PhD: Tensor decomposition for Efficient Robotic Perception
The Intelligent Vehicles group and the Delft Center for Systems and Control (DCSC) at the TU Delft is seeking a PhD candidate with an interest in performing fundamental research on Tensor Decomposition and Deep Learning in the exciting research area of self-driving vehicles.
Mobile robotics and intelligent vehicles with many multi-modal sensors collect and process large amounts of data during operation using cameras, lidar scanners, radars, and possibly even microphone arrays. Indeed, the current state-of-the-art in perception, modelling and control is mostly data-driven. However, the abundance of high bandwidth sensors data results in both online and offline processing bottlenecks. This flooding of data is a major technical limitation in the development of performant algorithms for modelling and control. For online processing, the data flood leads to large storage space requirements, high bandwidth needs for real-time communication, and computational challenges. For offline processing, more efficient methods are needed to train machine learning models on large amounts of mixed, unlabelled data.
This PhD position will explore the use of suitable Tensor Decompositions (TD) to efficiently represent the streaming sensor data. TD exploits low-rank properties of tensor data, similar to the SVD for matrices, which facilitates important real-time high-volume perception tasks found in robotics, and intelligent vehicles specifically. While the self-driving vehicle domain will be main application area in this proposal, developed methods will also benefit other robotics applications, and be of interest to the wider machine learning, applied mathematics, and control communities.
Prospective applicants should have a strong academic record in computer science, artificial intelligence or robotics with solid background in numerical linear algebra, statistics, machine learning, and/or robotics. Good software development and programming skills are expected, preferably in C++ and Python/Julia. Knowledge of deep-learning frameworks (Torch/TensorFlow) and ROS/CUDA is a plus. A certain affinity towards turning complex concepts into real-world practice (i.e. vehicle demonstrator) is desired. All applicant(s) are expected to be able to act independently as well as to collaborate effectively with members of a larger team. Good command of the English language is required (knowledge of Dutch is not a necessity).
CONDITIONS OF EMPLOYMENT
Fixed-term contract: 4 years.
TU Delft offers a customisable compensation package, a discount for health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. An International Children’s Centre offers childcare and an international primary school. Dual Career Services offers support to accompanying partners. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities.
As a PhD candidate you will be enrolled in the TU Delft Graduate School. TU Delft Graduate School provides an inspiring research environment; an excellent team of supervisors, academic staff and a mentor; and a Doctoral Education Programme aimed at developing your transferable, discipline-related and research skills. Please visit www.tudelft.nl/phd for more information.
Technische Universiteit Delft
Delft University of Technology (TU Delft) is a multifaceted institution offering education and carrying out research in the technical sciences at an internationally recognised level. Education, research and design are strongly oriented towards applicability. TU Delft develops technologies for future generations, focusing on sustainability, safety and economic vitality. At TU Delft you will work in an environment where technical sciences and society converge. TU Delft comprises eight faculties, unique laboratories, research institutes and schools.
Faculty Mechanical, Maritime and Materials Engineering
The 3mE Faculty trains committed engineering students, PhD candidates and post-doctoral researchers in groundbreaking scientific research in the fields of mechanical, maritime and materials engineering. 3mE is the epitome of a dynamic, innovative faculty, with a European scope that contributes demonstrable economic and social benefits.
The Cognitive Robotics department within the 3mE Faculty aims to develop intelligent robots and vehicles that will advance mobility, productivity and quality of life. Its mission is to bring robotic solutions to human-inhabited environments, focusing on research in the areas of machine perception, motion planning and control, machine learning, automatic control and interaction. The department combines fundamental research with work on physical demonstrators in areas such as self-driving vehicles, collaborative industrial robots, mobile manipulators and haptic interfaces. Collaborations exist with cross-faculty institutes TU Delft Robotics Institute and TU Delft Transport Institute), the national robotic ecosystem (RoboValley, Holland Robotics) and international industry and academia. For more information, see Cognitive Robotics (CoR).
To apply, please submit to application-3mE@tudelft.nl by 1 July 2020:
• a letter of motivation explaining why you are the right candidate,
• a detailed CV,
• a complete record of Bachelor and Master courses (including grades),
• your Master’s Thesis,
• any publications, and a list of projects you have worked on with brief descriptions of your contributions (max 2 pages), and the names and contact addresses of two references.
All these items should be combined in one PDF document. When applying for this position, please refer to vacancy number 3ME18-02.
Employer's other advertisements
Marie Skłodowska-Curie Early Stage Researcher PhD position: Automated manufacturing of carbon fibre reinforced composites for offshore wind turbine blades
ECONOMICS AND REGULATION OF GRIDS (WITH SPECIAL CONSIDERATION OF THE TECHNICAL REQUIREMENTS)
Vienna University of Technology - TU Wien Vienna
Professor in Automated Software Engineering
Umeå University Umeå
Professor in Software Security
Umeå University Umeå
Deputy Vice-Chancellor and Vice-Rector: Learning and Teaching
University of Stellenbosch South Africa
PhD Student in Construction Management and Building Technology
Luleå Tekniska Universitet Luleå