触覚シミュレーションを使わない触覚Sim2Real:ボトルネック潜在再構成による実現
Tactile Sim2Real without Tactile Simulation via Bottlenecked Latent Reconstruction
触覚センサのシミュレーションを避け、シミュレータ内のオラクルセンサ(点群と指先力)で学習したポリシーを、実センサの潜在表現をオラクルに合わせることで実機に転移するフレームワークを提案。挿入や歯車噛み合わせで高成功率を達成。
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: Fan Yang, Youngsun Wi, Jinhao Yu, Nima Fazeli, Dmitry Berenson
分類: cs.RO
原文アブストラクト
Robot sensor designs, particularly tactile sensors, are highly diverse and evolve rapidly. Modeling each sensor in simulation demands substantial domain expertise and computational approximations can degrade the fidelity of the simulated signals. We propose Sim2Real via Bottlenecked Latent Reconstruction (SBLR), a framework that avoids sensor-specific simulation entirely by (1) training policies on a simulator-native oracle sensor that is easy to construct without modeling any particular sensor (e.g. we use a point-cloud and finger-tip forces as a tactile oracle), and (2) aligning real sensor latent embeddings to those of the oracle sensor at inference time. Policy training proceeds in two-stage: the policy first learns from the oracle sensor latents, then a bottlenecked latent reconstruction adapts it to the information loss expected when using the real sensor instead of the oracle. The alignment between oracle and real sensor is learned from unpaired random-play data collected in both simulation and the real world, using rectified-flow-based transformation networks trained on nearest-neighbor pseudo-pairs. Simulation experiments on three contact-rich tasks show that SBLR matches or approaches the performance of an oracle with direct access to tactile simulation. Hardware experiments on Peg Insertion and Gear Meshing with GelSight Mini and DIGIT sensors demonstrate 85-97.5% zero-shot success without requiring any sensor-specific modeling or calibration, outperforming a physics-based tactile simulation baseline by 7.5-15%.