 Robotic Systems LabOpen OpportunitiesUse evolutionary algorithms with analytical force closure metrics to learn the optimal morphology of a dexterous hand. - Intelligent Robotics
- Master Thesis, Semester Project
| Develop a method for collision aware reaching tasks using reinforcement learning and shape encodings of the environment - Intelligent Robotics
- ETH Zurich (ETHZ), Master Thesis, Semester Project
| This project uses Visual Language Models (VLMs) for high-level planning and supervision in construction tasks, enabling task prioritization, dynamic adaptation, and multi-robot collaboration for excavation and site management.
prioritization, dynamic adaptation, and multi-robot collaboration for excavation and site management - Information, Computing and Communication Sciences
- Master Thesis, Semester Project
| This project addresses the computational bottlenecks in model-free reinforcement learning (RL) with high-dimensional image inputs by optimizing Gaussian Splatting—a GPU-accelerated technique for photorealistic image generation from point clouds—for RL applications. By integrating pre-sorting methods, the project aims to enhance rendering speeds, enabling broader RL applications beyond geometric constraints or abstraction layers. Building on previous work involving risk annotations in Gaussian splats, the project seeks to develop generalizable RL policies that leverage real-world knowledge. - Intelligent Robotics
- Master Thesis, Semester Project
|
This project aims to enhance RL-based planners by addressing their limited memory and short goal-reaching range (15–20m). Inspired by human navigation aided by positional memory, it proposes constructing a graph of past positions and providing it as input to the RL policy, enabling better memory utilization and extended goal distances. By leveraging RL's exploratory behavior, the approach seeks to resolve local minima and achieve human-like goal-reaching capabilities. Current advancements include a tenfold reduction in memory footprint and faster inference for far-away goals. The project will further integrate geometric and semantic environmental data to improve understanding and real-world applicability. - Intelligent Robotics
- Master Thesis, Semester Project
| Robots have become increasingly advanced recently, capable of performing challenging tasks such as taking elevators and cooking shrimp. Moreover, their ability to accomplish long-horizon tasks given simple natural language instructions is also made possible by large language models. However, with this increased functionality comes the risk that intelligent robots might unintentionally or intentionally harm people based on instructions from an operator. On the other hand, significant efforts have been made to restrain large language models from generating harmful content. Can these efforts be applied to robotics to ensure safe interactions between robots and humans, even as robots become more capable? This project aims to answer this question.
- Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis, Semester Project
| The goal of this project is to apply LLMs to teach the ANYmal robot new low-level skills via Reinforcement Learning (RL) that the task planner identifies to be missing. - Intelligent Robotics
- Master Thesis
| Robots may not be able to complete tasks fully autonomously in unstructured or unseen environments, however direct teleoperation from human operators may also be challenging due to the difficulty of providing full situational awareness to the operator as well as degradation in communication leading to the loss of control authority. This motivates the use of shared autonomy for assisting the operator thereby enhancing the performance during the task.
In this project, we aim to develop a shared autonomy framework for teleoperation of manipulator arms, to assist non-expert users or in the presence of degraded communication. Imitation learning, such as diffusion models, have emerged as a popular and scalable approach for learning manipulation tasks [1, 2]. Additionally, recent works have combined this with partial diffusion to enable shared autonomy [3]. However, the tasks were restricted to simple 2D domains. In this project, we wish to extend previous work in the lab using diffusion-based imitation learning, to enable shared autonomy for non-expert users to complete unseen tasks or in degraded communication environments.
- Intelligent Robotics, Robotics and Mechatronics
- ETH Zurich (ETHZ), Semester Project
| The GELLO system proposed in [1] is a low-cost “puppet” robot arm that is used to teleoperate a larger, main robot arm. This project aims to adapt this open source design to enable teleoperation of the DynaArm, which is a robot manipulator arm custom designed by the Robotic Systems Lab to be mounted on the ANYmal quadruped platform. Such a system provides a simplification over the existing DynaArm teleoperation interface consisting of a second identical DynaArm used purely as a human interface device [2], which may be an unnecessarily expensive and cumbersome solution. The system developed may have applications in remote teleoperation for industrial inspection or disaster response scenarios, as well as providing an interface for training imitation learning models, which may optionally be explored as time permits.
[1] Wu, Philip et al. "GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators". arXiv preprint (2024)
[2] Fuchioka, Yuni et al. AIRA Challenge: Teleoperated Mobile Manipulation for Industrial Inspection. Youtube Video. (2024) - Intelligent Robotics, Mechanical Engineering, Robotics and Mechatronics, Simulation and Modelling
- Bachelor Thesis, Master Thesis, Semester Project
| This project addresses sampling inefficiency in classical reinforcement learning by exploring smart weight initialization. Inspired by computer vision, we aim to enhance learning across different hardware (cross embodiment) and skills (cross skills) using pre-trained representations, reducing training times and potentially improving the overall effectiveness of reinforcement learning policies. - Engineering and Technology, Intelligent Robotics
- Master Thesis
|
|
