Research map / Vision-language and multimodal / Robot action and navigation
MobileManiBench: Simplifying Model Verification for Mobile Manipulation
Wenbo Wang, Fangyun Wei, Qixiu Li, Xi Chen, Yaobo Liang, Chang Xu, Jiaolong Yang, Baining Guo
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 depth to multi-view RGB input (ablation) | MobileManiVLA · MobileManiBench G1 ablation subset | success rate (%): 14.9 -> 28.2 | Improved |
| add wrist view to head-view RGB-D (ablation) | MobileManiVLA · MobileManiBench G1 ablation subset | success rate (%): 14.1 -> 28.2 | Improved |
| add depth to head-view RGB (ablation) | MobileManiVLA · MobileManiBench G1 ablation subset | success rate (%): 7.9 -> 14.1 | Improved |
| add wrist view to head-view RGB (ablation) | MobileManiVLA · MobileManiBench G1 ablation subset | success rate (%): 7.9 -> 14.9 | Improved |
| add hand pose state input (ablation) | MobileManiVLA · MobileManiBench G1 ablation subset | success rate (%): 22.4 -> 28.2 | Improved |
| add object grasp point state (ablation) | MobileManiVLA · MobileManiBench G1 ablation subset | success rate (%): 28.2 -> 32.3 | Improved |
| add goal point state (ablation) | MobileManiVLA · MobileManiBench G1 ablation subset | success rate (%): 32.3 -> 36.6 | Improved |
| add hand pose state input (ablation) | MobileManiVLA · MobileManiBench G1 ablation subset (cart) | success rate (%): 28.1 -> 23.5 | Hurt |
| test on seen scenes instead of unseen scenes (unseen objects) | MobileManiVLA · MobileManiBench G1 ablation subset | success rate (%): 28.2 -> 39.2 | Improved |
| test on seen objects instead of unseen objects (unseen scenes) | MobileManiVLA · MobileManiBench G1 ablation subset | success rate (%): 28.2 -> 51.3 | Improved |
| use MobileManiVLA instead of pi0.5 | pi0.5 · MobileManiBench G1 ablation subset | success rate (%): 18.8 -> 28.2 | Improved |
| use MobileManiVLA instead of OpenVLA | OpenVLA · MobileManiBench G1 ablation subset | success rate (%): 4.5 -> 28.2 | Improved |
Closest papers by meaning
- MoManipVLA: Transferring Vision-language-action Models for General Mobile Manipulation (CVPR 2025 · similarity 0.91)
- ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation (NeurIPS 2025 · similarity 0.90)
- Scaffolding Dexterous Manipulation with Vision-Language Models (NeurIPS 2025 · similarity 0.89)
- AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation (NeurIPS 2025 · similarity 0.89)
- ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning (NeurIPS 2026 · similarity 0.89)
- Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models (NeurIPS 2026 · similarity 0.89)
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.
