Sim2Val: テストプラットフォーム間の相関を活用した分散低減メトリクス推定
Sim2Val: Leveraging Correlation Across Test Platforms for Variance-Reduced Metric Estimation
シミュレーションと実世界のペアデータを制御変数として用い、実世界評価の分散を抑えて少ないサンプルで高信頼な性能推定を可能にする枠組みを提案。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Rachel Luo, Heng Yang, Michael Watson, Apoorva Sharma, Sushant Veer, Edward Schmerling, Marco Pavone
分類: cs.RO
原文アブストラクト
Learning-based robotic systems demand rigorous validation to assure reliable performance, but extensive real-world testing is often prohibitively expensive, and if conducted may still yield insufficient data for high-confidence guarantees. In this work we introduce Sim2Val, a general estimation framework that leverages paired data across test platforms, e.g., paired simulation and real-world observations, to achieve better estimates of real-world metrics via the method of control variates. By incorporating cheap and abundant auxiliary measurements (for example, simulator outputs) as control variates for costly real-world samples, our method provably reduces the variance of Monte Carlo estimates and thus requires significantly fewer real-world samples to attain a specified confidence bound on the mean performance. We provide theoretical analysis characterizing the variance and sample-efficiency improvement, and demonstrate empirically in autonomous driving and quadruped robotics settings that our approach achieves high-probability bounds with markedly improved sample efficiency. Our technique can lower the real-world testing burden for validating the performance of the stack, thereby enabling more efficient and cost-effective experimental evaluation of robotic systems.
