PhD on Dynamic Manipulation in Semi-Structured Industrial Settings

Introduction

Do you want to work on the next generation robot manipulators to give machines the ability to exploit repetitive contact and intentional collisions for swiftly performing pick-and-place and  assembly tasks? Are you passionate and skilled in advanced mathematics, robot dynamics, machine learning, robot control, advanced programming, and experimental validation? If so, you might be an excellent candidate for this PhD position. Join us, helping develop a technology that could provide a step change in manufacturing, logistics, aviation, and construction domains.

Job Description

The demand for autonomous robots capable of physically interacting with the world in flexible and adaptable ways is rapidly increasing across industries and society. These robots are needed to perform complex and fast physical interaction tasks, spanning from fine manipulation, such as kitting and cables manipulation, to heavy non-ergonomic tasks in semi-structured environments, such as depalletization and truck unloading.

This PhD project wants to explore the latest advances in robot control, robot learning, physics simulation, and robot hardware to generate robust contact-rich and impact-aware strategies that allow to perform assembly and pick-and-place tasks in man-made environments, targeting industry relevant use cases at required execution speed.  This is enabled by latest tactile robots that are impact-resilient, back-drivable, and capable of sensing contact interactions with the environment as well as computational hardware and parallel physics simulation software, enabling to train complex control policies or adaptable sampling-based MPC strategies. One use case of interest is, for example, the swift pick and place of heavy objects (>10kg) in clutter and in the presence of obstacles, with cycle times of 5 seconds.

Key Objectives and Challenges of this PhD Position Include:

• Develop simulation-based and pixel-to-action policies to quickly move objects in clutter, allowing to estimate/adapt to object properties on the fly while also continuously monitor task execution, swiftly replanning in case of inevitable occasional failures
• Collect experimental data and make it available according to FAIR principles and use it to validate physics engines (e.g., Isaac Sim, MuJoCo, Algoryx Dynamics) against real experiments, to explore the sim2real limits and use it to propose control strategies that respect and exploit the natural robot-environment contact dynamics for boosting task success rate
• Perform experimental work on the various robotic manipulation platforms available in the lab to assess progress with respect to the state of the art and showcase results to our research and industrial network

This project builds on previous work by Prof. Alessandro Saccon and in particular that conducted in the recently concluded H2020 I.AM project coordinated by the TU/e. The position is embedded in the Robotics section (RBT) within the Department of the Mechanical Engineering, with close connections with the Dynamics and Control (D&C) and Control Systems Technology (CST) sections in the same department.

Job Requirements

• A master’s degree (or equivalent) in a field relevant to robot learning and control, such as mechanical engineering, electrical engineering, control engineering, computer science, or related disciplines.
• Background knowledge in robot dynamics, machine learning, and control theory.
• Demonstrated high-level and low-level programming skills (Python and C/C++) and machine learning frameworks.
• Experience with performing physical experiments with robot manipulators.
• A research-oriented mindset, eager to take on exciting challenge.
• Willingness or demonstrated ability to work on multidisciplinary and collaborative projects.
• Motivation to develop teaching skills and mentor junior students (Bachelor’s and Master’s levels).
• Proficiency in spoken and written English (C1 level or higher).

Conditions of Employment

A meaningful job in a dynamic and ambitious university, in an interdisciplinary setting and within an international network. You will work on a beautiful, green campus within walking distance of the central train station. In addition, we offer you: 

• Full-time employment for four years, with an intermediate assessment (go/no-go) after nine months. You will spend a minimum of 10% of your four-year employment on teaching tasks.
• Salary and benefits (such as a pension scheme, paid pregnancy and maternity leave, partially paid parental leave) in accordance with the Collective Labour Agreement for Dutch Universities, scale P (min. € 2,901 max. € 3,707).  
• A year-end bonus of 8.3% and annual vacation pay of 8%. 
• High-quality training programs and other support to grow into a self-aware, autonomous scientific researcher. At TU/e we challenge you to take charge of your own learning process. 
• An excellent technical infrastructure, on-campus children's day care and sports facilities.  
• An allowance for commuting, working from home and internet costs. 
• A Staff Immigration Team and a tax compensation scheme (the 30% facility) for international candidates. 

Information

This position will be embedded into the Robotics (RBT) section at the Department of Mechanical Engineering. We have a very long and strong track record of both industrial collaboration and fundamental research. The lab is provided with state-of-the-art robot manipulators, motion capture systems, and computational hardware, with support of six technicians with complementary expertise and a robotics research software engineer who provides continuity and support of the developed software stack. We strongly collaborate with the interdisciplinary ecosystems, such as Eindhoven AI Systems Institute (EAISI) and industries in the Brainport region.

Do you recognize yourself in this profile and would you like to know more? Please contact the hiring manager Alessandro Saccon, Associate Professor (a.saccon@tue.nl).

Visit our website for more information about the application process or the conditions of employment. You can also contact HR advice (HRadviceME@tue.nl or +31 40 2475902).

Are you inspired and would like to know more about working at TU/e? Please visit our career page.

Application

We invite you to submit a complete application by using the apply button. The application should include a:

• Cover letter in which you describe your motivation and qualifications for the position.
• Curriculum vitae, potentially including a list of your publications, software projects (GitHub/GitLab), and the contact information of three references.
• Your MSc thesis report and eventually a small description of past research projects involving experimental or numerical work connected to robotic manipulation (with potential weblink to videos).
• If applicable, the most recent IELTS/TOEFL/Cambridge English (or similar) exam result.

We look forward to receiving your application and will screen it as soon as possible. The vacancy will remain open until the position is filled.