phd robotics netherlands

Mission driven

• Minor Robotics
• Other Minors
• Honours Class
• ROS Academy

Mission driven education: training robotic minds

Students and PhD’s are on a mission: they want to build robots and invent new robotic applications. TU Delft Robotics Institute helps them become inventors by offering mission driven education and – via RoboValley – by closing the gap between academia and the market.

Due to the multidisciplinary nature of robotics, there isn’t a straight path to becoming a robotics expert. Students must first specialise in mechanical engineering, electrical engineering, computer science, industrial design engineering or aerospace engineering before they can work successfully in the field of robotics.

But it is important that students can start their robotics mission as soon as they enter the university. Therefore, TU Delft Robotics Institute offers an Honours Programme Robotics for talented freshmen as well as a minor robotics for third-year BSc. Next to that, the Institute is working on a broader robotics curriculum, comparable to the bachelor liberal arts & sciences. In the end, a full robotics education programme will be offered by TU Delft Robotics Institute.

"TU Delft Robotics Institute is the place where new robotic inventions are being made"

TU Delft Robotics Institute is the place where new robotic inventions are being made. But we want those inventions to reach the market as well, so that society can benefit from the next generation robots. RoboValley, which emanated from TU Delft Robotics Institute, narrows the gap between the inventors and businesses.

RoboValley facilitates the collaboration between the, over 170, robotics researchers, other experts, entrepreneurs and decision makers in both public and private sectors. Thus, a unique network is thriving and RoboValley takes a leading role in the development of the next generation robots.

The combination TU Delft Robotics Institute and RoboValley makes sure that students can not only become inventors but entrepreneurs as well. They also make sure that their inventions can make it to our daily life.

Mission driven education

Javascript isn't supported or has been disabled. Some features on this website may not function as expected.

This website uses cookies to enhance user experience and to provide us with visitor analytics. okay

Engineering Doctorate Robotics (ROB)

Large robot-technical companies created the robotics platform Holland RoboNed in association with different Dutch educational and research institutions in 2010. RoboNed workshops show that there is a need for highly qualified employees, who have been in contact with the state-of-art of robotics. The market requires for high qualified designers who know modern robot-technological issues. But above all, they need employees who know how to work properly in a multidisciplinary design team who are dealing with solving complex issues.

EngD Robotics

The EngD programme in Robotics focuses on creating technical solutions for the industrial sector (i.e. automatic welding robots), for maintenance and inspection (i.e. sewer inspection) and medical use (like rehabilitation or surgical robotics). The track is based on functional and market-based requirements and focuses on quality, environment, safety and sustainability. During the programme, you transfer results into technological innovation in industry and society. A methodological approach, which tackles the always-present uncertainties, always comes first.

Employers of graduates of this EngD programme are often the organizations where the trainees do their design assignments. The branches of these organizations vary from large multinationals to smaller companies in the industrial, maintenance and medical sector.

The two years lasting EngD programme in Robotics combines academic research in a professional context with education in a range of related subjects. It consists of three blocks: a block of professional development, a block with in-depth and broadening courses and a technological design project. These blocks with a total of 120 EC can run parallel to each other.

The block with in-depth and broadening courses can partly be tailored to the technological design project. Gained skills in professional development and gained knowledge from in-depth and broadening courses are employed in the design project. During the design project, you transfer results into technological innovation in industry or society.

PROFESSIONAL DEVELOPMENT COURSES

The professional development courses are intended to improve professional skills and advance career opportunities. Therefore, the course in Professional Effectiveness and the TGS Introductory Workshop is compulsory. Other courses are elective and can be chosen in consultation with your supervisors. The total study load of the professional development courses is 6-10 EC. See  www.utwente.nl/ctd  for an overview of professional development courses.

IN-DEPTH AND BROADENING COURSES

The In-Depth and Broadening block carries a total study load of at least 42 EC and comprises a compulsory block and an elective block.

Compulsory courses (depending on your specialisation domain)

The compulsory block includes three compulsory courses:

• Systems Design & Engineering
• Modern Robotics for EngD

Besides, one course can be chosen from a set of 3 courses:

• Modelling and Simulation
• Design Principles for Precision Mechanics
• System Identification and Parameter Estimation

The compulsory courses will always be at a post-master level (master courses need to be upgraded to post-master courses).

Elective Courses

The elective block of at least 15 EC allows you to extend your competencies in a specific direction as further preparation for the design project. For the composition of this elective block, together with your (daily) supervisors, you can select courses which are of interest for the technological design project. Elective courses can either be master courses or post-master courses at the University of Twente, national research schools, Capita Selecta courses, conference visits (incl. paper and/or poster), summer schools, in-company courses, or courses at another 4TU location.  

DESIGN PROJECT

The design project will be defined in close consultation with the organisation or institution which you will be working for. The project can arise from a design question from the organisation/institution or from the valorisation of PhD research where the industry/government has an inquiry. The programme ensures that the design project is innovative and complex, contains sufficient design aspects and is sufficiently multidisciplinary. The design project is individual in the sense that you have your project. Because of the complex and multidisciplinary character of the project, in most projects, you will work together with colleagues. The University of Twente ensures that there is a clear part of the design, for which you are responsible and for which you will be judged.

Target groups

The EngD-programme in Robotics focuses on these target groups:

• Talented graduates of a Master of Science in the field of robotics, or a related discipline (national and international), with a special interest in design cases;
• Graduates of a Master of Science in robotics, or related discipline, with several years of experience within the field. Besides, these graduates must have the ambition and talent to accelerate in finding solutions / creating designs for complex robotic issues with a multidisciplinary character.
• Graduates of a Master of Science in Robotics working at your organization, who have the ambition to get out the most of their career.

The EngD programme focuses on talented graduates with an interest in designing solutions for complex robot technical problems. This means that not everyone will be allowed and that the selection for this track will be strict.

Selection criteria

Candidates will be tested based on these selection criteria:

• CV candidate, with special attention to  results MSc ;  other diplomas, courses ; and  years and types of work experience (if applicable)
• Motivation candidate, with a special focus on demonstrable affinity with design and multidisciplinary assignments
• Professional skills, such as English language skills, communication and interpersonal skills, teamwork, initiative and self-reflection
• Letter(s) of recommendation to senior / graduate professor

Candidates with a non-Dutch qualification and who have not had secondary and tertiary education in English can only be admitted with an IELTS test showing a total band score of at least 6.5, internet TOEFL test (TOEFL-iBT) showing a score of at least 90, or a Cambridge CAE-C (CPE).

The selection will be done by the EngD-selection committee.

Experiences

Interested?

If you are interested in this EngD track Robotics, read more about  how to apply .

If you have any further questions about the EngD programme in Robotics, please contact:

13 Best universities for Robotics in the Netherlands

Updated: February 29, 2024

• Art & Design
• Computer Science
• Engineering
• Environmental Science
• Liberal Arts & Social Sciences
• Mathematics

Below is a list of best universities in the Netherlands ranked based on their research performance in Robotics. A graph of 115K citations received by 5.57K academic papers made by 13 universities in the Netherlands was used to calculate publications' ratings, which then were adjusted for release dates and added to final scores.

We don't distinguish between undergraduate and graduate programs nor do we adjust for current majors offered. You can find information about granted degrees on a university page but always double-check with the university website.

1. Delft University of Technology

For Robotics

2. University of Twente

3. Eindhoven University of Technology

4. Utrecht University

5. University of Amsterdam

6. Free University Amsterdam

7. University of Groningen

8. Wageningen University

9. Radboud University

10. Maastricht University

11. Leiden University

12. Tilburg University

13. Erasmus University Rotterdam

The best cities to study Robotics in the Netherlands based on the number of universities and their ranks are Delft , Enschede , Eindhoven , and Utrecht .

Engineering subfields in the Netherlands

44 robotics PhD positions in Netherlands

Filtered by.

