From Pixel to Poses: Object-centric Tool Manipulation Learning from Human Demonstrations
cs.RO, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/OpenDriveLab/P2P-T
Terminology
Sources
- Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
- SAM 3D: 3Dfy Anything in Images
- EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data
- EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- FUNCTO: Function-Centric One-Shot Imitation Learning for Tool Manipulation
- SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation
- Octo: An Open-Source Generalist Robot Policy
- OpenVLA: An Open-Source Vision-Language-Action Model
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Dreamitate: Real-World Visuomotor Policy Learning via Video Generation
- Causal World Modeling for Robot Control
- RISE: Self-Improving Robot Policy with Compositional World Model
- TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding
- DINOv2: Learning Robust Visual Features without Supervision
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving