Pascal Roth

Pascal Roth

Ph.D. in Robot Learning

ETH Zurich

Biography

I am currently a doctoral student under the supervision of Prof. Marco Hutter at the Robotic Systems Lab in Zurich. Before I completed my Master Studies in Mechanical Engineering at ETH Zurich and my Bachelor Studies at TU Darmstadt.

During my master’s studies, I specialized in Robotics, Control, and Artificial Intelligence. I completed a range of relevant courses, including Advanced Machine Learning, Vision Algorithms for Mobile Robotics, and Deep Learning for Autonomous Driving. Additionally, I undertook projects such as building a Visual Inertial Odometry Pipeline, performing Path Planning in Dynamic Environment, and doing Multi-Task Learning for Depth and Semantics Estimation. These experiences culminated in a semester project on Self-Supervised Panoptic Segmentation for Improved Scene Understanding and a Master’s Thesis enhancing robotic navigation through the integration of geometric and semantic information.

Interests
  • Robtic Autonomy
  • Computer Vision
  • Reinforcement and Deep Learning
Education
  • PhD in Robot Learning

    ETH Zurich

  • MSc in Mechanical Engineering, 2023

    ETH Zurich

  • BSc in Mechanical Engineering, 2020

    TU Darmstadt

Recent Publications

(0001). ViPlanner: Visual Semantic Imperative Learning for Local Navigation. ICRA.

PDF Cite Code Project Video

Projects

*
ViPlanner - Visual Semantic Imperative Learning for Local Navigation
Local Path Planning with semantic and geometric understanding of the environment.
ViPlanner - Visual Semantic Imperative Learning for Local Navigation
Visual Odometry
Monocular continuous Visual Odometry (VO) pipeline designed for the purpose of vehicle localization
Visual Odometry
Orbit
A Unified Simulation Framework for Interactive Robot Learning Environments
Orbit
ETH Robotics Summer School
Search and Rescue Challenge
ETH Robotics Summer School
Self-Supervised Panoptic Segmentation
Self-supervised pre-training strategies for environment-specific segmentation models
Self-Supervised Panoptic Segmentation
Motion Planning
Using RRT* with motion primitives to guide a starship through a map with static and dynamic obstacles.
Motion Planning

Education

 
 
 
 
 
Robotic Systems Lab
Ph.D. Student
February 2024 – Present Zurich
Robot Learning and Navigation under the supervision of Prof. Marco Hutter
 
 
 
 
 
Robotic Systems Lab
MSc in Mechanical Engineering
August 2023 – January 2024 Zurich
Focus on Robotics, Control and Artificial Intelligence
 
 
 
 
 
Robotic Systems Lab
Student Exchange
September 2019 – January 2020 Zurich
Exchange Semester with focus on Machine Learning and Robotics
 
 
 
 
 
TU Darmstadt
BSc in Mechanical Enginnering
October 2017 – December 2020 Darmstadt, Germany

Experience

 
 
 
 
 
Robotic Systems Lab
Research Engineer
August 2023 – January 2024 Zurich
Research on Robotic Navigation and development of the ORBIT Framework
 
 
 
 
 
ETH Zurich
Robotics Summer School
August 2023 – January 2024 Zurich
Research on Robotic Navigation and development of the ORBIT Framework
 
 
 
 
 
Ansys Inc.
Research Intership
August 2023 – January 2024 Zurich
Research on Robotic Navigation and development of the ORBIT Framework

Contact