用历史功耗数据预测机器人能耗，精度高且实时可用。
Data-Driven Autoregressive Power Prediction for GTernal Robots in the Robotarium
- 基于近期功耗历史构建自回归预测模型
- 在新机器人和行为上达到0.87的R²，零样本迁移成功
- 每推理仅224微秒，适合实时控制
多机器人系统的节能算法需要精准的功耗模型，但现有方法依赖运动学近似，难以捕捉真实硬件的复杂动态。本文针对佐治亚理工学院机器人实验室部署的GTernal移动机器人平台，提出一个轻量级自回归预测器。通过对6次运动实验中采集的48,000个样本分析，发现功耗具有强时间自相关性（ρ₁ = 0.95），远超运动学影响。一个含7,041个参数的多层感知机（MLP）通过结合近期功耗历史，在保留测试运动模式上实现R² = 0.90，达到由测量噪声决定的理论预测上限。在七台机器人上的物理验证中，碰撞规避场景的平均R²为0.87，证明了对未见机器人和行为的零样本迁移能力。该预测器每推理耗时224 μs，可支持150倍于平台30 Hz控制频率的实时部署。模型与数据集已公开，以支持节能型多机器人算法开发。
原文摘要 · Abstract (English)
Energy-aware algorithms for multi-robot systems require accurate power consumption models, yet existing approaches rely on kinematic approximations that fail to capture the complex dynamics of real hardware. We present a lightweight autoregressive predictor for the GTernal mobile robot platform deployed in the Georgia Tech Robotarium. Through analysis of 48,000 samples collected across six motion trials, we discover that power consumption exhibits strong temporal autocorrelation ($ρ_1 = 0.95$) that dominates kinematic effects. A 7,041-parameter multi-layer perceptron (MLP) achieves $R^2 = 0.90$ on held-out motion patterns by conditioning on recent power history, reaching the theoretical prediction ceiling imposed by measurement noise. Physical validation across seven robots in a collision avoidance scenario yields mean $R^2 = 0.87$, demonstrating zero-shot transfer to unseen robots and behaviors. The predictor runs in 224 $μ$s per inference, enabling real-time deployment at 150$\times$ the platform's 30 Hz control rate. We release the trained model and dataset to support energy-aware multi-robot algorithm development.
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。