2025/06/16 by Qianzhong Chen, Chen, Qianzhong, Naixiang Gao +10 · 7 citations
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #FOS: Computer and information sciences #Robotic Path Planning Algorithms #Robotics (cs.RO) #Robotics and Sensor-Based Localization
paper · pdf · doi:10.48550/arxiv.2506.14009
openalex publication_date 2025/06/16 · openalex created_date 2025/10/18 · openalex updated_date 2026/07/28
Autonomous drones capable of interpreting and executing high-level language instructions in unstructured environments remain a long-standing goal. Yet existing approaches are constrained by their dependence on hand-crafted skills, extensive parameter tuning, or computationally intensive models unsuitable for onboard use. We introduce GRaD-Nav++, a lightweight Vision-Language-Action (VLA) framework that runs fully onboard and follows natural-language commands in real time. Our policy is trained in a photorealistic 3D Gaussian Splatting (3DGS) simulator via Differentiable Reinforcement Learning (DiffRL), enabling efficient learning of low-level control from visual and linguistic inputs. At its core is a Mixture-of-Experts (MoE) action head, which adaptively routes computation to improve generalization while mitigating forgetting. In multi-task generalization experiments, GRaD-Nav++ achieves a success rate of 83% on trained tasks and 75% on unseen tasks in simulation. When deployed on real hardware, it attains 67% success on trained tasks and 50% on unseen ones. In multi-environment adaptation experiments, GRaD-Nav++ achieves an average success rate of 81% across diverse simulated environments and 67% across varied real-world settings. These results establish a new benchmark for fully onboard Vision-Language-Action (VLA) flight and demonstrate that compact, efficient models can enable reliable, language-guided navigation without relying on external infrastructure.