Fully funded PhD position in robot world models and building digital twins
Fully funded PhD position in robot world models and building digital twins
You cannot apply for this job anymore (deadline was 24 Mar 2024).
Browse the current job offers or choose an item in the top navigation above.
Job description
Project Description
Mobile robots rely on skill-specific world models to perform tasks efficiently. These models, essential for path-planning, obstacle avoidance, and action planning, require regular updates to be able to describe the true state of the world reliably. In multi-robot systems, this update process becomes time-consuming and resolutions of conflicting world representation by different robots need to be resolved. In this PhD project we will explore approaches to create building digital twins (BDTs) that are robot-independent and represent the geometry as well as the semantic of the environment at hand.
BDTs provide a comprehensive, real-time representation of a facility, including semantic elements, 3D geometry, and material properties. By interpreting the BDT data, we seek to generate skill-specific world models for various robot types and skills. Leveraging our previous research [1-3], we can initialize the BDT from data extracted from Building Information Models (BIM) or convert point-cloud data in a similar representation.
Multiple heterogenous robots can then query the BDT to retrieve maps that are tailored to their physical characteristics and navigation skills. Because all maps are generated from the same source, we argue that maintaining a consistent BDT by merging information from the heterogenous robots becomes easier.
References:
[1] Pauwels, P., de Koning, R., Hendrikx, B., & Torta, E. (2023). Live semantic data from building digital twins for robot navigation: Overview of data transfer methods. Advanced Engineering Informatics, 56, 101959.
[2] de Vos, K., Torta, E., Bruyninckx, H., Martinez, C. A., & van de Molengraft, M. J. G. (2023). Automatic Configuration of Multi-Agent Model Predictive Controllers based on Semantic Graph World Models. arXiv preprint arXiv:2311.01180.
[3] Hendrikx, R. W. M., Pauwels, P., Torta, E., Bruyninckx, H. P., & van de Molengraft, M. J. G. (2021, May). Connecting semantic building information models and robotics: An application to 2D LiDAR-based localization. In 2021 IEEE International Conference on Robotics and Automation (ICRA) (pp. 11654-11660). IEEE.
Candidate Responsibilities:
As a PhD candidate in this project, your responsibilities will include:
1. Developing methods for skill-specific world model generation from Building Digital Twins (BDTs).
2. Investigating techniques to trigger BDT updates based on discrepancies between robot perceptual data and world models.
3. Collaborating with leading research groups at Eindhoven University of Technology (TU/e) and the Technical University of Munich (TUM). The candidate is required to spend 6 months at TU Munich during the duration of the PhD project.
4. Working on a physical demonstrator in the DSD Robotics lab of TU/e, showcasing practical implementation of robotic navigation based on the created BDT.
We offer a supportive research environment with access to state-of-the-art facilities. You will have the opportunity to make a meaningful contribution to the field of robotics and automation. Funding for your PhD studies is available, and your work will have real-world applications in areas such as the logistic and agro-food sectors.
TU/e will offer you plenty of opportunities for development. You can join the DISC (Dutch Institute for Systems and Control) school as well as several programs offered by TU/e for personal development.
We are looking for a very motivated candidate with eagerness to learn and approach problems from a fundamental as well as a practical perspective. When selected you will join the CST group of the Mechanical Engineering Department.
The Control Systems Technology (CST; website) section as part of the department of Mechanical Engineering (ME) has an internationally recognized reputation in mechatronics, precision motion control and robotics. CST targets areas in Precision Machines, Robotics, Biomedical and Automotive engineering by designing performance-based controllers, intelligent machine and algorithm designs. CST has a track record of over twenty years in bringing state-of-the-art systems and control theory into new designs and high-tech applications.
The CST group has a track record in European projects. It was coordinator of the FP7 - ROBOEARTH project, is and has been participating in H2020 projects EUREYECASE, ROPOD, AUTOPILOT and more recently SAFE-UP and many more European and nationally funded projects (INTEREG, OPZUID, FAST).
Since 2005, CST is the main contributor to the TU/e RoboCup team, named Tech United, 6 times world champion ('12, '14, '16, '18, '19, '23) in the Middle Size League and the 2019 world champion in the @Home Domestic Platform League with the TOYOTA Human Support Robot. The model-based, multidisciplinary-oriented approach has proven to be highly valuable in the field of robotics. The CST group is led by Prof. M. Steinbuch and has produced 5 start-ups in the past 10 years (Preceyes, MicroSure, Eindhoven Medical Robotics, Smart Robotics and recently RUVU- behavior for robots).
Mobile robots rely on skill-specific world models to perform tasks efficiently. These models, essential for path-planning, obstacle avoidance, and action planning, require regular updates to be able to describe the true state of the world reliably. In multi-robot systems, this update process becomes time-consuming and resolutions of conflicting world representation by different robots need to be resolved. In this PhD project we will explore approaches to create building digital twins (BDTs) that are robot-independent and represent the geometry as well as the semantic of the environment at hand.
BDTs provide a comprehensive, real-time representation of a facility, including semantic elements, 3D geometry, and material properties. By interpreting the BDT data, we seek to generate skill-specific world models for various robot types and skills. Leveraging our previous research [1-3], we can initialize the BDT from data extracted from Building Information Models (BIM) or convert point-cloud data in a similar representation.
Multiple heterogenous robots can then query the BDT to retrieve maps that are tailored to their physical characteristics and navigation skills. Because all maps are generated from the same source, we argue that maintaining a consistent BDT by merging information from the heterogenous robots becomes easier.
References:
[1] Pauwels, P., de Koning, R., Hendrikx, B., & Torta, E. (2023). Live semantic data from building digital twins for robot navigation: Overview of data transfer methods. Advanced Engineering Informatics, 56, 101959.
[2] de Vos, K., Torta, E., Bruyninckx, H., Martinez, C. A., & van de Molengraft, M. J. G. (2023). Automatic Configuration of Multi-Agent Model Predictive Controllers based on Semantic Graph World Models. arXiv preprint arXiv:2311.01180.
[3] Hendrikx, R. W. M., Pauwels, P., Torta, E., Bruyninckx, H. P., & van de Molengraft, M. J. G. (2021, May). Connecting semantic building information models and robotics: An application to 2D LiDAR-based localization. In 2021 IEEE International Conference on Robotics and Automation (ICRA) (pp. 11654-11660). IEEE.
Candidate Responsibilities:
As a PhD candidate in this project, your responsibilities will include:
1. Developing methods for skill-specific world model generation from Building Digital Twins (BDTs).
2. Investigating techniques to trigger BDT updates based on discrepancies between robot perceptual data and world models.
3. Collaborating with leading research groups at Eindhoven University of Technology (TU/e) and the Technical University of Munich (TUM). The candidate is required to spend 6 months at TU Munich during the duration of the PhD project.
4. Working on a physical demonstrator in the DSD Robotics lab of TU/e, showcasing practical implementation of robotic navigation based on the created BDT.
We offer a supportive research environment with access to state-of-the-art facilities. You will have the opportunity to make a meaningful contribution to the field of robotics and automation. Funding for your PhD studies is available, and your work will have real-world applications in areas such as the logistic and agro-food sectors.
TU/e will offer you plenty of opportunities for development. You can join the DISC (Dutch Institute for Systems and Control) school as well as several programs offered by TU/e for personal development.
We are looking for a very motivated candidate with eagerness to learn and approach problems from a fundamental as well as a practical perspective. When selected you will join the CST group of the Mechanical Engineering Department.
The Control Systems Technology (CST; website) section as part of the department of Mechanical Engineering (ME) has an internationally recognized reputation in mechatronics, precision motion control and robotics. CST targets areas in Precision Machines, Robotics, Biomedical and Automotive engineering by designing performance-based controllers, intelligent machine and algorithm designs. CST has a track record of over twenty years in bringing state-of-the-art systems and control theory into new designs and high-tech applications.
The CST group has a track record in European projects. It was coordinator of the FP7 - ROBOEARTH project, is and has been participating in H2020 projects EUREYECASE, ROPOD, AUTOPILOT and more recently SAFE-UP and many more European and nationally funded projects (INTEREG, OPZUID, FAST).
Since 2005, CST is the main contributor to the TU/e RoboCup team, named Tech United, 6 times world champion ('12, '14, '16, '18, '19, '23) in the Middle Size League and the 2019 world champion in the @Home Domestic Platform League with the TOYOTA Human Support Robot. The model-based, multidisciplinary-oriented approach has proven to be highly valuable in the field of robotics. The CST group is led by Prof. M. Steinbuch and has produced 5 start-ups in the past 10 years (Preceyes, MicroSure, Eindhoven Medical Robotics, Smart Robotics and recently RUVU- behavior for robots).
Specifications
- max. 38 hours per week
- Eindhoven View on Google Maps
:fill(white)/logos/tue-en-wide_acOLN2b.png)
Eindhoven University of Technology (TU/e)
Requirements
- A master's degree (or an equivalent university degree) in Physics, Computer Science, Electrical Engineering, Mechanical Engineering or a related discipline
- A research-oriented and proactive attitude.
- Good programming skills in python and/or C/C++.
- Ability to work in a team.
- Flexibility to spend 6 months at TU Munich.
- Excellent written and oral communication skills in English.
- Proactive and entrepreneurial mind-set, getting things done mentality.
- Active former membership of student teams participating in RoboCup are considered as a big plus.
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 evaluation (go/no-go) after nine months. You will spend 10% of your 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. €2,770 max. €3,539).
- 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.
