AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Occupancy Anticipation for Efficient Exploration and Navigation

Santhosh K. Ramakrishnan, Ziad Al-Halah, Kristen Grauman

ECCV 2020 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Vision-language navigation agents · 158 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
add occupancy anticipation (OccAnt) to depth mapperANS(depth) · Gibson val per-framemean IoU %: 19.3 -> 56.1Improved
add occupancy anticipation (OccAnt) to rgb mapperANS(rgb) · Gibson val per-framemean IoU %: 13.5 -> 46.1Improved
add RGB to depth input (rgbd instead of depth)OccAnt · Gibson val per-framemean IoU %: 56.1 -> 56.5No clear effect
add anticipation reward (ablation)OccAnt(rgbd) · Gibson small, noisy explorationmap accuracy (m^2): 16.9 -> 22.7Improved
add anticipation reward (ablation)OccAnt(depth) · Gibson large, noisy explorationmap accuracy (m^2): 44.2 -> 50.3Improved
add anticipation reward (ablation)OccAnt(rgbd) · Matterport3D, noisy explorationmap accuracy (m^2): 76.3 -> 99.9Improved
add anticipation reward (ablation)OccAnt(rgb) · Gibson large, noisy explorationmap accuracy (m^2): 44.2 -> 42.1Hurt
add anticipation reward (ablation)OccAnt(depth) · Matterport3D, noise-free explorationmap accuracy (m^2): 104.7 -> 96.5Hurt
add anticipation reward (ablation)OccAnt(depth) · Gibson val PointNavSPL %: 78.6 -> 77.8No clear effect
add anticipation reward (ablation)OccAnt(rgbd) · Gibson val PointNavSPL %: 77.9 -> 80.0Improved
add occupancy anticipation to rgb mapperANS(rgb) · Gibson val PointNavSPL %: 66.8 -> 71.2Improved
add occupancy anticipation to depth mapperANS(depth) · Matterport3D, noisy explorationmap accuracy (m^2): 72.5 -> 94.1Improved

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