Yuanfei Lin

Hello! I am currently working toward the Ph.D. degree in the Cyber Physical Systems group, School of Computation, Information and Technology , Technical University of Munich. Prior to that, I graduated with the double Master degree in Mechanical Engineering and Mechatronics and Robotics both with high distinction from the same university in 2020. I received the Bachelor degree in Automotive Engineering with Excellent Graduate honor from Tongji University in 2018.

Email  /  TUM Page  /  CV  /  Google Scholar  /  LinkedIn  /  Github

profile photo
Research Interests

I'm broadly interested in applying formal methods and machine learning technologies to motion planning algorithms for autonomous vehicles to increase their safety, liability, and efficiency.

Simplifying Sim-to-Real Transfer in Autonomous Driving: Coupling Autoware with the CommonRoad Motion Planning Framework
Gerald Würsching, Tobias Mascetta, Yuanfei Lin, Matthias Althoff.
IV, 2024
BibTex / VollText / Video

The first publicly available interface between CommonRoad and Autoware.

DrPlanner 🩺: Diagnosis and Repair of Motion Planners Using Large Language Models
Yuanfei Lin, Chenran Li, Mingyu Ding, Masayoshi Tomizuka, Wei Zhan, Matthias Althoff.
ArXiv, 2024
Project Page / VollText / Video

Leveraging the profound capabilities of large language models in addressing reasoning challenges, we returns repaired planners with detailed diagnostic descriptions.

Model Predictive Robustness of Signal Temporal Logic Predicates
Yuanfei Lin*, Haoxuan Li*, Matthias Althoff.
RA-L, 2023
BibTex / VollText / Video

A novel approach to determine the robustness of signal temporal logic predicates, where the model capability for rule compliance is explicitly considered.

Automatic Traffic Scenario Conversion from OpenSCENARIO to CommonRoad
Yuanfei Lin, Michael Ratzel, Matthias Althoff.
ITSC, 2023
BibTex / VollText / Poster / Presentation / Tool Page

The first openly accessible converter from OpenSCENARIO to CommonRoad.

CommonRoad-CriMe: A Toolbox for Criticality Measures of Autonomous Vehicles
Yuanfei Lin, Matthias Althoff.
IV, 2023
BibTex / VollText / Poster / Tool Page

An open-source toolbox for measuring the criticality of autonomous vehicles in a unified framework.

Rule-Compliant Trajectory Repairing using Satisfiability Modulo Theories
Yuanfei Lin, Matthias Althoff.
IV, 2022
BibTex / VollText / Video / Poster

The first work to repair trajectories violating traffic rules formalized in temporal logic.

Sampling-Based Trajectory Repairing for Autonomous Vehicles
Yuanfei Lin, Sebastian Maierhofer, Matthias Althoff.
ITSC, 2021
BibTex / VollText / Video

As replanning would be computationally expensive, we present a novel approach for repairing invalid trajectorie.

Invited Talk
iv Reliable-by-Repair: Trajectory Repairing for Autonomous Vehicles with Rule Compliance

Social, interactive and safe behaviors for AVs: benchmarks, models and applications
IEEE IV 2023 Workshops, Anchorage, AK, United States

tum Trajectory Repairing for Autonomous Vehicles: Collision Avoidance and Rule Compliance

School of Cyber Science and Engineering, Southeast University, China (online)

Teaching
tum 2022-2023: Techniques in Artificial Intelligence
2021-now: Motion Planning for Autonomous Vehicles
2021-now: Seminar of Cyber-Physical Systems
2020: Advanced Control 1

Teaching Assistant, Technical University of Munich, Germany

Education
tum

Aug. 2023 - Feb. 2024, Mechanical Systems Control Lab, University of California, Berkeley, USA

Visiting Scholar

tum

Since May. 2021, Department of Informatics, Technical University of Munich, Germany

Ph.D. in Informatics

tum

Sept. 2018 - Dec. 2020, Department of Mechanical Engineering, Technical University of Munich, Germany

M. Sc. w/ high distinction in Mechanical Engineering and Mechatronics and Robotics

tongji

Sept. 2013 - Jul. 2018, School of Automotive Studies, Tongji University, China

B. Eng. in Automotive Engineering


   Updated March 2024

Source