Phd Position Multi-Agent Aerial Manipulation for Construction

Are you interested in exploring how multi-agent aerial manipulation can contribute to construction and working at the intersection of robotics and machine learning?

In the HARPA project funded by the EIC Pathfinder Challenge, you will explore how heterogeneous aerial robotics teams can collaboratively and autonomously assemble a pavilion. Together with team members and collaborators from TUM and ETH, the project will culminate in a real-world demonstration of the autonomous assembly of a pre-fabricated pavilion using a team of aerial robots.

HARPA is looking for two motivated PhD candidates who will closely collaborate to enable this vision.

PhD #1: Multi-Agent Planning and Control for Cable-Suspended Aerial Multi-Lifting Systems

Cable-suspended Aerial Multi-Lifting systems (CAMLs) are composed of several UAVs that lift and control the orientation of pre-fabricated building components through cables. You will investigate multi-agent planning, learning and control methods to enable decentralized, robust, and precise aerial manipulation with CAMLs. The goal is to allow existing UAV platforms to operate in a scalable and decentralized manner while achieving obstacle avoidance using onboard sensing and adapting to changes in dynamic environments.

In parallel to the theoretical and algorithmic developments, you will work closely with the other PhD candidate, postdocs, engineers in the lab, and collaborators from TUM and ETH to establish a digital twin for construction and optimize CAML hardware platforms for the precise manipulation of prefabricated building components. You will also collaborate with FlyingBasket to validate the heavy-lifting system. In the final HARPA demonstration, you will be responsible for the CAML platform and its collaboration with aerial robotic manipulator platforms.

PhD #2: Contact-Aware Planning and Control for Aerial Robotic Manipulators

You will investigate contact-aware planning, control, and perception methods for aerial robotic manipulators (ARMs). These aerial manipulators will act as “flying hands” to support the connection and assembly of prefabricated building components. You will explore how learning-based methods, such as imitation learning and reinforcement learning, can be integrated with model-based low-level controllers and multimodal sensing to enable contact-rich aerial manipulation in unstructured and dynamic environments, particularly in close proximity to objects.

The developed algorithms will be validated through real-world experiments that enable multiple ARMs to work together with CAMLs for construction tasks. In addition, you will contribute to the design and optimization of aerial manipulation hardware platforms, supported by engineers in the lab, as well as to the development of digital twin platforms for simulation and pre-assembly validation. Finally, you will contribute to the final demonstration of pavilion assembly.

The positions are available with a flexible start date to be agreed upon. The PhD candidates will join the Autonomous Multi-Robots Lab at the Cognitive Robotics Department and will be supervised by Dr. Sihao Sun and Prof. Javier Alonso-Mora. You will also have the chance to collaborate with and visit partners from ETH Zurich and TU Munich. As part of the PhD position, there will be opportunities to gain teaching experience in relevant courses and/or supervise MSc students.

Job requirements

We are looking for a candidate experienced with aerial robotics, motion planning, control, manipulation and/or machine learning.

• Master of Science (MSc) diploma in Robotics, Computer Science, Systems & Control, Aerospace Engineering, Applied Maths or another related field.
• Drive for excellence in research and the ability to work independently and as part of a team.
• Willingness to conduct multidisciplinary research in collaboration with both scientific and industrial partners.
• Excellent problem-solving and analytical skills.
• TOEFL or IELTS English proficiency tests for all applicants except those who graduated from an MSc program taught in English. The minimum requirement is a TOEFL score of 100, or IELTS of 7.0 per sub-skill (writing, reading, listening, speaking).

TU Delft

Working at TU Delft means contributing to solutions that really make a difference.

At TU Delft, our people make the difference. With their knowledge and curiosity, staff provide high-quality education and conduct pioneering research that extends beyond the campus. You will have the opportunity to take the initiative, work with others, and grow as a professional.

Faculty Mechanical Engineering

ME is a dynamic and innovative faculty with high-tech lab facilities and international reach. Its combination of disciplines is reflected in state-of-the-art education and research.

Conditions of employment

Doctoral candidates will be offered a 4-year period of employment in principle, in the form of 2 employment contracts. An initial 1.5 year contract includes an official go/no go progress assessment within 15 months, followed by an additional contract for the remaining 2.5 years, assuming performance requirements are met.

As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills.

The TU Delft offers a customisable compensation package, discounts on health insurance, and a monthly work costs contribution. Flexible work schedules can be arranged.