Postdoc in AI-based Perception in Visually Uncertain Environments – DTU Electro

This postdoc position is part of the AUT section at DTU Electro which has demonstrated state of the art perception and machine learning solutions for autonomous systems in the fields of inspection, construction, agriculture and shipping.

The goal of this postdoc is to enable the AI-based understanding for a shotcrete robot under visually uncertain environments. Specifically, the postdoc will enhance the multitask semantic inference and attentional models with probabilistic methods. The end goal of this project will be to enable similar performance of the DTU-developed AI techniques under visually degraded conditions, as part of the RobetArme Project.

The RoBétArmé project aims toward a step-change in the Construction 4.0 by automating particularly laborious construction tasks in all phases of shotcrete application. Among other state of the art developments, this step change will be achieved via an advanced high-precision and real-time infrastructure perception system through AI- enabled technologies and multimodal sensor fusion.

Responsibilities and qualifications
The main purpose of this postdoc is to investigate the employment of probabilistic approaches to handle machine learning in visually degraded scenes, during robotic shotcrete application. The probabilistic approaches will be incorporated with multitask semantic inference and attentional models. 

The primary tasks will be:

• Analyze the available data streams and determine relevant ones to serve as basis for probabilistic inference.
• Design and co-develop novel probabilistic deep learning models for segmentation and classification.
• Characterization of probabilistic model behavior under highly uncertain and visually degraded environments.
• Realize deep learning pipelines in the context of construction robotics.
• Support and co-supervise students and PhD students working within the field of probabilistic learning, multitask learning and attentional models.

The qualifications of the successful candidate will preferably include experience with deep learning for ambiguous classification and segmentation tasks as well as adaptation of these in continuously shifting domains with regards to visual appearance. Experience with probabilistic learning approaches is prefered.

As a formal qualification, you must hold a PhD degree (or equivalent).

We offer
DTU is a leading technical university globally recognized for the excellence of its research, education, innovation and scientific advice. We offer a rewarding and challenging job in an international environment. We strive for academic excellence in an environment characterized by collegial respect and academic freedom tempered by responsibility.

Salary and terms of employment
The appointment will be based on the collective agreement with the Danish Confederation of Professional Associations. The allowance will be agreed upon with the relevant union.

The period of employment is 2 years. The preferred starting date is April 1 2023, or according to a mutual agreement. The position is a full time position.

You can read more about career paths at DTU here .

Further information
Further information may be obtained from Prof. Lazaros Nalpantidis by sending an email to [email protected] .

You can read more about the Department of Electrical and Photonics Engineering at www.electro.dtu.dk .

If you are applying from abroad, you may find useful information on working in Denmark and at DTU at DTU – Moving to Denmark . 

Application procedure
Your complete online application must be submitted no later than 8 March 2023 (Danish time). Applications must be submitted as one PDF file containing all materials to be given consideration. To apply, please open the link "Apply now", fill out the online application form, and attach all your materials in English in one PDF file. The file must include:

• Application (cover letter)
• CV
• Academic Diplomas (MSc/PhD – in English)
• List of publications
• Up to five (5) publications (journal or peer-reviewed conference papers) that are relevant for the evaluation of the requested qualifications
• Your ORCID number 

Applications received after the deadline will not be considered.

All interested candidates irrespective of age, gender, disability, race, religion or ethnic background are encouraged to apply.

DTU Electro has more than 300 employees with competencies in electrical and photonics engineering. Research is performed within robotics, autonomous systems, power electronics, acoustic, nanophotonics, lasers, quantum photonics, optical sensors, LEDs, photovoltaics, ultra-high speed optical transmission systems, bio-photonics.

Technology for people
DTU develops technology for people. With our international elite research and study programmes, we are helping to create a better world and to solve the global challenges formulated in the UN’s 17 Sustainable Development Goals. Hans Christian Ørsted founded DTU in 1829 with a clear mission to develop and create value using science and engineering to benefit society. That mission lives on today. DTU has 13,400 students and 5,800 employees. We work in an international atmosphere and have an inclusive, evolving, and informal working environment. DTU has campuses in all parts of Denmark and in Greenland, and we collaborate with the best universities around the world.