Private Multiparty Perception for NavigationDownload PDF

Published: 31 Oct 2022, Last Modified: 03 Jul 2024NeurIPS 2022 AcceptReaders: Everyone
Keywords: Visual Navigation, Privacy, Multi-party Computation
Abstract: We introduce a framework for navigating through cluttered environments by connecting multiple cameras together while simultanously preserving privacy. Occlusions and obstacles in large environments are often challenging situations for navigation agents because the environment is not fully observable from a single camera view. Given multiple camera views of an environment, our approach learns to produce a multiview scene representation that can only be used for navigation, provably preventing one party from inferring anything beyond the output task. On a new navigation dataset that we will publicly release, experiments show that private multiparty representations allow navigation through complex scenes and around obstacles while jointly preserving privacy. Our approach scales to an arbitrary number of camera viewpoints. We believe developing visual representations that preserve privacy is increasingly important for many applications such as navigation.
TL;DR: We introduce a framework for navigating through cluttered environments by connecting multiple cameras together while simultaneously preserving privacy via multi-party computation.
Supplementary Material: pdf
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/private-multiparty-perception-for-navigation/code)
9 Replies

Loading