Are you interested in developing intelligent robotic systems that make cognitive decisions using current machine learning approaches? Would you like to study how people can benefit from working together with an intelligent robotic arm? If so, then apply for this PhD position at Eindhoven University of Technology and join the Human Technology Interaction (HTI) group.
Visual robot perception has grown tremendously in the last ten years. Artificial neural networks allow to reliably classify objects and segment structures from RGB images. Moreover, they allow for 3D pose estimation for robot navigation and manipulation in partially structured/unstructured environments. However, vision alone is not sufficient. Versatile interaction with unstructured environments requires a new generation of robots fully exploiting also touch and proprioception (perception of own movement and associated effort). Combining touch and vision information leads to a better world interpretation. Touch allows for 3D modeling of unseen parts of the environment as well as object mass, inertia, and friction estimation. Moreover, Artificial Intelligence (AI) through memory and cognition combined with visuo-tactile sensing will improve robot decision making, bringing a robotic arm’s motions and behaviour closer to human capabilities. You can become part of a team of three PhD-students working on the integration the information from the senses into an overarching mental model for the robot.
As a PhD researcher at the Human-Technology Interaction (HTI) group, you will mainly focus on developing and implementing a mental model based on multi-sensory integration to enable robust robot perception and cognition in unstructured environments. To this end, you will work on a solution for data efficient, yet robust-to-noise, computation using Bayesian priors in a decision-making process. You will build a library of knowledge containing a rich prior of potential events and scenarios the systems can encounter. This knowledge you will then integrate with the sensory information received from the two fellow PhD researchers in your team, who will focus on obtaining visuo-tactile information and proprioceptive data and real world estimates of objects and humans in the environment. You will combine these streams of information by developing an overarching Bayesian multisensory integration model with internal memory and a predictive inner physics world, giving a robotic arm cognitive abilities for robust world understanding and decision making.
Furthermore, your job will be to reflect and capitalize on findings from ongoing studies at the TU/e and HTI on the application of Neural Networks and Bayesian Networks for high-fidelity data fusion. As a result you will contribute to innovative human-technology interaction in our society. You will publish your findings in top-tier academic journals preferably with a multi-disciplinary audience and proactively disseminate the methodology that you will develop through education, conferences, and workshops.
The research will be done in a multi-disciplinary approach across the departments of Industrial Engineering & Innovation Sciences (IE&IS), Mathematics and Computer Science (M&CS), Mechanical Engineering (ME), and Electrical Engineering (EE). You will become part of the EAISI institute (Eindhoven Artificial Intelligence Institute) to join forces in creating AI for the real world. You will receive day-to-day supervision from Sanne Schoenmakers (IE&IS). And you will work in a team with Andrei Jalba (M&CS), Alessandro Saccon (ME), Marco Fattori (EE) and Wijnand IJsselsteijn (IE&IS).
We are looking for a candidate who meets several of the following requirements:
The Eindhoven Artificial Intelligence Systems Institute (EAISI) was established in the summer of 2019 as a cross-departmental institute that brings together all AI activities of Eindhoven University of Technology (TU/e). EAISI stimulates, supports, and organizes collaboration between TU/e AI researchers and companies and societal partners. EAISI’s goal is to stimulate multidisciplinary AI research on the combination of three of TU/e’s traditionally strong research domains of Data Science, Humans and Ethics, and Engineering Systems. EAISI aims to develop AI technology for autonomous decision-making in engineering systems that interact with and support humans. Working for EAISI means you are supported in creating new and exciting AI applications with a direct and positive impact on the real world, especially focusing on the application areas of health, mobility and high-tech industry.
Eindhoven University of Technology (TU/e) is one of Europe's leading research universities. The Eindhoven area, in the southern part of the Netherlands, is one of Europe's top 'innovation ecosystems', with many high-tech companies and institutes. TU/e is intertwined with many of these companies and institutes, and research at TU/e is characterized by a combination of academic excellence, industrial relevance and societal interweaving.
Please visit www.tue.nl/jobs to find out more about working at TU/e!
We are an inclusive university community. Diversity is one of our most important values. We believe that engaging in international activities and welcoming students and staff from a wide variety of backgrounds enhances the quality of our education and research. We are always looking for people who can enrich our world with their own unique perspectives and experiences.
Do you recognize yourself in this profile and are you enthusiastic about the contents of the project? Then we invite you to apply to this position by submitting a complete application by using the 'apply now'-button on this page.
The application should include:
If you have any questions regarding the position, please contact dr.ir. Sanne Schoenmakers, s.schoenmakers[at]tue.nl or dr. Andrei Jalba, a.c.jalba[at]tue.nl
We look forward to your application and will screen it from 20 October onward. Screening will continue until the position has been filled.
Please keep in mind you can upload only 5 documents up to 2 MB each. If necessary, please combine files.
We do not respond to applications that are sent to us in a different way.