用强化学习实现机器人本地云端智能协作，提升实时导航效率。
UniLCD: Unified Local-Cloud Decision-Making via Reinforcement Learning
- 通过强化学习动态决策何时本地计算、何时云端处理。
- 在复杂导航任务中性能效率比顶尖方法提升35%以上。
- 适合对安全、延迟敏感的机器人实时系统应用。
具身视觉类真实世界系统（如移动机器人）需在能耗、计算延迟和安全约束间取得平衡，以适应动态任务与环境。由于本地计算能力受限，将计算任务卸载至远程服务器可节省本地资源，并利用强大模型获得高质量预测。然而，通信与延迟开销限制了云模型在动态、安全关键、实时场景中的应用。为此，我们提出UniLCD，一种新型混合推理框架，支持灵活的本地-云端协同。通过强化学习优化灵活的路由模块，并采用多任务目标，UniLCD专为满足安全关键型端到端移动系统的多重约束而设计。我们在一个要求频繁且及时切换本地/云端操作的复杂拥挤导航任务中验证该方法。结果表明，相比基于分段计算和早期退出策略的先进基线，UniLCD在整体性能与效率上提升超过35%。
原文摘要 · Abstract (English)
Embodied vision-based real-world systems, such as mobile robots, require a careful balance between energy consumption, compute latency, and safety constraints to optimize operation across dynamic tasks and contexts. As local computation tends to be restricted, offloading the computation, ie, to a remote server, can save local resources while providing access to high-quality predictions from powerful and large models. However, the resulting communication and latency overhead has led to limited usability of cloud models in dynamic, safety-critical, real-time settings. To effectively address this trade-off, we introduce UniLCD, a novel hybrid inference framework for enabling flexible local-cloud collaboration. By efficiently optimizing a flexible routing module via reinforcement learning and a suitable multi-task objective, UniLCD is specifically designed to support the multiple constraints of safety-critical end-to-end mobile systems. We validate the proposed approach using a challenging, crowded navigation task requiring frequent and timely switching between local and cloud operations. UniLCD demonstrates improved overall performance and efficiency, by over 35% compared to state-of-the-art baselines based on various split computing and early exit strategies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。