• Netherlands

Refine Your Search

• Last-24-hours 3
• Last-3-days 4
• Last-30-days 15
• Scholarship 43
• Research Job 1
• University of Groningen 8
• Delft University of Technology 7
• Eindhoven University of Technology (TU/e) 7
• AcademicTransfer 6
• Delft University of Technology (TU Delft) 5
• Eindhoven University of Technology 4
• University of Twente (UT) 2
• Erasmus University Rotterdam 1
• University Medical Centre Groningen (UMCG) 1
• University of Twente 1
• Utrecht University 1
• Vrije Universiteit Amsterdam (VU) 1
• Computer Science 25
• Medical Sciences 7
• Engineering 6
• Arts and Literature 3
• Chemistry 3
• Psychology 3
• Mathematics 2
• Education 1

PhD Student Position in Robot Learning and Representation Learning

robot learning & representation learning. You will be jointly supervised by the Assistant Professors Kevin Sebastian Luck (Computational Intelligence Group) and Shujian Yu (Quantitative Data Analysis

PhD Towards Human Interaction in Soft Robotics

PhD Towards Human Interaction in Soft Robotics PhD Towards Human Interaction in Soft Robotics Published Deadline Location today 11 Apr Eindhoven Are you fascinated by the potential of soft robotics

Job related to staff position within a Research Infrastructure? No Offer Description Soft robotics holds promise for a broad range of applications that involve interactions with humans including

PhD Position in Materials Chemistry and Surgical Robotics

that do not resemble the nature of the tissue surrounding it, such as a cardiovascular stent. This PhD project will design, synthesize, and operate a new multi-responsive soft miniaturized robot /device

PhD Position Safe Planning and Control for Autonomous Robots

How can autonomous robots prove that their plans are always safe? Ensuring safe planning and control is paramount when we deploy autonomous robots in complex environments around humans, such as in

Fully funded PhD position in robot world models and building digital twins

Job related to staff position within a Research Infrastructure? No Offer Description Project Description Mobile robots rely on skill-specific world models to perform tasks efficiently. These models

PhD position Biomimetic Robotics and Biomechanics: Bird-Inspired Aerial Robot Design (1.0 FTE)

Are you passionate about aerial robot design and biomechanics of flight? Applications are invited for a fully funded PhD position with Prof.dr.ir. David Lentink in the Biomimetics Group at Groningen

PhD position Biomimetic Robotics and Biomechanics: Bird-Inspired Aerial Robot Design (1.0 FTE) (V23.0822) « Back to the overview Job description Are you passionate about aerial robot design and

PhD position: Can Clinical Language Processing Improve Decisions?

settings. The challenge This research project focuses on developing natural language robots to support clinical decisions. These language robots are computer programs with the ability to understand spoken

PhD Position Integrated Planning and Learning for Drones

of robotic learning. The research will especially focus on planning for small drones operating in challenging scenarios, e.g. monitoring plant parameters in greenhouses, where commonly used conventional

Searches related to robotics

• robotics phd
• engineering
• machine learning
• mechatronics
• computer science
• phd robotics phd
• postdoctoral
• phd robotics

• Search Education
• Challenge Based Learning
• Internationally renowned research and education
• A great boost for your career
• Strong ties with industry
• Excellent atmosphere
• Bachelorprograms
• Program structure
• Study-choice check
• Honors Academy
• Types of universities
• Upcoming events
• For teachers and deans
• Master programs
• How we teach
• EngD at TU/e
• Graduate programs
• Professional Education
• Bachelor programs
• EngD programs
• PhD Doctor of Philosophy
• Admission and enrollment
• Tuition fees and other study costs
• Scholarships and grants
• Immigration, bank account and insurance
• Extra support during your studies
• Master Kick-off
• Welcome Day Internationals
• Exchange students
• Education Innovation Projects
• News and Events
• Testimonials

PhD at TU/e

• Open PhD positions
• I'm a PhD candidate at TU/e
• Defenses and ceremonies
• Chat with our students
• Becoming a PhD candidate
• Life as PhD
• After your PhD

Do you have a master's degree, and do you aspire to a career in scientific research? Then consider a PhD position at TU/e. For four years, you will conduct (paid) in-depth research within a specific field of research. At a top international university known for its strong ties with industry, right in the middle of Brainport (the smartest region in the world).

