Max Planck ETH Center for Learning Systems| Acronym | MPG ETH CLS | | Homepage | http://learning-systems.org/ | | Country | [nothing] | | ZIP, City | | | Address | | | Phone | | | Type | Alliance | | Current organization | Max Planck ETH Center for Learning Systems | | Members | |
Open OpportunitiesThis Master's thesis/semester project focuses on the microfluidic fabrication of micromachines with multi-environmental responsiveness. The aim is to develop micromachines capable of adapting to various environmental cues. We envision that these micromachines will be used for complex tasks in biomedical and environmental applications. - Chemistry, Engineering and Technology, Medical and Health Sciences
- ETH Zurich (ETHZ), Internship, Master Thesis, Semester Project, Student Assistant / HiWi
| Event cameras are an exciting new technology enabling sensing of highly dynamic content over a broad range of illumination conditions. The present thesis explores novel, sparse, event-driven paradigms for detecting structure and motion patterns in raw event streams. - Engineering and Technology
- Master Thesis
| Experiment with Gaussian Splatting based map representations for highly efficient camera tracking and simultaneous change detection and map updating. Apply to different exteroceptive sensing modalities. - Engineering and Technology
- Master Thesis
| This project consists of reconstructing soft object along with their appearance, geometry, and physical properties from image data for inclusion in reinforcement learning frameworks for manipulation tasks. - Engineering and Technology
- Master Thesis
| Push the limits of arbitrary online video reconstruction by combining the most recent, prior-supported real-time Simultaneous Localization And Mapping (SLAM) methods with automatic supervision techniques. - Engineering and Technology
- Master Thesis
| Computing, time, and energy requirements of recent neural networks have demonstrated dramatic increase over time, impacting on their applicability in real-world contexts. The present thesis explores novel ways of implementing neural network implementations that will substantially reduce their computational complexity and thus energy footprint. - Engineering and Technology
- Master Thesis
| Quasi-direct drive robot arms experience high deflection in the presence of large end effector forces. This leads to stability issues when these forces change rapidly, such as when dropping a heavy object. Existing works use reinforcement learning to achieve end effector tracking[1] as well as force control[2]. In this project, you will extend upon this by developing a controller capable of tracking end effector poses in the presence of sudden, large changes in end effector disturbance. You will first deploy your controller on a standalone robotic arm and then work towards deployment on our ANYmal-based bimanual mobile manipulator.
[1] Martín-Martín et al., Variable Impedance Control in End-Effector Space:
An Action Space for Reinforcement Learning in Contact-Rich Tasks (IROS 2019)
[2] Portela et al., Learning Force Control for Legged Manipulation (ICRA 2024)
- Robotics and Mechatronics
- Bachelor Thesis, Semester Project
| In the BIROMED-Lab we have been developing an endoscopic system for safer neurosurgeries with inspiration from human finger anatomy. Its two degrees of freedom allow the endoscope to investigate areas of the brain that would be inaccessible with standard rigid endoscopes. Thanks to springs in the transmission between the motors and the movable endoscope tip, the interaction forces between the instrument and the brain tissue can be reduced. Furthermore the interaction forces can be estimated by measuring the deflection of the spring. To make the telemanipulation of the endoscope safer and more intuitive for the surgeon, force feedback was also implemented. - Biomedical Engineering
- Master Thesis
| Robotics is dominated by on-policy reinforcement learning: the paradigm of training a robot controller by iteratively interacting with the environment and maximizing some objective. A crucial idea to make this work is the Advantage Function. On each policy update, algorithms typically sum up the gradient log probabilities of all actions taken in the robot simulation. The advantage function increases or decreases the probabilities of these taken actions by comparing their “goodness” versus a baseline. Current advantage estimation methods use a value function to aggregate robot experience and hence decrease variance. This improves sample efficiency at the cost of introducing some bias.
Stably training large language models via reinforcement learning is well-known to be a challenging task. A line of recent work [1, 2] has used Group-Relative Policy Optimization (GRPO) to achieve this feat. In GRPO, a series of answers are generated for each query-answer pair. The advantage is calculated based on a given answer being better than the average answer to the query. In this formulation, no value function is required.
Can we adapt GRPO towards robot learning? Value Functions are known to cause issues in training stability [3] and a result in biased advantage estimates [4]. We are in the age of GPU-accelerated RL [5], training policies by simulating thousands of robot instances simultaneously. This makes a new monte-carlo (MC) approach towards RL timely, feasible and appealing. In this project, the student will be tasked to investigate the limitations of value-function based advantage estimation. Using GRPO as a starting point, the student will then develop MC-based algorithms that use the GPU’s parallel simulation capabilities for stable RL training for unbiased variance reduction while maintaining a competitive wall-clock time.
- Intelligent Robotics, Knowledge Representation and Machine Learning, Robotics and Mechatronics
- Bachelor Thesis, Master Thesis, Semester Project
| Safety is a fundamental requirement for critical systems such as power converter protection, robotics, and autonomous vehicles. Ensuring long-term safety in these systems requires both characterizing safe behaviour and designing feedback controllers that enforce safety constraints. Control Barrier Functions (CBFs) have recently emerged as a powerful tool for addressing these challenges by defining safe regions in the state space and formulating control strategies that maintain safety. When the dynamical system is precisely modeled, a CBF can be designed by solving a convex optimization problem, where the state-space model is incorporated into the constraints.
However, designing valid CBFs remains difficult when system models are uncertain or time-varying. More importantly, CBFs and control laws derived from inaccurate models may lead to unsafe behaviour in real-world systems. To overcome these difficulties, this project aims to develop a data-driven approach for constructing CBFs without relying on explicit system models. Instead, we will leverage behavioural systems theory to replace model information in the design program by persistently exciting data. The proposed method will be applied to output current protection in power converters or robotics collision avoidance. - Engineering and Technology
- Master Thesis, Semester Project
|
|
