ニューラル・タスク・プログラミング：階層的タスクへの汎化を学ぶ
Neural Task Programming: Learning to Generalize Across Hierarchical Tasks
タスクの映像デモを入力に、階層的にサブタスクへ再帰分解し、下位プログラムを呼び出すニューラルプログラムでロボット操作を学習する枠組みを提案。未見の長さ・構造・目的のタスクへ汎化できることを示した。
著者: Danfei Xu, Suraj Nair, Yuke Zhu, Julian Gao, Animesh Garg, Li Fei-Fei, Silvio Savarese
分類: cs.AI, cs.LG, cs.RO
原文アブストラクト
In this work, we propose a novel robot learning framework called Neural Task Programming (NTP), which bridges the idea of few-shot learning from demonstration and neural program induction. NTP takes as input a task specification (e.g., video demonstration of a task) and recursively decomposes it into finer sub-task specifications. These specifications are fed to a hierarchical neural program, where bottom-level programs are callable subroutines that interact with the environment. We validate our method in three robot manipulation tasks. NTP achieves strong generalization across sequential tasks that exhibit hierarchal and compositional structures. The experimental results show that NTP learns to generalize well to- wards unseen tasks with increasing lengths, variable topologies, and changing objectives.
