PhD Position Model Based Control of Soft Robots

We’re looking for a motivated PhD student with a Master’s in Robotics, Control Theory, Applied Math, or Mechanical Engineering eager to work on model-based control of soft robots.

Job description

We are looking for a motivated PhD candidate to join the Physical Intelligence Lab at TU Delft and contribute to advancing model-based control of soft robots. The position is funded by the ERC Starting Grant “RIPLEY,” led by Dr. Cosimo Della Santina. The project aims to rethink how soft robots can interact with their environment, focusing on large-area, multi-point contacts—similar to how an elephant wraps its trunk around an object.

Unlike traditional robots, which rely on rigid links and localized interaction points, soft robots are composed of deformable materials that can conform to complex geometries and operate safely around humans. They offer unique advantages for manipulation and locomotion, but current control algorithms do not fully exploit their capabilities. Most rely on approximations tailored for rigid systems or require extensive sensing and computation. This project addresses the challenge of developing model-based control strategies tailored to soft bodies, capable of exploiting their compliant nature.

The PhD candidate will focus on the theoretical and algorithmic development of control methods that combine physical modeling and real-time computation. The work will involve deriving reduced-order models, designing controllers that exploit the system’s distributed dynamics, and validating them experimentally on soft robotic platforms in our lab. These include tentacle-like manipulators and soft arms, eventually leading toward autonomous, multi-limb systems for tasks such as inspection, agriculture, and healthcare.

The PhD student will be supervised by Dr. Della Santina and work closely with a team of researchers in soft robotics, control theory, and machine learning. They will have access to a fully equipped lab and benefit from collaborations within the ERC team and across TU Delft. There will be opportunities to present at leading international conferences and to collaborate with other academic and industrial partners.

• Develop model-based control strategies for soft robots.
• Combine physical modeling and real-time computation in control design.
• Derive reduced-order models.
• Design controllers that exploit distributed dynamics.
• Validate methods experimentally on soft robotic platforms in the lab.
• Work with platforms including tentacle-like manipulators and soft arms, with a view toward autonomous multi-limb systems.
• Collaborate with researchers in soft robotics, control theory, and machine learning.
• Present work at leading international conferences and collaborate with academic and industrial partners.

The ideal candidate holds a Master’s degree in Robotics, Control Theory, Mechanical Engineering, or Applied Mathematics. A background in system dynamics, modeling, or control is essential; prior experience with soft robotics or experimental work is a plus but not required. We value independence, curiosity, and a willingness to bridge theory and practice.

TU Delft offers a stimulating and supportive research environment and broad training opportunities for career development.

Job requirements

• First and foremost: scientific curiosity!
• A Master’s degree (or equivalent) in Robotics, Control Theory, Mechanical Engineering, Applied Mathematics, or a related field.
• Solid background in dynamical systems, modeling, and control.
• Some programming experience.
• Strong analytical mindset and problem-solving attitude.
• Good communication skills and the ability to work both independently and in a team.
• Proficiency in written and spoken English.
• Prior experience in soft robotics, machine learning for control, or experimental robotics is a plus, but not required.
• Affinity with hands-on work and willingness to interact with physical robotic platforms is a plus, but not required.

Conditions of employment

Doctoral candidates will be offered a 4-year period of employment in principle, but in the form of 2 employment contracts. An initial 1.5 year contract with an official go/no go progress assessment within 15 months. Followed by an additional contract for the remaining 2.5 years assuming everything goes well and 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.