EdgeNav-QE: QLoRA量化与动态提前退出用于边缘设备上的基于LAM的导航
EdgeNav-QE: QLoRA Quantization and Dynamic Early Exit for LAM-based Navigation on Edge Devices
AI总结：
EdgeNav-QE通过QLoRA量化和动态提前退出机制优化LAMs在边缘设备上的实时导航性能，显著降低延迟和内存占用，同时保持高导航成功率。
摘要：
大型动作模型（LAMs）通过将高层推理与低层控制相结合，在自主导航中展现出巨大潜力。然而，将这些数十亿参数模型部署到边缘设备上仍然面临显著挑战，因为存在内存限制和延迟要求。在本文中，我们提出了EdgeNav-QE，一种新颖的框架，将量化低秩适应（QLoRA）与动态提前退出（DEE）机制相结合，以优化LAMs用于实时边缘导航。通过将骨干网络量化到4位精度，并战略性地放置提前退出分支，使模型能够对简单的导航任务提前终止推理，同时保留完整深度用于复杂决策。在使用Matterport3D数据集的Habitat-Sim环境中，使用OpenVLA-7B骨干网络的实验结果表明，与全精度基线相比，EdgeNav-QE将推理延迟降低了82.7%，内存占用减少了66.7%，同时保持了81.8%的导航成功率。此外，它在延迟方面比最先进的静态提前退出方法高出17.9%，证明了内容感知自适应计算在安全关键应用中的优越性。
英文摘要：
Large Action Models (LAMs) have shown immense potential in autonomous navigation by bridging high-level reasoning with low-level control. However, deploying these multi-billion parameter models on edge devices remains a significant challenge due to memory constraints and latency requirements. In this paper, we propose EdgeNav-QE, a novel framework that integrates Quantized Low-Rank Adaptation (QLoRA) with a dynamic early-exit (DEE) mechanism to optimize LAMs for real-time edge navigation. By quantizing the backbone to 4-bit precision and strategically placing early-exit branches, we enable the model to terminate inference early for simple navigation tasks while retaining full depth for complex decision-making. Experimental results on the Habitat-Sim environment with Matterport3D dataset using OpenVLA-7B backbone, demonstrate that EdgeNav-QE reduces inference latency by 82.7% and memory footprint by 66.7% compared to full-precision baselines, while maintaining 81.8% navigation success rate. Furthermore, it outperforms state-of-the-art static early-exit method by 17.9% in latency, demonstrating the superiority of content-aware adaptive computation for safety-critical applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
