AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Affordance-Guided Coarse-to-Fine Exploration for Base Placement in Open-Vocabulary Mobile Manipulation

Tzu-Jung Lin, Jia-Fong Yeh, Hung-Ting Su, Chung-Yi Lin, Yi-Ting Chen, Winston H. Hsu

AAAI 2026 · Vision-language and multimodal › Robot action and navigation · approach: Memory and subgoal-based manipulation · 2 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 coarse-to-fine schedule (alpha rising) instead of fixed alpha=0 (ablation)Affordance-Guided Coarse-to-Fine · OVMM 5 taskssuccess rate (%): 43 -> 85Improved
use rising alpha instead of fixed alpha=0.5 (ablation)Affordance-Guided Coarse-to-Fine · OVMM 5 taskssuccess rate (%): 76 -> 85Improved
use rising alpha instead of geometry-only alpha=1 (ablation)Affordance-Guided Coarse-to-Fine · OVMM 5 taskssuccess rate (%): 79 -> 85Improved
alpha=1 versus rising alpha on simple can-throw task (ablation)Affordance-Guided Coarse-to-Fine · Throw the can into trashsuccesses out of 20: 17/20 -> 20/20 (alpha=1 higher)Mixed
add Affordance Guidance Projection (Affordance RGB + Obstacle Map+) (ablation)Affordance-Guided Coarse-to-Fine · OVMM 5 taskssuccess rate (%): 48 -> 85Improved
add coarse affordance direction arrow A and fan region (ablation)Affordance-Guided Coarse-to-Fine · OVMM 5 taskssuccess rate (%): 62 -> 85Improved
add the 12 auxiliary directional arrows (ablation)Affordance-Guided Coarse-to-Fine · OVMM 5 taskssuccess rate (%): 80 -> 85Improved
use VLM-selected affordance point instead of object center for classical plannersA*/RRT* base placement · OVMM 5 taskssuccess rate (%): 47 -> 58 (A*); 50 -> 61 (RRT*)Improved
feed VLM obstacle map and affordance RGB instead of RGB only (Pivot)Pivot · OVMM 5 taskssuccess rate (%): 26 -> 23No clear effect
use proposed method instead of classical object-center plannersbase placement · OVMM 5 taskssuccess rate (%): 47 -> 85 (A*)Improved

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