視覚的ゴール指向メタ学習のための文脈計画ネットワーク
Visual Goal-Directed Meta-Learning with Contextual Planning Networks
ゴール画像を条件として未知の操作タスクにゼロショットで適応する文脈計画ネットワーク(CPN)を提案し、Metaworldの24タスクと実機Jengaタスクで評価した。
著者: Corban G. Rivera, David A Handelman
分類: cs.RO, cs.AI
原文アブストラクト
The goal of meta-learning is to generalize to new tasks and goals as quickly as possible. Ideally, we would like approaches that generalize to new goals and tasks on the first attempt. Toward that end, we introduce contextual planning networks (CPN). Tasks are represented as goal images and used to condition the approach. We evaluate CPN along with several other approaches adapted for zero-shot goal-directed meta-learning. We evaluate these approaches across 24 distinct manipulation tasks using Metaworld benchmark tasks. We found that CPN outperformed several approaches and baselines on one task and was competitive with existing approaches on others. We demonstrate the approach on a physical platform on Jenga tasks using a Kinova Jaco robotic arm.