What does a PhD at TU/e entail?

In four years, you will become an excellent, independent researcher. A professor will assist you in conducting in-depth, groundbreaking research in the field of your choice. You will work together with other research groups, industrial partners, and research institutions, depending on the subject of your research. After successfully defending your dissertation, you will be awarded the PhD title.

A PhD program offers you a great deal of freedom to conduct research into socially relevant topics. You can develop your ideas in an environment with state-of-the-art research facilities. 

• Explore our research groups

Why become a PhD candidate at TU/e?

If you choose to pursue a PhD at TU/e, you will be given the space and support to excel in your field. In addition, our small-scale and personal approach makes it easy to communicate and collaborate with other departments and research groups. Also, PhD candidates are valued employees at our university. Most have an employment contract and therefore receive a salary during their training.

Meet some of our PhD candidates

Open culture.

The Netherlands has an open, friendly culture and a population that speaks English well. At TU/e you will find students from more than 80 different countries, who come together in one of the many communities. We embrace diversity and inclusion, as it adds to our success and pleasure in education and research. TU/e is a university where students and lecturers know each other on a first-name basis and work together on innovative projects with real-life significance.   

State-of-the-art research facilities

To conduct groundbreaking research, to attract outstanding scientific talent, and to train new generations of engineers, we have ultramodern research labs and facilities at our disposal. Some of our labs are unique in the Netherlands, or even in the world.

PROOF program

As a PhD candidate, you will plunge into an intensive learning experience over a period of four (or five) years. Learning takes place all the time, both consciously and subconsciously: on the job, when interacting with others, while (informally) researching, and during courses and workshops. To support and facilitate the development of your competences, TU/e offers a dedicated training program for PhD candidates.

Is a PhD track right for me?

To successfully pursue a PhD, you must be able to work and write independently. In addition, you have an above-average interest in technology, are a go-getter, and can think analytically. Of course, you enjoy doing research and finding out the underlying cause of things. Finally, you need to have a suitable prior education. 

• More information about requirements

Or an EngD (Engineering Doctorate)?

Do you want to continue your education, but not spend four years doing in-depth research? In that case an EngD program might be something for you: a two-year, paid, full-time program to become a technological designer. You will expand your technological knowledge, gain practical experience with the latest methods, and work on your professional skills. The main difference between an EngD program and a PhD track is its focus. A PhD is aimed at establishing yourself as an independent researcher. On the other hand, an EngD prepares you for a high-level position in industry. 

• More information about EngD

CHAT WITH OUR STUDENTS

They are happy to answer your questions and share their experiences!

Events and information for PhD's

Watch the program video where a PhD candidate and an EngD trainee will tell you more about their experiences at TU/e. Ask your question(s) directly to one of our PhD students. Or visit our Graduate School Event on campus!

• CREATE AN ACCOUNT OR LOG IN

Program videos

Want to know more about our bachelors, masters, EngD or PhD programs? Watch one of our program videos presented by our staff and students.

Master's Open Day

Visit the TU/e during the open day of our Graduate School

Fact & Figures PhD candidates

1650 phd candidates.

About 1650 people are working as a PhD candidate at TU/e.

PhD Defenses

Every year about 225 PhD’s defenses take place.

Male Female Ratio

About 33% of the PhD candidates are women, 67% are men.

International environment

About 60% of our PhD candidates have an international background. The other 40% have Dutch nationality. English is our working language.

Average duration

On average, the duration of the PhD trajectory at TU/e is one of the shortest in the Netherlands.

Satisfaction

PhD candidates assess their PhD trajectory on average with a 7.5 (on a scale of 1-10).

PhD research

PhD research is at the heart of what we do as a University. Around 2000 PhD candidates are involved in research and education at the UvA and around 400 doctorates are conferred each year. Two-thirds of these are in the Sciences or Medicine.

PhD vacancies

Getting your PhD at the UvA

UvA Staff Housing

This PDF brings together all kinds of information about the PhD process, from the regulations and different steps in the process to terms of employment and facilities you can make use of as a PhD candidate.

Doctoral programme: from admission to completion

Documents and forms, phd contact information, central phd council, cookie consent.

The UvA uses cookies to ensure the basic functionality of the site and for statistical and optimisation purposes. Cookies are also placed to display third-party content and for marketing purposes. Click 'Accept all cookies' to consent to the placement of all cookies, or choose 'Decline' to only accept functional and analytical cookies. Also read the UvA Privacy statement .

Institute for Robotics and Intelligent Machines

Ph.D. Program

Ph.d. program in robotics.

Offered jointly by the College of Computing and the College of Engineering, the Ph.D. program in Robotics is the first truly multidisciplinary robotics degree of its kind in the world—and only the second robotics doctorate offered in the U.S. The program involves the schools of Interactive Computing, Electrical & Computer Engineering, Mechanical Engineering, Biomedical Engineering and Aerospace Engineering.

We educate a new generation of robotics researchers who are prepared to be impactful contributors upon entering the high-tech workforce. The Institute for Robotics & Intelligent Machines (IRIM) serves as the flagship for Tech’s robotics efforts; therefore, IRIM has an integral relationship with the program, and many IRIM faculty members serve as research advisors to students pursuing the degree. The Robotics program supports Tech’s mission to provide instruction in disciplines related to science, technology, and interdisciplinary areas.

Program of Study

The main emphasis of the Ph.D. program is the successful completion of an original and independent research thesis. The degree requirements are designed around this goal.

Minimum Requirements

• Completion of 36 semester hours of courses with a letter grade
• Passing a comprehensive qualifying exam with written and oral components.
• Successfully conducting, documenting, and defending a piece of original research culminating in a doctoral thesis.

PLEASE NOTE

Home Unit Teaching Apprenticeship and Extra-curricular Requirements Robotics Ph.D. students are subject to their home unit's teaching apprenticeship requirements (e.g., a certain number of semesters serving as a TA) and other the extra-curricular requirements such as seminar attendance or annual review process. For example, students with home units in BME, IC, and ME are required to do two semesters of teaching practicum or apprenticeship and register for the corresponding courses. Students should contact their home units for details for any departmental requirements that are in addition to the Robotics degree requirements. Students are responsible for ensuring that they understand and satisfy any home unit requirements as well as the Robotics program and Institute requirements.

*A maximum of two classes (6 semester hours) at the 4000 level may be used to satisfy the minor requirements only. No courses used to satisfy any bachelor's degree requirements can be used towards a graduate degree.

DOWNLOAD THE ROBOTICS Ph.D. HANDBOOK HERE

Program director dr. nader sadegh, faculty coordinators .

For questions about academic and research components of the program, contact the faculty member for your area. All questions about application procedures and processes, as well as additional contact information, may be found on the schools’ websites.

• Mechanics: Frank Hammond , ME/BME
• Control: Patricio Vela , ECE
• Perception : Jim Rehg , IC
• HRI: Karen Feigh , AE 

The RoboGrads site offers a lot of useful information!

• Home  > 
• Scholarships  > 

International PhD Position in Surgical Robotics, Netherlands

•  Not Specified
•   Netherlands
• $$  Full-time position with a starting salary of €2,770 in the first year, increasing to €3,539 in the fourth year gross per month.

The Department of Biomechanical Engineering at the University of Twente, The Netherlands, is delighted to announce International PhD Position in Surgical Robotics for the academic session 2024/2025.

The research project aims to develop methods for modeling and controlling soft/flexible surgical devices and medical microrobots to enhance targeting accuracy during minimally invasive procedures. The project involves collaboration with the Surgical Robotics Laboratory, the Department of Biomechanical Engineering, and other esteemed institutions, focusing on improving clinical outcomes and advancing medical technologies.

