ロボ触覚オリンピアード2.0:触覚ベース強化学習の標準化ベンチマーク
roto 2.0: The Robot Tactile Olympiad
触覚ベースの強化学習を標準化するため、4種類のロボット形態で「盲目的」操作を評価するGPU並列ベンチマークを提案し、既存手法より10倍高速な性能を達成した。
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: Elle Miller, Jayaram Reddy, Ayush Deshmukh, Trevor McInroe, David Abel, Oisin Mac Aodha, Sethu Vijayakumar
分類: cs.RO, cs.LG
原文アブストラクト
Tactile-based reinforcement learning (RL) is currently hindered by fragmented research and a focus on over-saturated orientation tasks. We introduce v2 of the Robot Tactile Olympiad (\texttt{roto 2.0}), a GPU-parallelised benchmark designed to standardise tactile-based RL across four distinct robotic morphologies (16-DOF to 24-DOF). Unlike prior benchmarks, roto focuses on end-to-end "blind" manipulation, utilising only proprioception and tactile sensing without state information or distillation. We demonstrate a significant performance leap, with our blind agents achieving 13 Baoding ball rotations in 10 seconds, an order of magnitude faster than current state-of-the-art speeds. By open-sourcing our environments and robustly tuned baselines, we reduce the barrier to entry and enable researchers to prioritise fundamental algorithmic challenges over tedious RL tuning. Website: https://elle-miller.github.io/roto/
