成功軌道を保持しながら学習済み制御器を逐次改善する手法
Sequential Recovery Updates for Learned Controllers under Successful-Trajectory Preservation
学習済み制御器に失敗時の回復スキルを追加する際、既存の成功軌道を壊さないよう入口規則を制約し、その保証のコストを定量化した研究。
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: Zongtan Li, Tianming Liu, Ye Zhao
分類: cs.RO, cs.AI
原文アブストラクト
A competent learned controller already recovers from many disturbances. Improving it means learning a correction, and learning when not to apply it. Freezing a skill's parameters does not settle the second half. In a controller that routes among frozen skills, a new entry rule can redirect the states an old skill succeeded on. We therefore constrain entry instead of parameters. Each update searches for a feedback skill at a measured failure. It fits an entry rule that reads observations and rejects every state on an accumulated successful trajectory. The skill is admitted only if the composed controller reproduces the new recovery on its own and replays every protected trajectory exactly. A finite-trajectory condition states when this preserves the previous controller. One mechanism runs on four streams: two motions on each of two humanoid systems. Two updates per stream add 62 recoveries over 192 withheld perturbations, and lose none of the base controller's successes. We then price that guarantee. Removing the constraint recovers 33 more conditions but stops eight protected ones from completing at all, and excluding only what admission proves necessary recovers none of that cost.
関連論文
- 幾何学的接触流:ダイナミクスと制御のための接触同相写像ロボティクス/制御