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 (ρ1=0.95) that dominates kinematic effects. A 7,041-parameter multi-layer perceptron (MLP) achieves R2=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 R2=0.87, demonstrating zero-shot transfer to unseen robots and behaviors. The predictor runs in 224 μs 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.
Figures & tables
Figure 1: Power consumption autocorrelation across six motion trials. All trials exhibit lag-1 correlation ρ1>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 R2=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 R2 (left) and MAE (right) during multi-robot collision avoidance. The predictor achieves mean R2=0.87 across seven robots despite training on a single unit.
Accurate prediction of electrical power consumption is essential for energy-aware motion planning, battery management, and thermal monitoring in battery-powered humanoid robots. This letter presents a physics-based, linear-in-parameters model for the electrical power consumption of the seven-degree-of-freedom left arm of the UnitreeG1 humanoid robot. The proposed formulation combines actuator loss terms with a baseline-torque correction that captures changes in gravity-compensation load and enables accurate prediction of negative net power trajectories. Pairwise interaction terms are introduced to model power coupling during simultaneous multi-joint motion. Model parameters are identified from experimental data collected on a physical UnitreeG1 using onboard power measurements as the regression target. Across 897 trajectories covering single-joint and coordinated arm motions at multiple speed levels, the identified model achieves R2=0.933 with an RMSE of 1.07 (W). Validation on 46 trajectories executed at previously unseen speeds yields R2=0.965, demonstrating strong generalisation beyond the identification dataset. Analysis of the identified parameters reveals distinct power-consumption characteristics across the arm, with viscous friction dominating most joints (shoulder pitch and all three wrist joints), copper losses dominating shoulder yaw and the elbow, and shoulder roll uniquely dominated by Coulomb friction.
Nestor N. Deniz, Sebastian Vega, Simon Parsons +1
Engineering Department at Harper Adams University, Newport, Shropshire TF10 8NB, UK · Lincoln Institute for Agri-Food Technology and Lincoln Centre for Autonomous Systems
Accurate dynamics models are critical for the design of predictive controllers for autonomous mobile robots. Physics-based models are often too simple to capture relevant real-world effects, while data-driven models are data-intensive and slow to train. We introduce an approach for fast adaptation of neural robot dynamic models that combines offline training with efficient online updates. Our approach learns an incremental neural dynamics model offline and performs low-rank second-order parameter adaptation online, enabling rapid updates without full retraining. We demonstrate the approach on a real quadrotor robot, achieving robust predictive tracking control in novel operational conditions.
Abdullah Altawaitan, Nikolay Atanasov
Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA 92093, USA · Kuwait University
Autonomous aerial and aquatic robots that attain mobility by perturbing their medium, such as multicopters and torpedoes, produce wake effects that act as disturbances for adjacent robots. Wake effects are hard to model and predict due to the chaotic spatio-temporal dynamics of the fluid, entangled with the physical geometry of the robots and their complex motion patterns. Data-driven approaches using neural networks typically learn a memory-less function that maps the current states of the two robots to a force observed by the "sufferer" robot. Such models often perform poorly in agile scenarios: since the wake effect has a finite propagation time, the disturbance observed by a sufferer robot is some function of relative states in the past. In this work, we present an empirical study of the properties a wake-effect predictor must satisfy to accurately model the interactions between two robots mediated by a fluid. We explore seven data-driven models designed to capture the spatio-temporal evolution of fluid wake effects in four different media. This allows us to introspect the models and analyze the reasons why certain features enable improved accuracy in prediction across predictors and fluids. As experimental validation, we develop a planar rectilinear gantry for two spinning monocopters to test in real-world data with feedback control. The conclusion is that support of history of previous states as input and transport delay prediction substantially helps to learn an accurate wake-effect predictor.