The importance of vision for robots is pervasive: from self-driving cars to detecting and handling objects for service robots in homes, from kitting in industrial workshops, to robots filling shelves and shopping baskets in supermarkets, etc. All these applications, and many more, imply interacting with a wide variety of objects, requiring in turn a deep understanding of what these objects look like, their properties, functionalities and likely locations. There are robots performing complex tasks such as loading a dishwasher or flipping pancakes. However, the knowledge about the objects involved in these tasks is usually manually encoded within the robots control programs or knowledge bases, limiting them to operate on the objects they have been programmed to understand. This is not enough. Any robot, regardless of how much knowledge has been manually encoded into it, will inevitably face novel situations, and thus will always have gaps, conflicts or ambiguities in its own knowledge and capabilities. This calls for robots able to learn continuously about the objects they see by themselves.
The goal of our research is to enable robots to learn perceptual and semantic object knowledge from external knowledge sources. We consider the Web as our privileged knowledge source, looking for algorithms able to mine the Web autonomously for 2D, 2.5D and 3D perceptual data, and for approaches able to make this perceptual information usable in the situated, embodied reality of the robot. This position will particularly focus on how to mine the Web for depth information, and how to make it useful in the robot perceptual domain.
The candidate should have a strong technical and theoretical background, with a M. Sc. in Computer science, Physics, Electrical engineer or similar, and a proven research record on visual recognition using deep networks. Prior experience on depth images and robot vision, documented by a publication record in the field, will be a plus.
The successful candidate will work starting from October 2017 in the newly established Visual and Multimodal Applied Learning Laboratory (VANDAL), led by Prof. Caputo, in Milan, with high end computing and robotic facilities.
Please submit your applications (deadline is August 15, 2017), including a detailed curriculum vitae, 2 representative publications and 1 page of research statement in PDF format, to firstname.lastname@example.org quoting “Fellow position CB 74247” in the subject line.
Please note that this position is pending transfer ERC budget to IIT (H2020_ERC-2014-STG: RoboExNovo, Grant Agreement number 637076).
IIT was established in 2003 and successfully created the large scale infrastructure in Genova, a network of 10 state of the art laboratories countrywide, recruited an international staff of about 1100 people from more than 50 countries. IIT's research endeavour focuses on high-tech and innovation, representing the forefront of technology with possible application from medicine to industry, computer science, robotics, life sciences and nanobiotechnologies.
In order to comply with the Italian law (art. 23 of Privacy Law of the Italian Legislative Decree n. 196/03), we have to kindly ask the candidate to give his/her consent to allow IIT to process his/her personal data.
We inform you that the information you provide will be used solely for the purpose of assessing your professional profile to meet the requirements of Istituto Italiano di Tecnologia.
Your data will be processed by Istituto Italiano di Tecnologia, with headquarters in Genoa, Via Morego 30, acting as the Data Holder, using computer and paper based means, observing the rules on protection of personal data, including those relating to the security of data. Please also note that, pursuant to art.7 of Legislative Decree 196/2003, you may exercise your rights at any time as a party concerned by contacting the Data Manager.”
Istituto Italiano di Tecnologia is an Equal Opportunity Employer that actively seeks diversity in the workforce.