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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use coarse-to-fine schedule (alpha rising) instead of fixed alpha=0 (ablation) | Affordance-Guided Coarse-to-Fine · OVMM 5 tasks | success rate (%): 43 -> 85 | Improved |
| use rising alpha instead of fixed alpha=0.5 (ablation) | Affordance-Guided Coarse-to-Fine · OVMM 5 tasks | success rate (%): 76 -> 85 | Improved |
| use rising alpha instead of geometry-only alpha=1 (ablation) | Affordance-Guided Coarse-to-Fine · OVMM 5 tasks | success rate (%): 79 -> 85 | Improved |
| alpha=1 versus rising alpha on simple can-throw task (ablation) | Affordance-Guided Coarse-to-Fine · Throw the can into trash | successes 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 tasks | success rate (%): 48 -> 85 | Improved |
| add coarse affordance direction arrow A and fan region (ablation) | Affordance-Guided Coarse-to-Fine · OVMM 5 tasks | success rate (%): 62 -> 85 | Improved |
| add the 12 auxiliary directional arrows (ablation) | Affordance-Guided Coarse-to-Fine · OVMM 5 tasks | success rate (%): 80 -> 85 | Improved |
| use VLM-selected affordance point instead of object center for classical planners | A*/RRT* base placement · OVMM 5 tasks | success rate (%): 47 -> 58 (A*); 50 -> 61 (RRT*) | Improved |
| feed VLM obstacle map and affordance RGB instead of RGB only (Pivot) | Pivot · OVMM 5 tasks | success rate (%): 26 -> 23 | No clear effect |
| use proposed method instead of classical object-center planners | base placement · OVMM 5 tasks | success rate (%): 47 -> 85 (A*) | Improved |
Closest papers by meaning
- OmniManip: Towards General Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraints (CVPR 2025 · similarity 0.90)
- AffordDP: Generalizable Diffusion Policy with Transferable Affordance (CVPR 2025 · similarity 0.90)
- Localizing, Structuring, and Rendering: Bridging 3D and 2D Vision-Language-Action Models for Robotic Manipulation (CVPR 2026 · similarity 0.89)
- SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model (CVPR 2025 · similarity 0.88)
- MoManipVLA: Transferring Vision-language-action Models for General Mobile Manipulation (CVPR 2025 · similarity 0.88)
- Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Models (AAAI 2026 · similarity 0.88)
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.
