ニューラルプロセスにおける時間表現の探求：マルチモーダル行動予測への応用
Exploring Temporal Representation in Neural Processes for Multimodal Action Prediction
ロボットの自己行動予測タスクにおいて、条件付きニューラルプロセスを用いた既存モデルの時間表現の限界を特定し、位置エンコーディングを導入した改良版DMBN-PTEを提案した。
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: Marco Gabriele Fedozzi, Yukie Nagai, Francesco Rea, Alessandra Sciutti
分類: cs.RO, cs.AI
原文アブストラクト
Inspired by the human ability to understand and predict others, we study the applicability of Conditional Neural Processes (CNP) to the task of self-supervised multimodal action prediction in robotics. Following recent results regarding the ontogeny of the Mirror Neuron System (MNS), we focus on the preliminary objective of self-actions prediction. We find a good MNS-inspired model in the existing Deep Modality Blending Network (DMBN), able to reconstruct the visuo-motor sensory signal during a partially observed action sequence by leveraging the probabilistic generation of CNP. After a qualitative and quantitative evaluation, we highlight its difficulties in generalizing to unseen action sequences, and identify the cause in its inner representation of time. Therefore, we propose a revised version, termed DMBN-Positional Time Encoding (DMBN-PTE), that facilitates learning a more robust representation of temporal information, and provide preliminary results of its effectiveness in expanding the applicability of the architecture. DMBN-PTE figures as a first step in the development of robotic systems that autonomously learn to forecast actions on longer time scales refining their predictions with incoming observations.
