Research map / 3D vision / 3D generation
Whole-Body Coordination for Dynamic Object Grasping with Legged Manipulators
Qiwei Liang, Boyang Cai, Rongyi He, Hui Li, Tao Teng, Haihan Duan, Changxin Huang, Runhao Zeng
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 Grasp Fusion Module to teacher (ablation) | DQ-Net · DQ-Bench Level 4 | GSR student (%): 33.3 -> 41.0 | Improved |
| add object velocity input to teacher (ablation) | DQ-Net · DQ-Bench Level 4 | GSR student (%): 34.8 -> 41.0 | Improved |
| add Grasp Fusion Module to teacher (ablation) | DQ-Net · DQ-Bench Level 4 | OSSR (%): 28.9 -> 38.5 | Improved |
| add velocity input to teacher (ablation) | DQ-Net · DQ-Bench Level 4 | OSSR (%): 34.0 -> 38.5 | Improved |
| add GFM to teacher (ablation) | DQ-Net · DQ-Bench Level 1 | TSC (timesteps): 36.20 -> 35.45 | Mixed |
| add velocity input to teacher (ablation) | DQ-Net · DQ-Bench Level 3 | TSC (timesteps): 35.22 -> 35.27 | No clear effect |
| DQ-Net vs VBC-D (reward adapted for dynamic grasping) | DQ-Net student · DQ-Bench Level 4 | GSR (%): 16.0 -> 41.0 | Improved |
| adapt VBC reward/constraints for dynamic objects (VBC-D vs VBC) | VBC · DQ-Bench Level 1 | GSR-T (%): 0.0 -> 57.5 | Improved |
| Transformer dual-view student instead of CNN-based student (ablation) | student policy · DQ-Bench Level 4 | GSR (%): 36.14 -> 41.04 | Improved |
| DQ-Net vs VBC-D on timesteps | DQ-Net · DQ-Bench Level 4 | TSC (timesteps): 41.56 -> 34.32 | Improved |
Closest papers by meaning
- D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions (CVPR 2022 · similarity 0.88)
- Target-Referenced Reactive Grasping for Dynamic Objects (CVPR 2023 · similarity 0.87)
- ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks (AAAI 2026 · similarity 0.86)
- UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping (CVPR 2025 · similarity 0.86)
- Humanoid Horizon: Extending Task Horizon in Whole-Body Loco-Manipulation via Parallel Training, Dynamic Starting, and Reward Gating (NeurIPS 2026 · similarity 0.85)
- Omnigrasp: Grasping Diverse Objects with Simulated Humanoids (NeurIPS 2024 · similarity 0.85)
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.
