Robotic Systems Lab

Open Opportunities

Urban Navigation for Wheeled-Legged Robots ETH Zurich Robotic Systems Lab Traditional legged robots are capable of traversing challenging terrain but lack energy efficiency and speed when compared to wheeled systems. We propose a novel optimization/learning framework that enables a legged robot equipped with powered wheels to perform hybrid locomotion. Electrical and Electronic Engineering, Information, Computing and Communication Sciences, Mechanical and Industrial Engineering Collaboration, ETH Organization's Labels (ETHZ), Internship, Lab Practice, Master Thesis, Semester Project

Enhancing Mobile Manipulation Capabilties of a Quadrupedal Robot with an Arm ETH Zurich Robotic Systems Lab We want to enhance the existing manipulation capabilities of ANYmal with arm. We are currently developing a shared autonomy framework, allowing the robot to perform various autonomous manipulation and cooperation tasks, while allowing an operator to intervene in case something unexpected happens. Engineering and Technology Master Thesis, Semester Project

Efficient Simulation of flexible Shanks for the ANYmal Robot ETH Zurich Robotic Systems Lab Flexible Materials have the Potential to highly increase the performance of walking robots, such as ANYmal. Unfortunately, using Reinforcement Learning on such Systems, an efficient and stable Simulation Environment for Robots is needed, which is currently not available. The goal is the implementation of a spatial model of a quadruped with flexible shanks as well as writing a simulation framework based on an already existing multi-body simulation for flexible bodies, which includes soft as well as rigid links. All the software will be written in Python. If the project is carried out successfully, the integration of the software stack into NVIDIA's Isaac Gym is possible in cooperation with NVIDIA. Engineering and Technology, Information, Computing and Communication Sciences Master Thesis

Physical HRI with a Tethered Quadruped ETH Zurich Autonomous Systems Lab Other organizations: Robotic Systems Lab This project aims to develop a system for guiding visually-impaired humans through physical interaction with a robot. Inspired by guide dogs, the human is physically connected to a quadruped robot (ANYmal) through a tether or rigid link. The robot is able to pull the human toward a desired position (or along a path) only using forces as an indirect communication-channel. Robotics and Mechatronics Master Thesis

Tree Manipulation with an Autonomous Harvester ETH Zurich Robotic Systems Lab We would like to develop an approach to solve the planning/control aspect of robotic tree manipulation, with the goal of using our autonomous tree harvester, Harveri, for robotic forestry missions. The project can be tailored to your needs/wishes. Intelligent Robotics Master Thesis, Semester Project

Learning Rapid Transporting of Objects without Spillage ETH Zurich Robotic Systems Lab Rapid object transportation is in increased demand for automated warehouses. However, high-speed motions are susceptible to unsafe behaviors. This project looks into learning a control policy for high-speed robotic manipulation. Control Engineering, Intelligent Robotics, Robotics and Mechatronics Master Thesis, Semester Project

Collision Avoidance Motion Planning for Robotic Manipulation ETH Zurich Robotic Systems Lab Obstacle avoidance is a fundamental problem in robotics and is particularly relevant for field robots operating in cluttered environments, e.g. forestry robots. In this project, we would like to develop a real-time feedback framework for this task in parts: perception and detection for obstacles with onboard sensing, and planning for robotic manipulator collision avoidance in cluttered environments Intelligent Robotics, Robotics and Mechatronics Master Thesis, Semester Project

Motion-Primitives Planning for Legged Robots ETH Zurich Robotic Systems Lab Autonomous navigation in complex environments is a fundamental problem in robotics and typically requires samples and search on continuous space for traversable paths. When navigating through areas without environmental priors, re-sampling or searching exclusively through updated traversable space is expensive with onboard sensing, limiting the execution of dynamic motions. In this project, we aim to explore methods to generate trajectories for legged robots toward highly efficient and reactive local planning in complex environments. Intelligent Robotics Semester Project

Augmented Reality for ANYmal ETH Zurich Robotic Systems Lab In this project, we would like to integrate our legged robot ANYmal into Augmented (Mixed-) Reality. AR has the opportunity to more easily communicate the sensor data, internal state, and intention of the robot. The build application should run on a tablet device (IOS or Android) which can be reliably used to visualize data, and control the robot with a superior user experience compared to a classical Joy Stick and external monitor. Ideally, the application can visualize raw sensor measurements, such as point clouds, camera images, the robot configuration, contact forces, velocities, and position but also more complex data such as traversability information, semantic understanding of the environment, and a fused map representation. While a lot of work was spent within the last years on generating this data properly little emphasis was devoted to visualizing this data nicely for a human. In addition, the tablet should allow to fully control the robot (given waypoints) in a more intuitive way. Engineering and Technology, Software Engineering, Virtual Reality and Related Simulation Master Thesis

Contrastive learning for navigation in the wild ETH Zurich Robotic Systems Lab Implementation of a contrastive learning navigation pipeline for ANYmal. Development of a novel algorithm for navigation based on expert demonstration and integration into the existing ANYmal software stack. Intelligent Robotics, Robotics and Mechatronics Master Thesis