Universiteit Twente Information

Eligibility Criteria

Are you looking for Scholarships in 2022-2023? We are happy to help you find best matches! Plus more!

Offered Benefits

Application process.

Subscribe for Scholarship Updates

Get a weekly email that thousands of students use to get the latest scholarships and grants.

** Scholarships.plus will not share your details without your permission.

More Suggestions:

We are building a new Scholarship Assistant This assistant will simplify your search and monitoring of the scholarships relevant to your study and needs.

Select language

Neuroscience and Cognition Utrecht

Phd programs.

The NC Utrecht environment harbors close to 300 PhD students. Most of them participate in one of the following PhD training programs:

Clinical & Experimental Neuroscience , provided by the Rudolf Magnus Institute

Cognition & Behaviour, provided by the Helmholtz Institute

Linguistics, provided by the Institute for Language Sciences .

The PhD programs of Clinical & Experimental Neuroscience  and Cognition & Behaviour are also part of the Graduate School of Life Sciences . The program on Linguistics is part of the Graduate School of Humanities .

Utrecht University Heidelberglaan 8 3584 CS Utrecht The Netherlands Tel. +31 (0)30 253 35 50

Unlock over 16 fully-funded PhD positions available in diverse fields at prestigious universities in Sweden and the Netherlands!

Are you looking for exciting PhD positions at esteemed universities in Sweden and the Netherlands?

Over 16 fully-funded multiple doctoral scholarships in diverse fields are available at various universities in Sweden and the Netherlands for the year 2024. These fellowships provide funding for doctoral researchers to conduct their research projects at universities, research institutions, and other organizations in these countries. These PhD positions are funded by prestigious sources including the MSCA doctoral program and other funding programs.

For detailed information on specific doctoral positions, please visit the provided links to explore corresponding PhD scholarships, which include specific requirements and application procedures.

PhD positions available in Swedish universities.

1. Computational condensed matter physics, Linköping University

2. Urban Freight Management, Chalmers University of Technology

3. eDNA environmental monitoring, Sveriges lantbruksuniversitet

4. Cyber-Physical Systems (CPS), Luleå University of Technology

5. Medical Science - Regional differences in gestational duration, University of Gothenburg

6. Computational Sciences within the national Data-Driven Life Sciences program, Umeå universitet

7. Computational biology of infection, Lunds universitet

PhD positions available in Dutch/Netherlands universities.

8. Donders Centre of Neuroscience - Motor Disorder Rehabilitation, Radboud University

9. Human-aligned Video-AI, University of Amsterdam (UvA)

10. Multivariate Dependence Modelling and Statistical Machine Learning Algorithms for Patient Risk Profiling, Delft University of Technology (TU Delft)

11. Computational Cognitive Neuroscience at the Predictive Brain Lab, Radboud University

12. Atmospheric Sciences - Unraveling the mesoscale organisation of shallow convective clouds for better climate projection, Wageningen University & Research

13. Dynamic On-Body and In-Body Compression Systems, University of Twente (UT)

14. Modelling Micropollutant Removal using Charge-Mosaic Nanofiltration Membranes, University of Twente (UT)

15. Economic Life Cycle Costing and Life Cycle Sustainability Assessment of Hydropower, University of Twente (UT)

16. Environmental Life Cycle Assessment of Hydropower, University of Twente (UT)

Don't miss this exceptional opportunity to advance your research career!! Apply now!

Animal brain inspired AI game changer for autonomous robots

A team of researchers at Delft University of Technology has developed a drone that flies autonomously using neuromorphic image processing and control based on the workings of animal brains.  Animal brains use less data and energy compared to current deep neural networks running on GPUs (graphic chips). Neuromorphic processors are therefore very suitable for small drones because they don’t need heavy and large hardware and batteries. The results are extraordinary: during flight the drone’s deep neural network  processes data up to 64 times faster and consumes three times less energy than when running on a GPU. Further developments of this technology may enable the leap for drones to become as small, agile, and smart as flying insects or birds. The findings were recently published in Science Robotics. 

