L., Enhancing software module reusability using port plug-ins: an experiment with the iCub robot, in Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems, Chicago, Illinois, 2014. [pdf]
  • Paikan, A., Fitzpatrick, P., Metta, G., and Natale, L., Data Flow Port's Monitoring and Arbitration, Journal of Software Engineering for Robotics, vol. 5, no. 1, pp. 80-88, 2014. [pdf]
  • Fitzpatrick, P., Metta, G., and Natale, L., Towards Long-Lived Robot Genes, Robotics and Autonomous Systems, Volume 56, Issue 1, pp. 29-45, Elsevier 2008. [pdf]