Training Generalist Navigation Policies via Action Self-Distillation

arXiv:2610.17593 · cs.RO, cs.LG · Submitted 2026-10-13 · Read on arXiv

cs.RO, cs.LG

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: Accepted to the 10th Conference on Robot Learning (CoRL 2026)

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

Terminology

• Distillation — 1× in this paper · explained in 2 episodes
• Self-Distillation — 1× in this paper · explained in 7 episodes

Sources

• OpenVLA: An Open-Source Vision-Language-Action Model
• OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation
• Rapid Exploration for Open-World Navigation with Latent Goal Models
• ViNT: A Foundation Model for Visual Navigation
• Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs
• VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable Navigation
• Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
• NaVILA: Legged Robot Vision-Language-Action Model for Navigation
• Reinforcement Learning via Self-Distillation
• Self-Distillation Enables Continual Learning
• VERDI: VLM-Embedded Reasoning for Autonomous Driving
• VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision
• Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail

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