A Practical Recipe Towards Improving Sim-and-Real Correlation for VLA Evaluation
Researchers have developed a systematic study to improve the correlation between simulation and real-world robot evaluations for vision-language-action (VLA) policies. The study analyzes how well simulation platforms preserve real-world conclusions regarding policy ranking and performance. It also offers guidance on leveraging simulation for policy improvement, including when simulator-based fine-tuning is beneficial and how data volume impacts alignment. AI
IMPACT Provides a framework to enhance the reliability of simulation for developing and evaluating AI-driven robot policies.