Papers
1
Total Citations
32
H-Index
1
About
Yangge Li is a researcher at the forefront of safety-critical autonomous systems, specializing in the formal verification of controllers that integrate vision-based perception. His most-cited work, "Verifying Controllers With Vision-Based Perception Using Safe Approximate Abstractions," introduces a practical method for reasoning about the safety of systems where fully formal verification of perception models remains intractable. By systematically constructing safe approximate abstractions, Li enables rigorous safety guarantees for control systems reliant on neural perception—a critical step toward trustworthy autonomous driving and robotics. With 32 citations since 2022, this paper has quickly become a foundational reference for researchers bridging the gap between formal methods and real-world perception. Li’s contributions address a pressing challenge: ensuring that imperfect, learned perception modules do not compromise overall system safety. His work is notable for its pragmatic approach, offering engineers a viable path to verification without requiring perfect models. For students and researchers, Li’s research exemplifies how to tackle the tension between theoretical rigor and practical deployment in AI-driven control systems.
Research Focus
Key Achievements
Top Papers
- 1