Speaking the Navigator's Language: Trajectory-Grounded Instruction Translation for Frozen Aerial VLN Agents
cs.AI
Submitted: 2026-10-07
Updated: 2026-10-07
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Openfly: A comprehensive platform for aerial vision-language navigation
- LoRA: Low-Rank Adaptation of Large Language Models
- NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards
- Code as Policies: Language Model Programs for Embodied Control
- Advances in Embodied Navigation Using Large Language Models: A Survey
- VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation
- A Survey on Vision-Language-Action Models for Embodied AI
- Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation
- AeroVerse: UAV-Agent Benchmark Suite for Simulating, Pre-training, Finetuning, and Evaluating Aerospace Embodied World Models
- T-araVLN: Translator for Agricultural Robotic Agents on Vision-and-Language Navigation
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems