COMPASS: 自律システムのための対照マルチモーダル事前学習
COMPASS: Contrastive Multimodal Pretraining for Autonomous Systems
マルチモーダルな信号をグラフで結び、運動パターン空間と現在状態空間の2つの潜在空間に写像する汎用事前学習手法を提案し、ドローン航行・車両レース・視覚オドメトリで有効性と実環境への汎化を示した。
著者: Shuang Ma, Sai Vemprala, Wenshan Wang, Jayesh K. Gupta, Yale Song, Daniel McDuff, Ashish Kapoor
分類: cs.RO
原文アブストラクト
Learning representations that generalize across tasks and domains is challenging yet necessary for autonomous systems. Although task-driven approaches are appealing, designing models specific to each application can be difficult in the face of limited data, especially when dealing with highly variable multimodal input spaces arising from different tasks in different environments.We introduce the first general-purpose pretraining pipeline, COntrastive Multimodal Pretraining for AutonomouS Systems (COMPASS), to overcome the limitations of task-specific models and existing pretraining approaches. COMPASS constructs a multimodal graph by considering the essential information for autonomous systems and the properties of different modalities. Through this graph, multimodal signals are connected and mapped into two factorized spatio-temporal latent spaces: a "motion pattern space" and a "current state space." By learning from multimodal correspondences in each latent space, COMPASS creates state representations that models necessary information such as temporal dynamics, geometry, and semantics. We pretrain COMPASS on a large-scale multimodal simulation dataset TartanAir \cite{tartanair2020iros} and evaluate it on drone navigation, vehicle racing, and visual odometry tasks. The experiments indicate that COMPASS can tackle all three scenarios and can also generalize to unseen environments and real-world data.
関連論文
- 空間知能の構築:自律システムのためのマルチモーダル事前学習ロードマップマルチモーダル事前学習
