Safety
LyEvO: Lyapunov-Guided Evolutionary Optimization for Safe and Robust Sim-to-Real Policy Learning
arXiv:2608.06481v1 Announce Type: cross Abstract: Training controllers that are safe and robust in simulation, and systematically assessing their readiness for real-world deployment, remain key challe
arXiv:2608.06481v1 Announce Type: cross Abstract: Training controllers that are safe and robust in simulation, and systematically assessing their readiness for real-world deployment, remain key challenges in sim-to-real transfer. To address this, we propose LyEvO, a physics-grounded framework that combines constrained Evolutionary Optimization and Statistical Model Checking (SMC)-based verification with Lyapunov-based stability analysis. Leveraging prior knowledge of the system dynamics, LyEvO uses Lyapunov analysis to compute an initial candidate stability region. An iterative loop then uses operational scenarios drawn from this region to jointly optimize and statistically verify a policy, and subsequently expands the region's boundaries based on the verification outcome. This integrated procedure provides a practical criterion for assessing deployment readiness. We evaluate LyEvO on Cartpole and 3D Quadrotor benchmarks through extensive simulations and targeted real-world experiments, demonstrating safe and robust sim-to-real transfer.
Related
- ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors
- Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving
- From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model
- Scenario Generation for Risk-Aware Reinforcement Learning with Probably Approximately Safe Guarantees
Source: arXiv cs.AI | 2026-08-10