Medical Emergency Autopilot
Project HERCULES will provide the required technological infrastructure to obtain an order-of-magnitude improvement in the cost and power consumption of next generation real-time applications. It will develop an integrated framework to allow achieving predictable performance on top of cutting-edge heterogeneous CTOS multi-core platforms, implementing real-time scheduling techniques and execution models recently proposed in the research community. The framework will be applied to two innovative industrial use cases: a pioneering autonomous driving system for the automotive domain, and a visual recognition system for the avionic domain..
Ranked #1 project among EU’s Horizon 2020 programme in 2015, our HiPeRT Lab @ UNIMORE is currently leading Hercules.
NVIDIA DRIVE™ PX 2 is the open AI car computing platform that enables automakers and their tier 1 suppliers to accelerate production of automated and autonomous vehicles. It scales from a palm-sized, energy efficient module for AutoCruise capabilities, to a powerful AI supercomputer capable of autonomous driving. DRIVE PX 2 systems can fuse data from multiple cameras, as well as lidar, radar, and ultrasonic sensors. Use of Deep Neural Networks (DNN) for the detection and classification of objects dramatically increases the accuracy of the resulting fused sensor data.
We have a strong partnership with NVIDIA, and actively contribute, as external consultants, to the development of their certifiable embedded platforms for the automotive market.
NVIDIA Drive Platform Family
Marko Bertogna is Associate Professor and leader of the HiPeRT Lab. His main interests are in multi-/many-core systems, Real-Time scheduling and schedulability analysis. He published several papers in international conferences and journals, obtaining six Best Paper Awards. He is Senior Member of the IEEE, Member of HiPEAC and of the Technical Committee on Real-Time Systems.
Paolo BurgioChief Integration Engineer
Eng. Paolo Burgio, PhD, is research fellow at UNIMORE. He currently leads the hardware/software integration of the DriveBox Control Units. Paolo spent one year as an associate research in Real-Time systems at Linköpings Universitet (SE), then he enrolled for a Ph.D. in electronics engineering from University of Bologna (IT) and Université de Bretagne-Sud (FR), with special focus on highly parallel architectures, compilers and low-power systems. He also has a years-lasting expertise as a freelance consultant for big enterprises in the IT domain.
Nicola CapodieciCertification Data Manager
Eng. Nicola Capodieci, PhD, is a post-doc at UNIMORE. He did his research activity in different institutions such as UNIMORE, Univ. of Groningen (NL) for his M.Sc. thesis, Univ. of New Brunswick (CAN) as a research internship and Edinburgh Napier Uni. (UK) for his Ph.D. Thesis, and, least but not last, in NVIDIA in a four-month internship where he actively worked at the Drive PX2 platform project. His main research interests are Bio-inspired AI, Multi-Agent and Self-Organizing Systems, but also languages, architectures and everything related to GPUs. Nicola knows the Drive PX2 platform better than anyone else in the team, and he will be the certification engineer of the DriveBox.
Roberto CavicchioliChief Software/OS architect
Dott. Roberto Cavicchioli, PhD, is a post-doc at UNIMORE. His research has been focused in Numerical Optimization and Parallelization of algorithms on multicore systems and platforms such as Drive PX2. In particular the target was mainly to speed up computations for Image Reconstruction algorithms by exploiting High Performance Computing systems, especially in NVIDIA platforms. Together with Nicola, Roberto worked at the Drive PX2 project in NVIDIA. Due to his skills, Roberto is the software architect of the Drive PX2, and is in charge of porting and maintaining the Hercules OS on the board.
Project manager and accountant. He has a strong expertise as research advisor and project manager of EU funding projects (FP7, EUAID, H2020, EASME, 3° Health programme, NIH). He will be responsible for administrative, financial and legal issues as well as monitoring the timing and the quality of the project deliverables and milestones.
Roberto MatiQuality Manager
Eng. Roberto Mati, PhD, is CEO at PITOM srl. Roberto holds a PhD in Automation & Robotics, and a strong expertise in the design of Perception, Guidance, Navigation and Control Systems for Autonomous Vehicles. In 2007 he joined the Ohio State University (OH, USA) to develop an autonomous Toyota SUV at the 2007 DARPA Urban Challenge. In 2008 he served the University of Pisa as scientific and financial responsible in the FP7 ENFICA-FC project, that led to the design of the first European hydrogen/battery powered aircraft. He kept then developing components for Autonomous and Electric/Hybrid Vehicles. Roberto is bringing his strong relations with Chinese car-makers into DriveBox, that he serves as Quality Manager.
Michele FranchiVehicle Integration
Eng. Michele Franchi is CTO at PITOM srl. Michele holds a Master Degree in Automation and Robotics Engineering at the University of Pisa. He spent 2 years in the Autonomous Vehicles Laboratory at the same University, developing novel autopilots and control systems for unmanned ground and aerial vehicles. He also gave strong support to the design and integration of control systems for novel hybrid vehicles. After PITOM foundation, he led all the Robotic activities within the company, comprising the Artificial Intelligence for Robotic Lawn Mowers, Aerial Drones, Autonomous Boats, and Intelligent Reach-Stackers. Michele is the Vehicle Integration & Test Manager of DriveBox.