Research map / Vision-language and multimodal / Robot action and navigation
MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation
Pingrui Zhang, Xianqiang Gao, Yuhan Wu, Kehui Liu, Dong Wang, Zhigang Wang, Bin Zhao, Yan Ding, Xuelong Li
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 |
|---|---|---|---|
| add robot information (base height, arm reach) tokens (ablation) | NavAff · MoMa-Kitchen test (unseen scenes) | PCC: 0.670 -> 0.680 | Improved |
| add robot information tokens (ablation) | NavAff · MoMa-Kitchen test (unseen scenes) | RMSE: 0.148 -> 0.147 | No clear effect |
| add Visual Alignment Module (VAM) (ablation) | NavAff · MoMa-Kitchen test (unseen scenes) | PCC: 0.562 -> 0.680 | Improved |
| add Visual Alignment Module (VAM) (ablation) | NavAff · MoMa-Kitchen test (unseen scenes) | RMSE: 0.165 -> 0.147 | Improved |
| add global point cloud input (ablation) | NavAff · MoMa-Kitchen test (unseen scenes) | PCC: 0.534 -> 0.680 | Improved |
| add global point cloud input (ablation) | NavAff · MoMa-Kitchen test (unseen scenes) | RMSE: 0.168 -> 0.147 | Improved |
| use NavAff instead of PointNet++ baseline | PointNet++ · MoMa-Kitchen test (unseen scenes) | RMSE: 0.164 -> 0.147 | Improved |
| use NavAff instead of PointNet++ baseline | PointNet++ · MoMa-Kitchen test (unseen scenes) | Top1 MSR: 0.60 -> 0.72 | Improved |
| use learned affordance model instead of random positions | Random · MoMa-Kitchen test (unseen scenes) | Top1 MSR: 0.080 -> 0.72 | Improved |
| expand candidate selection from Top1 to Top5 | NavAff · MoMa-Kitchen test (unseen scenes) | MSR: 0.72 -> 0.66 | No clear effect |
Closest papers by meaning
- A0: An Affordance-Aware Hierarchical Model for General Robotic Manipulation (ICCV 2025 · similarity 0.91)
- Affordance-Guided Coarse-to-Fine Exploration for Base Placement in Open-Vocabulary Mobile Manipulation (AAAI 2026 · similarity 0.90)
- MobileManiBench: Simplifying Model Verification for Mobile Manipulation (ECCV 2026 · similarity 0.90)
- MoManipVLA: Transferring Vision-language-action Models for General Mobile Manipulation (CVPR 2025 · similarity 0.89)
- AffordDP: Generalizable Diffusion Policy with Transferable Affordance (CVPR 2025 · similarity 0.88)
- ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks (ICLR 2025 · similarity 0.87)
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.
