運動ニューロンに着想を得たサンプリングによるモデル予測パス積分制御
Motoneuron-Inspired Sampling for Model Predictive Path Integral Control
運動ニューロンの動態を模した時間的に構造化されたサンプリング手法をMPPI制御に導入し、MuJoCoのアリモデルで標準的なガウスサンプリングと比較して制御の滑らかさが向上することを示した。
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: Alexis Poignant, Jan Babič
分類: cs.RO
原文アブストラクト
Model Predictive Path Integral (MPPI) control relies on stochastic trajectory sampling, and its performance under limited rollout budgets depends strongly on the structure of the proposal distribution. Standard implementations commonly perturb control sequences with Gaussian noise, despite growing evidence that temporally correlated and structured sampling can improve finite-budget control. We introduce Spike-MPPI, a motoneuron-inspired proposal that generates temporally structured perturbations through a simplified model of motoneuron dynamics. The proposal is evaluated within a common MPPI framework on torque-actuated and antagonistically actuated MuJoCo Ant models against standard Gaussian sampling and spectrum-matched Gaussian controls. Results show that structured sampling substantially improves executed-control smoothness, while its effect on task performance depends on rollout condition and robot actuation. Spectrum matching reproduces a substantial part of the observed behavior, while the full Spike proposal retains additional effects beyond second-order spectral structure. These results support treating proposal design as a combination of second-order spectral structure and higher-order statistical organization.