TAME-Nav: Temporal Asymmetric Mixture-of-Experts Distillation for Agile and Versatile Robot Navigation
cs.RO
Submitted: 2026-10-09
Updated: 2026-10-09
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- NaVILA: Legged Robot Vision-Language-Action Model for Navigation
- Learning Real-world Autonomous Navigation by Self-Supervised Environment Synthesis
- SaferPath: Hierarchical Visual Navigation with Learned Guidance and Safety-Constrained Control
- Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion
- TOP-Nav: Legged Navigation Integrating Terrain, Obstacle and Proprioception Estimation
- Asymmetric Actor Critic for Image-Based Robot Learning
- Toward Reliable Sim-to-Real Predictability for MoE-based Robust Quadrupedal Locomotion
- Proximal Policy Optimization Algorithms
- SEA-Nav: Efficient Policy Learning for Safe and Agile Quadruped Navigation in Cluttered Environments
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