We are seeking a highly motivated Masters student to join the Service Robotics Team at MIRMI and perform research on cloth manipulation. The research will be jointly supervised by collaborators and will focus on developing novel solutions to address the open problem dynamic real-time cloth folding. Most efforts along the same lines use domain randomization in simulations for sim2real transfer, often overlooking domain adaptation techniques that allow dynamic adjustment based on real-time feedback due to perceptual challenges.Research: In this investigation, we will develop a framework that respects the sim2real transfer using a high level trajectory optimization combined with a low level planning policy. More in detail, the first task is to set-up differentiable simulation environment with a cloth. Then, gather data to set up a learning pipeline for behavior cloning with a real-time visual input. Finally, we carry out experiments on a real robotic system.
Research:
In this investigation, we will develop a framework that respects the sim2real transfer using a high level trajectory optimization combined with a low level planning policy. More in detail, the first task is to set-up differentiable simulation environment with a cloth. Then, gather data to set up a learning pipeline for behavior cloning with a real-time visual input. Finally, we carry out experiments on a real robotic system.
Requirements:
Contact:
Dr. Tianyu Ren (tianyu.ren@tum.de)
Riddhiman Laha (riddhiman.laha@tum.de)
Hamid Sadeghian (hamid.sadeghian@tum.de)
Georg-Brauchle-Ring 60-62, 80992 München
Refenrences:
https://arxiv.org/pdf/2407.01361
To apply:
Send your personal info as attachment to the contact person with the following naming
FirstnameLastname_ Forschungspraxis/Thesis_Staringdate.pdf
e.g., TianyuRen_Thesis_26062024.pdf
Shared autonomy refers to a collaborative control paradigm wherein both a human operator and an autonomous robotic system share the responsibility of executing a task [1]. This approach leverages the strengths of human intelligence—such as intuition, adaptability, and decision-making—alongside the precision, repeatability, and computational power of robots. Consequently, this system is capable of managing complex tasks while enhancing efficiency, safety, and usability.
In this study, we focus on addressing the industrial assembly task through teleoperation skills. However, due to low transparency of the system and human-interaction manner, tackling contact-rich manipulation tasks, particularly those involving tight-clearance manipulation, remains a significant challenge. To remedy this gap, we propose integrating the knowledge gained from robotic assembly tasks into teleoperation within a shared-autonomy framework.
Send your personal CV and transcript as attachment to both yansong.wu(at)tum.de and xiaoyu.chen(at)tum.de.
Project description: The Integrated Bi-Stiffness Actuator (iBSA) [1,2] consists of modules such as motor, spring, brake, clutch, and link (see Fig. 1). With these modules, the actuator can be configured in various operating modes. It also consists of various sensors which enable multiple sensor feedback. The objective is to develop a Modular Low-level Control Framework for Modular Actuator with Multiple Sensor Feedback. By exploiting the modular structure characteristic of the BSA, the effects of each element such as link decoupling, the performance of the elastic element, stiffness brake, and motor control can be tested independently. Moreover, other factors such as friction, hysteresis, effects of coupling and mechanical play between parts, and the effect of switching which creates instantaneous change in velocity can also be analyzed and their effect reduced through control at low-level. The end goal is to integrate the controllers into a generalized framework for the combined system.
Prerequisites:
To apply, send your CV, cover letter, and supporting documents to Samuel Kangwagye (s.kangwagye(at)tum.de).
Chair of Robotics Science and Systems Intelligence
Munich Institute of Robotics and Machine Intelligence
Technical University of Munich
Recent advancements of robotics, especially humanoids and quadruppeds are largely due to the adoption of the novel actuator technologies involving high power density BLDC motors with lower gear ratio for maintaining good proprioceptive feedback and control. [1] However, development is not finished yet, focusing mostly on the way to enable better dynamic behaviour. One of the important directions is augmentatation of such actuators with mechanical springs for storing and releasing energy at the dynamic peaks.
Our works focuses on the developement and testing one such actuator. Thats where the help is needed. In particular, task will be to prepare our Solidworks design for manufacturing, assemble and eventually test all the mechanical functionalities. Further responsibility involves cooridanation with other team members on incoroporating electronics part, modeling, developing and testing simple control of the built setup.
What you will gain:
Requirements from candidates:
To apply, you can send your CV, and short motivation to:
Supervisor
M.Sc. Vasilije Rakcevic
[1] P. M. Wensing, A. Wang, S. Seok, D. Otten, J. Lang and S. Kim, "Proprioceptive Actuator Design in the MIT Cheetah: Impact Mitigation and High-Bandwidth Physical Interaction for Dynamic Legged Robots," in IEEE Transactions on Robotics, vol. 33, no. 3, pp. 509-522, June 2017, doi: 10.1109/TRO.2016.2640183.
You can find more research opportunities at the Chairs of our Principal Investigators!
When you apply for a position with the Technical University of Munich (TUM), you are submitting personal information. With regard to personal information, please take note of the Datenschutzhinweise gemäß Art. 13 Datenschutz-Grundverordnung (DSGVO) zur Erhebung und Verarbeitung von personenbezogenen Daten im Rahmen Ihrer Bewerbung. (data protection information on collecting and processing personal data contained in your application in accordance with Art. 13 of the General Data Protection Regulation (GDPR)). By submitting your application, you confirm that you have acknowledged the above data protection information of TUM.