English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Developing embodied agents in simulation has been a key research topic inrecent years. Exciting new tasks, algorithms, and benchmarks have beendeveloped in various simulators. However, most of them assume deaf agents insilent environments, while we humans perceive the world with multiple senses.We introduce Sonicverse, a multisensory simulation platform with integratedaudio-visual simulation for training household agents that can both see andhear. Sonicverse models realistic continuous audio rendering in 3D environmentsin real-time. Together with a new audio-visual VR interface that allows humansto interact with agents with audio, Sonicverse enables a series of embodied AItasks that need audio-visual perception. For semantic audio-visual navigationin particular, we also propose a new multi-task learning model that achievesstate-of-the-art performance. In addition, we demonstrate Sonicverse's realismvia sim-to-real transfer, which has not been achieved by other simulators: anagent trained in Sonicverse can successfully perform audio-visual navigation inreal-world environments. Sonicverse is available at:https://github.com/StanfordVL/Sonicverse.

Sonicverse: A Multisensory Simulation Platform for Embodied Household Agents that See and Hear