Paper Info
Title
COMPASS: Contrastive Multimodal Pretraining for Autonomous Systems.
Abstract
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.
Year
DOI
Venue
2022
10.1109/IROS47612.2022.9982241
IEEE/RJS International Conference on Intelligent RObots and Systems (IROS)
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
0
7
Name
Order
Citations
PageRank
Shuang Ma1487.97
Sai Vemprala213.73
Wenshan Wang3249.00
Jayesh K. Gupta4889.68
Yale Song531217.89
Daniel McDuff600.34
Ashish Kapoor71833119.72