Extra in the BBC documentary "Hyper Evolution: Rise of the Robots"
Ben Garrod of BBC visited our lab and we showed him how the iCub humanoid robot can learn to form his own understanding of the world. [link]
Postdoctoral Researcher. The University of Edinburgh, Machine Learning Group.
New methods for compressing large neural networks (in collaboration with Huawei).
Supervisor: Amos Storkey
Research Intern in the Camera Platform team. Snap Inc. (London)
Disentangling latent representations in deep autoencoders.
Website: www.snapchat.com
PhD student in Computational Modelling and Robotics. University of Plymouth (UK).
Implementing social skills in humanoid robots using machine learning algorithms.
Supervisors: Angelo Cangelosi, Torbjorn Dahl, Giorgio Metta
Artificial Intelligence specialist. Eurolink Systems group (Rome, Italy).
Autonomous control for unmanned ground vehicle and unmanned aerial vehicle.
Internship. Laboratory of Artificial Life and Robotics (LARAL). Rome (Italy). Artificial neural networks and genetic algorithms in evolutionary robotics.
MSc Cognitive Neuroscience. La Sapienza University (Rome, Italy). Supervisors: Stefano Puglisi Allegra, Domenico Parisi, Gianluca Baldassarre
BSc Experimental Cognitive Psychology. La Sapienza University (Rome, Italy). Supervisors: Marta Olivetti Belardinelli, Valerio Santangelo
Recent Activity
Completed Machine Learning class
Completed the Coursera Machine Learning class (Andrew Ng) with 100% final score [link]
Hackathon: Robots at your Service
We represented Plymouth University at the Hackathon "Robots at your Services" in Amsterdam.
NVIDIA academic hardware grant
I received a Tesla K40 GPU in support of a project on head pose estimation through convolutional neural networks.
The Robot Sawyer
The robot Sawyer of Rethink Robotics has been visiting Plymouth University.
HRI Summer School
Partecipating to the 2nd summer school in Human Robot Interaction. Aland Islands (Finland).
Live demo at Devonport Naval Heritage
Introducing NAO and iCub at Devonport Naval Heritage Centre.
Publications
Polvara* R., Patacchiola*, M., Sharma S., Wan J., Manning A., Sutton R., Cangelosi A. (under review). Autonomous Quadrotor Landing using Deep Reinforcement Learning. *Co-first authors. [arxiv]
Polvara* R., Patacchiola*, M., Sharma S., Wan J., Manning A., Sutton R., Cangelosi A. (2018). Toward End-To-End Control for UAV Autonomous Landing Via Deep Reinforcement Learning. The 2018 International Conference on Unmanned Aircraft Systems. *Co-first authors. [PDF]
Surace, L., Patacchiola, M., Battini Sonmez, E., Spataro, W., & Cangelosi, A. (2017). Emotion Recognition in the Wild using Deep Neural Networks and Bayesian Classifiers. In Proceeding of the Fifth Emotion Recognition in the Wild (EmotiW) Challenge, Glasgow, United Kingdom. [arxiv]
Patacchiola, M., & Cangelosi, A. (2017). Head Pose Estimation in the Wild using Convolutional Neural Networks and Adaptive Gradient Methods. Pattern Recognition, Elsevier, vol. 71, pp. 132-143. [PDF]
Patacchiola, M., & Cangelosi, A. (2016). A Developmental Bayesian Model of Trust in Artificial Cognitive Systems. In Proceedings of the International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob-2016). [PDF]
Zanatto, D., Patacchiola, M., Goslin, J., & Cangelosi, A. (2016). Priming Anthropomorphism: Can the credibility of humanlike robots be transferred to non-humanlike robots?. In The Eleventh ACM/IEEE International Conference on Human Robot Interation (pp. 543-544). IEEE Press. [PDF]
Paglieri, F., Parisi, D., Patacchiola, M., & Petrosino, G. (2015). Investigating intertemporal choice through experimental evolutionary robotics. Behavioural processes, vol. 115, pp. 1-18. [PDF]