Research map / 3D vision / 3D generation
BiPreManip: Learning Affordance-Based Bimanual Preparatory Manipulation through Anticipatory Collaboration
Yan Shen, Feng Jiang, Zichen He, Xiaoqi Li, Yuchen Liu, Zhiyu Li, Ruihai Wu, Hao Dong
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 anticipatory goal affordance stage (ablation) | BiPreManip · Articulated Bottle (unseen) | Success rate: 13% -> 26% | Improved |
| add anticipatory goal affordance stage (ablation) | BiPreManip · Articulated Pen-cap (unseen) | Success rate: 10% -> 32% | Improved |
| add anticipatory goal affordance stage (ablation) | BiPreManip · Articulated Stapler (unseen) | Success rate: 23% -> 30% | Improved |
| add anticipatory object pose predictor (ablation) | BiPreManip · Articulated Bottle (unseen) | Success rate: 15% -> 26% | Improved |
| add anticipatory object pose predictor (ablation) | BiPreManip · Articulated Pliers (unseen) | Success rate: 31% -> 29% | No clear effect |
| add anticipatory object pose predictor (ablation) | BiPreManip · Articulated USB (unseen) | Success rate: 6% -> 14% | No clear effect |
| add anticipatory components overall (ablation) | BiPreManip · Articulated tasks | Success rate | Improved |
| use BiPreManip instead of single-arm W2A | BiPreManip · Edge-pushing Cap (unseen) | Success rate: 4% -> 74% | Improved |
| use BiPreManip instead of 3DFA bimanual policy | BiPreManip · Real-world Edge Hat | Success (of 10): 0/10 -> 8/10 | Improved |
| use BiPreManip instead of handcrafted Heuristic with GT info | BiPreManip · Articulated Plate (unseen) | Success rate: 78% -> 82% | No clear effect |
Closest papers by meaning
- Afford-X: Generalizable and Slim Affordance Reasoning for Task-Oriented Manipulation (TPAMI 2026 · similarity 0.90)
- BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly (ICML 2025 · similarity 0.90)
- A0: An Affordance-Aware Hierarchical Model for General Robotic Manipulation (ICCV 2025 · similarity 0.90)
- AffordGrasp: Cross-Modal Diffusion for Affordance-Aware Grasp Synthesis (CVPR 2026 · similarity 0.89)
- AffordDP: Generalizable Diffusion Policy with Transferable Affordance (CVPR 2025 · similarity 0.89)
- OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion (CVPR 2024 · 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.
