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

Recent advances in deep reinforcement learning and scalable photorealisticsimulation have led to increasingly mature embodied AI for various visualtasks, including navigation. However, while impressive progress has been madefor teaching embodied agents to navigate static environments, much lessprogress has been made on more dynamic environments that may include movingpedestrians or movable obstacles. In this study, we aim to benchmark differentaugmentation techniques for improving the agent's performance in thesechallenging environments. We show that adding several dynamic obstacles intothe scene during training confers significant improvements in test-timegeneralization, achieving much higher success rates than baseline agents. Wefind that this approach can also be combined with image augmentation methods toachieve even higher success rates. Additionally, we show that this approach isalso more robust to sim-to-sim transfer than image augmentation methods.Finally, we demonstrate the effectiveness of this dynamic obstacle augmentationapproach by using it to train an agent for the 2021 iGibson Challenge at CVPR,where it achieved 1st place for Interactive Navigation. Video link:https://www.youtube.com/watch?v=HxUX2HeOSE4

Benchmarking Augmentation Methods for Learning Robust Navigation Agents: the Winning Entry of the 2021 iGibson Challenge