5 citations · 9 across the 5 of their papers we have counts for
6 papers
LLM-Powered Automatic Theorem Proving and Synthesis for Hybrid Systems and Games
Aditi Kabra, Jonathan Laurent, Ruben Martins +2
Hybrid games model cyber-physical systems (CPS), like cars, trains, and airplanes, where discrete control decisions interact with continuous physical dynamics. We use Large Languag…
Can Large Language Models Autoformalize Kinematics?
Aditi Kabra, Jonathan Laurent, Sagar Bharadwaj +3
Autonomous cyber-physical systems like robots and self-driving cars could greatly benefit from using formal methods to reason reliably about their control decisions. However, befor…
Hybrid Game Control Envelope Synthesis
Aditi Kabra, Jonathan Laurent, Stefan Mitsch +1
Control problems for embedded systems like cars and trains can be modeled by two-player hybrid games. Control envelopes, which are families of safe control solutions, correspond to…
Adaptive Shielding via Parametric Safety Proofs
Yao Feng, Jun Zhu, André Platzer +1
A major challenge to deploying cyber-physical systems with learning-enabled controllers is to ensure their safety, especially in the face of changing environments that necessitate…
Oracular Programming: A Modular Foundation for Building LLM-Enabled Software
Jonathan Laurent, André Platzer
Large Language Models (LLMs) can solve previously intractable tasks given only natural-language instructions and a few examples, but they remain difficult to steer precisely and la…
CESAR: Control Envelope Synthesis via Angelic Refinements
Aditi Kabra, Jonathan Laurent, Stefan Mitsch +1
This paper presents an approach for synthesizing provably correct control envelopes for hybrid systems. Control envelopes characterize families of safe controllers and are used to…