Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Data-Driven Autoregressive Power Prediction for GTernal Robots in the Robotarium

Yassin Abdelmeguid, Ammar Hasan

Abstract

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.

Data-Driven Autoregressive Power Prediction for GTernal Robots in the Robotarium

Abstract

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 () that dominates kinematic effects. A 7,041-parameter multi-layer perceptron (MLP) achieves 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 , demonstrating zero-shot transfer to unseen robots and behaviors. The predictor runs in 224 s per inference, enabling real-time deployment at 150 the platform's 30 Hz control rate. We release the trained model and dataset to support energy-aware multi-robot algorithm development.
Paper Structure (10 sections, 5 figures)

This paper contains 10 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Data Collection
  4. Power Consumption Analysis
  5. Model Architecture
  6. Results
  7. Single-Robot Validation
  8. Multi-Robot Physical Validation
  9. Deployment
  10. Conclusion

Figures (5)

  • Figure 1: Power consumption autocorrelation across six motion trials. All trials exhibit lag-1 correlation $\rho_1 > 0.94$, with the structure persisting across diverse motion patterns. This strong temporal dependence motivates autoregressive prediction.
  • Figure 2: Time series of predicted and actual power over a 20-second segment from the structured motion trial. The predictor tracks rapid transitions and sustained levels with minimal lag.
  • Figure 3: Predicted versus actual power consumption on the held-out steady-state trial. Points cluster tightly around the identity line with $R^2 = 0.92$ and MAE = 31.5 mW.
  • Figure 4: Distribution of prediction residuals across all trials. The distribution is approximately Gaussian with mean 1.3 mW and 90% of errors falling within $[-47, 50]$ mW.
  • Figure 5: Per-robot $R^2$ (left) and MAE (right) during multi-robot collision avoidance. The predictor achieves mean $R^2 = 0.87$ across seven robots despite training on a single unit.