Fellow positions in “Efficient multimodal neuromorphic perception for human-robot interaction”
- (24000066)

Project: PRIMI — HORIZON-CL4-2022-DIGITAL-EMERGING-02 - Grant Agreement n.101120727
Commitment & contract: entry level fellowship, collaboration contract
Location: Genoa, Italy
ABOUT US
At IIT we work enthusiastically to develop human-centered Science and Technology to tackle some of the most pressing societal challenges of our times and transfer these technologies to the production system and society. Our Genoa headquarters are strictly interconnected with the other 11 centers around Italy and two outstations based in the US. We promote excellence in basic and applied research such as neuroscience and cognition, humanoid technologies and robotics, nanotechnology, materials for a truly multidisciplinary scientific experience.
YOUR TEAM
The research activities will be carried out under the supervision of Dr. Chiara Bartolozzi and Dr. Gaurvi Goyal. You will be working in a multicultural and multi-disciplinary group, where computational scientists, neuromorphic engineers and robotics experts collaborate to carry out common research. The current composition of the group consists of people from 6 different countries on 3 different continents.
The EDPR Research Unit is coordinated by Chiara Bartolozzi, who has extensive experience in neuromorphic engineering, and event-driven sensing and perception for robots. The Neuromorphic domain is a strongly emerging alternative computing ecosystem that can provide a more sustainable option to mainstream digital computing.
The position is part of a larger EU project, PRIMI, that will rely on the efficiency and accuracy of neuromorphic sensing and computation and its link to the real-world dynamics through its asynchronous, event-driven nature, to support the development of the robot’s understanding of itself, of the environment and of other agents. This approach is deemed to deliver robots with human-like motor performance and interaction. As part of the PRIMI project, you will interact with roboticists, neuromorphic engineers (while using the Spi NNaker2 platform) and neuroscientists.
Within this broad context, we are working on two main projects: Neuromorphic Human Pose Estimation and Neuromorphic Multimodal Perception.
Neuromorphic Human Pose Estimation
We will develop spiking neural networks for Human Pose Estimation at very high frequency, very low latency and high accuracy, with a precise estimation of the timing of the action, needed to better coordinate human and robot’s cooperative interactions, to be deployed on the visual system of the i Cub humanoid robot. We will work at the intersection between neuromorphic perception and latest machine learning approaches, to build models that are robust to special and intersectional factors (gender, ethnicity, age, socioeconomic status, disability) including features such as adaptability to disabilities, aiming at deployment in assistive robotics and robotic enabled rehabilitation therapies. To this aim, we will investigate and implement techniques in areas like meta learning, transfer learning and domain adaptation, that build the adaptability implicitly into the models with minimal new data to augment the training phases, for applications to uncommon cases where building large-scale dataset is either inefficient or impossible.
Neuromorphic Multimodal Perception
We will develop neuromorphic multisensory perception to infer the state of the robot, of the environment, of humans and of their interaction, using proprioception, touch and vision, for precise action timing execution during physical human robot interaction.
We will use spiking, event-driven neuromorphic sensors integrated in the i Cub robot, and neuromorphic spiking neural networks for the estimation and execution of task dynamics during physical human robot interaction. To do so, we will study the development of a representation of the robot’s body and networks for generating goal directed movements, taking inspiration from the brain.
YOUR RESPOSIBILITY
Within the team, depending on your expertise and choice between one of the two main projects, your main responsibilities will be:

• Develop spiking neural networks for human pose estimation, focusing on methods that are robust to intersectional factors and minimise training data;
• Optimize their implementation for low-latency and real-time, on neuromorphic hardware;
• Develop a method to integrate tactile, proprioceptive and visual cues to inform the robot on the task dynamics and execute movements;
• Team up with the other researchers in the project to integrate all modules on the i Cub robot

This research is financed by the European Commission, within the Performance in Robot Interaction via Mental Imagery (PRIMI) project.
ESSENTIAL REQUIREMENTS

• A MSc in computer science, engineering, robotics, or related fields
• Good skills in algorithm development, programming, and analyzing and explaining your results
• Good command in spoken and written English

ADDITIONAL SKILLS (though not necessary)

• Experience on circuit design
• Knowledge of spiking neural networks and/or learning
• Background in neuromorphic engineering
• Good communication skills
• Strong problem solving attitude
• High motivation to learn
• Spirit of innovation and creativity
• Adeptness at time and priority management
• Ability to work in a challenging and international environment
• Ability to work independently and collaboratively in a highly interdisciplinary environment
• Excited about getting hands-on experience with humanoid robots

COMPENSATION & BENEFITS

• Competitive salary for international standards
• Private health care coverage
• Wide range of staff discounts

If you feel this tickles your appetite for change, do not hesitate and apply!

Please submit your application using the online form and including a detailed CV, university transcripts, cover letter (outlining motivation, experience and qualifications) and contact details of 2 references.
Application’s deadline: September 8th, 2024
We inform you that the information you provide will be used solely for the purposes of evaluating and selecting professional profiles in order to meet the requirements of Istituto Italiano di Tecnologia.
Your data will be processed by Istituto Italiano di Tecnologia, based in Genoa, Via Morego 30, acting as Data Controller, in compliance with the rules on protection of personal data, including those related to data security.
Please also note that, pursuant to articles 15 et. seq. of European Regulation no. 679/2016 (General Data Protection Regulation), you may exercise your rights at any time by contacting the Data Protection Officer (phone Tel: +39 010 28961 - email: dpo@iit.it ).

Primary Location GENOVA S. QUIRICO

Job Fellow

Organization Event-Driven Perception for Robotics

Job Posting Aug 19, 2024, 8:50:43 AM