Learning from animal brains: spiking neural networks

Artificial intelligence holds great potential to provide autonomous robots with the intelligence needed for real-world applications. However, current AI relies on deep neural networks that require substantial computing power. The processors made for running deep neural networks (Graphics Processing Units, GPUs) consume a substantial amount of energy. Especially for small robots like flying drones this is a problem, since they can only carry very limited resources in terms of sensing and computing.  

Animal brains process information in a way that is very different from the neural networks running on GPUs. Biological neurons process information asynchronously, and mostly communicate via electrical pulses called spikes. Since sending such spikes costs energy, the brain minimizes spiking, leading to sparse processing.  

Inspired by these properties of animal brains, scientists and tech companies are developing new, neuromorphic processors. These new processors allow to run spiking neural networks and promise to be much faster and more energy efficient. 

“The calculations performed by spiking neural networks are much simpler than those in standard deep neural networks.”, says Jesse Hagenaars, PhD candidate and one of the authors of the article, “Whereas digital spiking neurons only need to add integers, standard neurons have to multiply and add floating point numbers. This makes spiking neural networks quicker and more energy efficient. To understand why, think of how humans also find it much easier to calculate 5 + 8 than to calculate 6.25 x 3.45 + 4.05 x 3.45.” 

This energy efficiency is further boosted if neuromorphic processors are used in combination with neuromorphic sensors, like neuromorphic cameras. Such cameras do not make images at a fixed time interval. Instead, each pixel only sends a signal when it becomes brighter or darker. The advantages of such cameras are that they can perceive motion much more quickly, are more energy efficient, and function well both in dark and bright environments. Moreover, the signals from neuromorphic cameras can feed directly into spiking neural networks running on neuromorphic processors. Together, they can form a huge enabler for autonomous robots, especially small, agile robots like flying drones. 

First neuromorphic vision and control of a flying drone

In an article published in Science Robotics on May 15, 2024, researchers from Delft University of Technology, the Netherlands, demonstrate for the first time a drone that uses neuromorphic vision and control for autonomous flight. Specifically, they developed a spiking neural network that processes the signals from a neuromorphic camera and outputs control commands that determine the drone’s pose and thrust. They deployed this network on a neuromorphic processor, Intel’s Loihi neuromorphic research chip, on board of a drone. Thanks to the network, the drone can perceive and control its own motion in all directions. 

“We faced many challenges,” says Federico Paredes-Vallés, one of the researchers that worked on the study, “but the hardest one was to imagine how we could train a spiking neural network so that training would be both sufficiently fast and the trained network would function well on the real robot. In the end, we designed a network consisting of two modules. The first module learns to visually perceive motion from the signals of a moving neuromorphic camera. It does so completely by itself, in a self-supervised way, based only on the data from the camera. This is similar to how also animals learn to perceive the world by themselves. The second module learns to map the estimated motion to control commands, in a simulator. This learning relied on an artificial evolution in simulation, in which networks that were better in controlling the drone had a higher chance of producing offspring. Over the generations of the artificial evolution, the spiking neural networks got increasingly good at control, and were finally able to fly in any direction at different speeds. We trained both modules and developed a way with which we could merge them together. We were happy to see that the merged network immediately worked well on the real robot.” 

With its neuromorphic vision and control, the drone is able to fly at different speeds under varying light conditions, from dark to bright. It can even fly with flickering lights, which make the pixels in the neuromorphic camera send great numbers of signals to the network that are unrelated to motion.  

Improved energy efficiency and speed by neuromorphic AI

“Importantly, our measurements confirm the potential of neuromorphic AI. The network runs on average between 274 and 1600 times per second. If we run the same network on a small, embedded GPU, it runs on average only 25 times per second, a difference of a factor ~10-64! Moreover, when running the network, , Intel’s Loihi neuromorphic research chip consumes 1.007 watts, of which 1 watt is the idle power that the processor spends just when turning on the chip. Running the network itself only costs 7 milliwatts. In comparison, when running the same network, the embedded GPU consumes 3 watts, of which 1 watt is idle power and 2 watts are spent for running the network. The neuromorphic approach results in AI that runs faster and more efficiently, allowing deployment on much smaller autonomous robots.”, says Stein Stroobants, PhD candidate in the field of neuromorphic drones. 

