Towards Precise Intent-Aligned VLA Aerial Navigation via Expert-Guided GRPO

• URL: http://arxiv.org/abs/2606.02313v1
• Date: Mon, 01 Jun 2026 14:31:35 GMT
• Title: Towards Precise Intent-Aligned VLA Aerial Navigation via Expert-Guided GRPO
• Abstract summary: We introduce an efficient reinforcement learning framework for VLA-based aerial navigation.<n>At its core, we propose EG-GRPO to augment online rollouts with few-shot expert data.<n>Across multiple tasks specified by complex human intents, EG-GRPO improves the success rate to 2.13x that of the SFT baseline, while improving intent alignment performance by 60.9%.
• Score: 10.368821738661707
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models offer a promising end-to-end paradigm for unmanned aerial vehicles (UAVs) to accomplish complex tasks specified by fine-grained instructions. However, standard supervised fine-tuning (SFT) suffers from data scarcity, limited generalization, and weak supervision for nuanced and complicated human intents. Reinforcement fine-tuning offers a natural way to mitigate these challenges and align policy behaviors with human intents through designable feedback, but applying it to aerial navigation remains challenging due to inefficient exploration in expansive continuous spaces. To address these challenges, we introduce an efficient reinforcement learning (RL) framework for VLA-based aerial navigation. At its core, we propose EG-GRPO (Expert-Guided Group Relative Policy Optimization) to augment online rollouts with few-shot expert data. Additionally, we design a heterogeneous pipeline enabling parallel simulation and inference, which reduces rollout time by 43.5%. Across multiple tasks specified by complex human intents, EG-GRPO improves the success rate to 2.13x that of the SFT baseline, while improving intent alignment performance by 60.9%. These results demonstrate that our framework can move aerial navigation toward precise intent-aligned flight.

Related papers

• HiPAN: Hierarchical Posture-Adaptive Navigation for Quadruped Robots in Unstructured 3D Environments [13.984002802852638]
  Navigating quadruped robots in unstructured 3D environments poses significant challenges, requiring goal-directed motion, effective exploration to escape from local minima, and posture adaptation to traverse narrow, height-constrained spaces.<n>We propose Hierarchical Posture-Adaptive Navigation (HiPAN), a framework that operates directly on onboard depth images at deployment.<n>HiPAN achieves myopic higher navigation success rates and greater path efficiency than classical reactive planners and end-to-end baselines, while real-world experiments further validate its applicability across diverse, unstructured 3D environments.
  arXiv  Detail & Related papers  (2026-04-29T10:08:48Z)
• HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving [51.268878540511054]
  We propose HAD, an end-to-end planning framework with a Hierarchical Diffusion Policy.<n>We show that HAD achieves new state-of-the-art performance on both NAVSIM and HUGSIM.
  arXiv  Detail & Related papers  (2026-04-04T04:12:47Z)
• $π$, But Make It Fly: Physics-Guided Transfer of VLA Models to Aerial Manipulation [14.43820301560473]
  We introduce AirVLA, a system that investigates the transferability of manipulation-pretrained VLAs to aerial pick-and-place tasks.<n>To bridge this "dynamics gap," we introduce a Payload-Aware Guidance mechanism that injects payload constraints directly into the policy's flow-matching sampling process.<n>We evaluate our method through a cumulative 460 real-world experiments which demonstrate that this synthetic data is a key enabler of performance.
  arXiv  Detail & Related papers  (2026-03-26T05:19:54Z)
• Trajectory-Diversity-Driven Robust Vision-and-Language Navigation [39.4949197412916]
  Vision-and-Language Navigation (VLN) requires agents to navigate photo-realistic environments following natural language instructions.<n>We present NavGRPO, a reinforcement learning framework that learns goal-directed navigation policies.<n>We demonstrate +14.89% SPL gain over the baseline, confirming that goal-directed RL training builds substantially more robust navigation policies.
  arXiv  Detail & Related papers  (2026-03-16T14:46:54Z)
• TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training [53.93696896939915]
  Training tool-use agents typically rely on Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks.<n>We propose TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology.<n>TopoCurate achieves consistent gains of 4.2% (SFT) and 6.9% (RL) over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-02T10:38:54Z)
• Hierarchical Reinforcement Learning for Cooperative Air-Ground Delivery in Urban System [41.96919926267983]
  We propose HRL4AG, a Hierarchical Reinforcement Learning framework for cooperative Air-Ground delivery.<n>Specifically, HRL4AG employs a high-level manager to tackle the scalability bottleneck by decomposing the joint action space.<n>Experiments on two real-world datasets and an evaluation platform demonstrate that HRL4AG significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-13T13:19:59Z)
• VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments [12.689250855332569]
  VLA-AN is a framework dedicated to autonomous drone navigation in complex environments.<n>It addresses four major limitations of existing large aerial navigation models.<n>It achieves a maximum single-task success rate of 98.1%.
  arXiv  Detail & Related papers  (2025-12-17T10:02:55Z)
• STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization [73.98141357780032]
  VLN-CE task requires agents to navigate 3D environments using natural language instructions, without any scene-specific training.<n>Existing methods often fail to achieve robust navigation due to a lack of structured decision-making and insufficient integration of feedback from previous actions.<n>We propose STRIDER, a novel framework that systematically optimize the agent's decision space by integrating spatial layout priors and dynamic task feedback.<n>Our approach introduces two key innovations: 1) a Structured Waypoint Generator that constrains the action space through spatial structure, and 2) a Task-Alignment Regulator that adjusts behavior based on task progress, ensuring semantic alignment throughout navigation.
  arXiv  Detail & Related papers  (2025-10-27T04:37:21Z)
• Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning [125.61772424068903]
  Vision-and-language navigation (VLN) asks an agent to follow a given language instruction to navigate through a real 3D environment. We present a model-agnostic training paradigm, called Progressive Perturbation-aware Contrastive Learning (PROPER) to enhance the generalization ability of existing VLN agents.
  arXiv  Detail & Related papers  (2024-03-09T02:34:13Z)
• Angle Robustness Unmanned Aerial Vehicle Navigation in GNSS-Denied Scenarios [66.05091704671503]
  We present a novel angle navigation paradigm to deal with flight deviation in point-to-point navigation tasks. We also propose a model that includes the Adaptive Feature Enhance Module, Cross-knowledge Attention-guided Module and Robust Task-oriented Head Module.
  arXiv  Detail & Related papers  (2024-02-04T08:41:20Z)
• Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation [72.24964965882783]
  Reinforcement learning (RL) is a promising approach for robotic navigation, allowing robots to learn through trial and error.<n>Real-world robotic tasks often suffer from sparse rewards, leading to inefficient exploration and suboptimal policies.<n>We introduce Confidence-Controlled Exploration (CCE), a novel method that improves sample efficiency in RL-based robotic navigation without modifying the reward function.
  arXiv  Detail & Related papers  (2023-06-09T18:45:15Z)
• Counterfactual Vision-and-Language Navigation via Adversarial Path Sampling [65.99956848461915]
  Vision-and-Language Navigation (VLN) is a task where agents must decide how to move through a 3D environment to reach a goal.<n>One of the problems of the VLN task is data scarcity since it is difficult to collect enough navigation paths with human-annotated instructions for interactive environments.<n>We propose an adversarial-driven counterfactual reasoning model that can consider effective conditions instead of low-quality augmented data.
  arXiv  Detail & Related papers  (2019-11-17T18:02:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.