PhD: Learning of socially compliant motion planning for autonomous vehicles

PhD: Learning of socially compliant motion planning for autonomous vehicles

Published Deadline Location
28 Apr 1 Jul Delft
In this project you will develop novel methods for safe and socially compliant autonomous navigation, leveraging machine learning and trajectory optimization techniques.

Job description

We are looking for an ambitious PhD candidate who would like to develop novel methods for safe and socially compliant autonomous navigation in crowded urban canals, with a combination of machine learning (learning from historical data, reinforcement learning) and trajectory optimization approaches.

You will join a team of researchers within the context of the project "Sustainable Transportation and Logistics over Water: Electrification, Automation and Optimization (TRiLOGy)" funded by the Dutch Research Council (NWO). In this project, we will investigate (i) fleet management decisions at the high level (1 PhD position supervised by Assist. Prof. B. Atasoy) and (ii) autonomous navigation methodologies for autonomous vessels in urban canals (1 PhD position supervised by Assist. Prof. J. Alonso-Mora). You will be responsible for the latter, autonomous navigation.

The objective of the autonomous navigation part is to develop autonomy tools for navigation in inland waterways, among other manned and unmanned vessels. The main challenge to ensure safe and efficient navigation of autonomous vessels in urban waters is that of generating safe trajectories that (i) take into account the complex dynamics of the vessel, (ii) coordinate with other traffic participants and (iii) show socially-compliant behavior based on past experiece and historical data. In TRiLOGy we will rely on historical data from manned vessels and machine learning strategies (supervised learning, reinforcement learning, multi-agent reinforcement learning) to improve the performance of the motion planning system (trajectory optimization) and produce feasible human-like motions for the autonomous vessel. The developed motion planners will closely interact with the perception modules of the autonomous vessel. A typical scenario is that of crowded canals and intersections, where efficient navigation can be achieved with tight coordination among the interacting participants.

The autonomous navigation methods that will be developed in this project will be tested and verified through their application to autonomous vessels in the ResearchLab Autonomous Shipping (RAS). You will also interact with our industrial partners (Zoev City, Municipality of Amsterdam, Flying Fish and DEMCON Unmanned Systems), with the Amsterdam Institute of Advanced Metropolitan Solutions (AMS) and with MIT researchers working on the AMS Roboat project.

The PhD candidate will be embedded within the Autonomous Multi-robots Lab of the Department Cognitive Robocs at TU Delft. For more information of our ongoing research see https://www.autonomousrobots.nl.

Specifications

Delft University of Technology (TU Delft)

Requirements

The candidate has a very good MSc degree in Robotics, Computer Science, Systems and Control, Electrical/Mechanical Engineering, Applied Mathematics, or a related field. The candidate must have strong analytical skills and must be able to work at the intersection of several research domains. Good programming skills and experience with Python/C++ and ROS are of foremost importance to implement the learning methods and the proposed designs on real ASVs. A very good command of the English language is required, as well as excellent communication skills. Candidates having exhibited their ability to perform research in machine learning, control, optimization, perception and/or robotics are especially encouraged to apply.

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.

Employer

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.

Department

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 main focus of the Cognitive Robotics department is the development of intelligent robots and vehicles that will advance mobility, productivity and quality of life. Our 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 physical interaction of intelligent machines with humans. We combine fundamental research with work on physical demonstrators in areas such as self-driving vehicles, collaborative industrial robots, mobile manipulators and haptic interfaces. Strong collaborations exist with cross-faculty institutes TU Delft Robotics Institute and TU Delft Transport Institute), our national robotic ecosystem (RoboValley, Holland Robotics) and international industry and academia.

Additional information

If you have specific questions about this position, please contact Assist. Prof. J. Alonso-Mora (j.alonsomora@tudelft.nl, +31 152785489)  Always specify the vacancy number in the email subject. Please do not send application emails to these email addresses but use the specified address (application-3mE@tudelft.nl).

To apply, please send via e-mail:
• a letter of motivation explaining why you are the right candidate for this project,
• a detailed CV,
• a complete record of Bachelor and Master courses (including grades),
• your Master Thesis (at least as draft),
• any publications, and a list of projects you have worked on with brief descriptions of your contributions (max 2 pages),
• the names and contact addresses of two or three references.

All these items should be combined in one PDF document. Applications should be submitted at the earliest convenience to application-3mE@tudelft.nl. When applying for this position, always refer to the vacancy number 3mE20-44. The review of applications will start on June 1st and continue until the position is filled. The intended starting date is fall 2020 (flexible).

Specifications

  • PhD
  • Engineering
  • 36—40 hours per week
  • €2325—€2972 per month
  • University graduate
  • 3mE20-44

Employer

Delft University of Technology (TU Delft)

Learn more about this employer

Location

Mekelweg 2, 2628 CD, Delft

View on Google Maps

X

Apply for this job

Apply for this job

Fill in the form to apply for this job via AcademicTransfer. We will send your application to the employer.

Personalia

Attachments

Attachments

Upload at least one document, i.e. a cover letter and/or CV. Please note: use an alternative like a cloud service for large files as employers might refuse e-mails that exceed their companies policy.

Upload at least one document, i.e. a cover letter and/or CV. Please note: use an alternative like a cloud service for large files as employers might refuse e-mails that exceed their companies policy.
Only the following file extensions are allowed: pdf, doc, docx, jpg, jpeg and png.
The combined size of the documents must not exceed: 19.0 MB.
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
File added
Add a file
Drag file here or browse
Add more files

Application procedure

Application procedure

Make sure to apply no later than 1 Jul 2020 23:58 (Europe/Amsterdam).