Research map / Vision-language and multimodal / Robot action and navigation
A3D: Adaptive Affordance Assembly with Dual-Arm Manipulation
Jiaqi Liang, Yue Chen, Qize Yu, Yan Shen, Haipeng Zhang, Hao Dong, Ruihai Wu
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 Top-K candidate sampling (ablation) | A3D · Test categories: Screw | success rate: 54.1% -> 56.3% | Improved |
| add Top-K candidate sampling (ablation) | A3D · Test categories: Pick Up | success rate: 41.1% -> 47.1% | Improved |
| add Top-K candidate sampling (ablation) | A3D · Test categories: Push | success rate: 53.7% -> 67.9% | Improved |
| add Top-K candidate sampling (ablation) | A3D · Train categories: Pick Up | success rate: 66.1% -> 62.0% | Hurt |
| add interaction-context adaptation (ablation) | A3D · Test categories: Screw | success rate: 34.2% -> 56.3% | Improved |
| add interaction-context adaptation (ablation) | A3D · Test categories: Pick Up | success rate: 42.2% -> 47.1% | Improved |
| add interaction-context adaptation (ablation) | A3D · Train categories: Push | success rate: 74.3% -> 80.6% | Improved |
| use learned affordance framework over heuristic rules (ablation) | A3D · Test categories: Pull | success rate: 31.9% -> 61.7% | Improved |
| use A3D over DP3 imitation policy (ablation) | A3D · Test categories: Pull | success rate: 10.1% -> 61.7% | Improved |
| use LLM-guided support prediction | A3D · All tasks | success rate: 0.0% on all tasks | Hurt |
| use A3D over heuristic in real world | A3D · Real world: Pick Up | successes /15: 5 / 15 -> 9 / 15 | Improved |
Closest papers by meaning
- BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly (ICML 2025 · similarity 0.89)
- Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation (CVPR 2025 · similarity 0.89)
- AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning (ICLR 2025 · similarity 0.87)
- SRSA: Skill Retrieval and Adaptation for Robotic Assembly Tasks (ICLR 2025 · similarity 0.87)
- IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos (NeurIPS 2024 · similarity 0.86)
- IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments (CVPR 2025 · similarity 0.86)
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.
