Zero-Shot Generalization from Motion Demonstrations to New Tasks

arXiv:2603.15445 · cs.RO · Submitted 2026-03-16 · Read on arXiv

cs.RO

Submitted: 2026-03-16

Updated: 2026-03-16

Journal ref: 2026 IEEE 22nd International Conference on Automation Science and Engineering (CASE), 2026, pp. 1-8

DOI: 10.1109/CASE69030.2026.11704238

Code: https://github.com/KilianFt/DemoStitching

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generalization — 3× in this paper · explained in 13 episodes
• Convergence Guarantees — 1× in this paper · explained in 3 episodes
• Motion Primitives — 1× in this paper · explained in 2 episodes
• Zero-Shot Generalization — 1× in this paper · explained in 5 episodes

Sources

• OpenVLA: An Open-Source Vision-Language-Action Model

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
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies