-
EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving
Paper • 2604.22851 • Published • 2 -
Target-Bench: Can World Models Achieve Mapless Path Planning with Semantic Targets?
Paper • 2511.17792 • Published • 6 -
Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving
Paper • 2607.14387 • Published • 7 -
Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis
Paper • 2506.11526 • Published • 2
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving
Validate the Dream Before You Trust Its Verdict: Admissibility for World-Model Simulators
Organization Card
Autonomous Vehicle Systems Lab @ TUM
Technical University of Munich · School of Engineering and Design Prof. Dr.-Ing. Johannes Betz
We build the software and learning stack for autonomous vehicles — from motion planning and control on real platforms (EDGAR, autonomous racing) to foundation models that reason about driving scenes and vehicle dynamics.
🌐 Lab website · 💻 github.com/TUM-AVS · 🎓 LinkedIn
*Open to collaboration and thesis projects — see the lab site. *
-
EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving
Paper • 2604.22851 • Published • 2 -
Target-Bench: Can World Models Achieve Mapless Path Planning with Semantic Targets?
Paper • 2511.17792 • Published • 6 -
Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving
Paper • 2607.14387 • Published • 7 -
Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis
Paper • 2506.11526 • Published • 2