Future applications of neuromorphic AI for tiny robots

“Neuromorphic AI will enable all autonomous robots to be more intelligent,” says Guido de Croon, Professor in bio-inspired drones, “but it is an absolute enabler for tiny autonomous robots. At Delft University of Technology’s Faculty of Aerospace Engineering, we work on tiny autonomous drones which can be used for applications ranging from monitoring crop in greenhouses to keeping track of stock in warehouses. The advantages of tiny drones are that they are very safe and can navigate in narrow environments like in between ranges of tomato plants. Moreover, they can be very cheap, so that they can be deployed in swarms. This is useful for more quickly covering an area, as we have shown in exploration and gas source localization settings.” 

“The current work is a great step in this direction. However, the realization of these applications will depend on further scaling down the neuromorphic hardware and expanding the capabilities towards more complex tasks such as navigation.” 

“ Fully neuromorphic vision and control for autonomous drone flight ”, F. Paredes-Vallés, J. J. Hagenaars, J. Dupeyroux, S. Stroobants, Y. Xu, G. C. H. E. de Croon, Science Robotics, May 15, 2024.  

Guido de Croon (Principal Investigator)

• 0031-152781402
• g.c.h.e.decroon@tudelft.nl

Science Information Officer Digital Society

Marc de kool.

• 06 1003 8065
• a.j.m.deKool@tudelft.nl

Available: Monday to Thursday.

Micro Air Vehicle Lab TU Delft

Share this page:.

Meet the daughter of Nigerian immigrants who is the first Black woman to earn U-M Robotics PhD

Oluwami (Wami) Dosunmu-Ogunbi is the first Black woman to get a PhD in robotics at the University of Michigan . The daughter of Nigerian immigrants set off on her educational career with no clear end goal in mind. After graduating with her bachelor’s degree, she decided to devote the next five years to research, excited by the PhD regalia. 

However, it wasn’t until recently that she understood there were several ways she could apply her engineering background to better people’s lives.

At the engineering graduate commencement ceremony on May 1, Ogunbi shared her story of failure and support. “I do not stand here on my own two feet alone. None of us got here by our individual merit alone,” she said, per the University of Michigan .

She entered the U-M mechanical engineering PhD program adorned with academic awards, including her MVP award from the University of Illinois ’ Pi Tau Sigma chapter, the mechanical engineering honor society. Despite this, she failed the U-M mechanical engineering PhD program’s qualifying tests.

She sought counsel from robotics professor Chad Jenkins, her mentor, when she considered leaving during the pandemic. Seeing Ogunbi’s promise, the lecturer worked quickly to put her in contact with robotics professor Jessy Grizzle, who, along with Jenkins, was a major figure in the founding of Michigan’s robotics program.

Grizzle, for his part, postponed his retirement plans and invited Ogunbi to work in his lab as his last PhD student. Ogunbi attempted her qualifying examinations again, and, fortunately, she found inspiration from Kira Barton, a robotics professor, and Robert Gregg, an associate professor of robotics, who asked questions that helped Ogunbi regain her confidence and get back on track.

Surrounded by a group of professors and colleagues who provided the necessary support, Ogunbi completed her study, with the main outcome being the development of a new stair-climbing controller for bipedal walking robots. She even performed the first demonstration of a bipedal robot stepping on, riding, and getting off a moving walkway.

Her most recent accomplishments are just a few of her distinctions. The university stated that Ogunbi has been a prominent member of the robotics community, having been appointed an outreach ambassador by Robotics for three consecutive years, 2021–2023, and receiving an MLK Spirit Award for mentorship and inspiration from the College of Engineering. She also placed second in the College of Engineering’s 3-minute thesis competition.

She has been admitted to the Bouchet Society, which celebrates outstanding scholarly performance and supports diversity in graduate education and the professoriate.

Ogunbi is currently applying for faculty positions.