Robotic Systems Lab

Open Opportunities

Design of a Compliant Mechanism for Human-Robot Collaborative Transportation with Non-Holonomic Robots ETH Zurich Robotic Systems Lab Human-robot collaboration is an attractive option in many industries for transporting long and heavy items with a single operator. In this project, we aim to enable HRC transportation with a non-holonomic robotic base platform by designing a compliant manipulation mechanism, inspired by systems like the Omnid Mocobots. Intelligent Robotics, Mechanical Engineering ETH Zurich (ETHZ), Master Thesis

Boosting Reinforcement Learning with High-Speed Gaussian Splatting ETH Zurich Robotic Systems Lab 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

BEV meets Semantic traversability ETH Zurich Robotic Systems Lab Enable Birds-Eye-View perception on autonomous mobile robots for human-like navigation. Computer Vision, Intelligent Robotics, Neural Networks, Genetic Alogrithms and Fuzzy Logic, Pattern Recognition, Photogrammetry and Remote Sensing ETH Zurich (ETHZ), Master Thesis

Scene graphs for robot navigation and reasoning ETH Zurich Robotic Systems Lab Elevate semantic scene graphs to a new level and perform semantically-guided navigation and interaction with real robots at The AI Institute. Computer Vision, Engineering and Technology, Intelligent Robotics, Neural Networks, Genetic Alogrithms and Fuzzy Logic, Pattern Recognition ETH Zurich (ETHZ), Master Thesis

Digital Twin for Spot's Home ETH Zurich Computer Vision and Geometry Group Other organizations: Research Zeilinger, Robotic Systems Lab MOTIVATION ⇾ Creating a digital twin of the robot's environment is crucial for several reasons: 1. Simulate Different Robots: Test various robots in a virtual environment, saving time and resources. 2. Accurate Evaluation: Precisely assess robot interactions and performance. 3. Enhanced Flexibility: Easily modify scenarios to develop robust systems. 4. Cost Efficiency: Reduce costs by identifying issues in virtual simulations. 5. Scalability: Replicate multiple environments for comprehensive testing. PROPOSAL We propose to create a digital twin of our Semantic environment, designed in your preferred graphics Platform to be able to simulate Reinforcement Learning agents in the digital environment, to create a unified evaluation platform for robotic tasks. Artificial Intelligence and Signal and Image Processing Master Thesis, Semester Project

KALLAX Benchmark: Evaluating Household Tasks ETH Zurich Computer Vision and Geometry Group Other organizations: Robotic Systems Lab Motivation ⇾ There are three ways to evaluate robots for pick-and-place tasks at home: 1. Simulation setups: High reproducibility but hard to simulate real-world complexities and perception noise. 2. Competitions: Good for comparing overall systems but require significant effort and can't be done frequently. 3. Custom lab setups: Common but lead to overfitting and lack comparability between labs. Proposal ⇾ We propose using IKEA furniture to create standardized, randomized setups that researchers can easily replicate. E.g, a 4x4 KALLAX unit with varying door knobs and drawer positions, generating tasks like "move the cup from the upper right shelf into the black drawer." This prevents overfitting and allows for consistent evaluation across different labs. Artificial Intelligence and Signal and Image Processing Master Thesis, Semester Project

Evolve to Grasp: Learning Optimal Finger Configuration for a Dexterous Multifingered Hand ETH Zurich Robotic Systems Lab Use evolutionary algorithms with analytical force closure metrics to learn the optimal morphology of a dexterous hand. Intelligent Robotics Master Thesis, Semester Project

Learn to Reach: Collision Aware End-Effector Path Planning & Tracking using Reinforcement Learning ETH Zurich Robotic Systems Lab Other organizations: ETH Competence Center - ETH AI Center 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

Visual Language Models for Long-Term Planning in Construction ETH Zurich Robotic Systems Lab 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

LLM-Driven Skill Acquisition for the ANYmal robot ETH Zurich Robotic Systems Lab 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