Siwei Ju
Research Interests
Reinforcement Learning, Imitation Learning, Autonomous Driving
Affiliation
TU Darmstadt, Intelligent Autonomous Systems, Computer Science Department
Contact
Siwei.ju@tu-darmstadt.de
Room E326, Building S2|02, TU Darmstadt, FB-Informatik, FG-IAS, Hochschulstr. 10, 64289 Darmstadt
Siwei Ju joined the Intelligent Autonomous Systems lab as an external Phd student in collaboration with Porsche Motorsports on October 1, 2021, as a Ph.D. student. Since December 1, 2024 she has also become internal Phd Student. She finishes her Master's study in RWTH Aachen university with a major in automation engineering.
Her research topics include reinforcement learning and imitation learning for race car driving and robots. For race car driving, she explores imitation learning and reinforcement learning to imitate and outperform top-class human race drivers in high-fidelity simulation environment.
She recently explores reinforcement learning and imitation learning for robots locomotion on quadruped and humanoid robots. She is also interested in ensuring safety of robot control using neural control barrier functions.
Recent Publications
- Loeckel, S.; Ju, S.; Schaller, M.; van Vliet, P.; Peters, J. (2023). An Adaptive Human Driver Model for Realistic Race Car Simulations, IEEE Transactions on Systems, Man and Cybernetics: Systems (TSMC), 53, 11, pp.6718-6730.
- Ju, S.; van Vliet, P.; Arenz, O.; Peters, J. (2023). Digital Twin of a Driver-in-the-Loop Race Car Simulation with Contextual Reinforcement Learning, IEEE Robotics and Automation Letters (RA-L), 8, 7, pp.4107-4114.
- Loeckel, S.; Ju, S.; Schaller, M.; van Vliet, P.; Peters, J. (2022). An Adaptive Human Driver Model for Realistic Race Car Simulations, arXiv.