AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

NeoNav: Improving the Generalization of Visual Navigation via Generating Next Expected Observations

Qiaoyun Wu, Dinesh Manocha, Jun Wang, Kai Xu

AAAI 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Disentangled and discrete latent models · 18 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use four-view instead of front-view only input (ablation)NeoNav · AVD novel scenes, without stop actionsuccess rate (%): 37.1 -> 47.7Improved
generate next expected observation via variational sampling (vs non-generative) (ablation)NeoNav · AVD novel scenes, without stop actionsuccess rate (%): 34.8 -> 47.7Improved
use mixture-of-posteriors prior instead of standard normal (ablation)NeoNav · AVD novel scenes, without stop actionsuccess rate (%): 40.3 -> 47.7Improved
use depth input instead of RGB (ablation)NeoNav · AVD novel scenes, without stop actionsuccess rate (%): 37.1 -> 47.7Improved
use depth input instead of RGBD (ablation)NeoNav · AVD novel scenes, without stop actionsuccess rate (%): 42.2 -> 47.7Improved
NeoNav vs best baseline with stop actionNeoNav · AVD novel scenes, with stop actionsuccess rate (%): 14.2 -> 19.9Improved
NeoNav vs best baseline in AI2-THORNeoNav · AI2-THOR novel scenes, with stop actionsuccess rate (%): 11.7 -> 16.7Improved
NeoNav vs TD-A3C in bathroom scenesNeoNav · AI2-THOR bathroomssuccess rate (%): 24.3 -> 21.9Hurt
fewer training scenes (8 to 2) with NeoNavNeoNav · AVD without stop actionsuccess rate (%): 47.9 -> 35.1Hurt
NeoNav vs TD-Semantic with depth input in semantic-driven navigationNeoNav · AVD semantic-driven navigationsuccess rate (%): 53.6 -> 66.3Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy