Energy consumption optimisation has emerged as a critical need in Autonomous Mobile Robots (AMRs). Conventional A* implementations typically minimise path distance, neglecting energy-relevant factors such as directional changes and trajectory smoothness that significantly impact battery life and operational costs. This work proposes two energy-aware A* variants trained on empirical data from the KUKA KMP 1500 platform, where energy consumption is measured as battery SoC depletion: A*-RF, which integrates a Random Forest (RF) model directly into the cost function, and A*-MOD, which approximates the energy model through RF feature importance weights, achieving linear computational complexity O(nf). The RF model predicted energy consumption with an RMSE below 1.5% relative error, identifying travel distance and rotation angle as the dominant energy factors. Experimental validation across 42 path planning scenarios on a real industrial factory floor demonstrates that A*-MOD reduces energy consumption by up to 58.91% and improves operational autonomy by 2.21 times, with statistically significant improvements (p < 0.01) across all evaluated metrics.

Accurate energy prediction is essential for energy-aware planning and navigation of autonomous mobile robots (AMRs). This study investigates whether a compact feed-forward neural network (FFNN) can predict relative energy consumption from operational variables with high accuracy and interpretability. Using a curated dataset of controlled translation and rotation trials on a KUKA KMP 1500P, energy demand is expressed as the per-trial reduction in battery state of charge (SoC), defined as $N_{1\mathrm{\%}}$. For unit-free reporting, it is also considered the normalized SoC consumed per trial, defined as $E=1/N_{1\mathrm{\%}}$. Model development followed a two-stage optimization pipeline, (i) systematic feature-subset screening and (ii) cross-validated architecture and regularization search with early stopping, assessed by a composite of MSE, MAE, ${\mathrm{R}}^2$, and the 68th-percentile absolute error ($∆X_{68}$) as the prediction precision index. The selected FFNN (ReLU multilayer perceptron with L2 weight decay) achieved strong generalization on the independent test set (MAE = 0.9954, MSE = 4.5512, ${\mathrm{R}}^2$ = 0.9795, $∆X_{68}$ = 0.0193). Post hoc explainability methods (SHAP and input perturbation) identified angular velocity and linear acceleration as the dominant predictors, with payload mass exerting secondary effects. These results demonstrate that a compact, regularized FFNN provides accurate, repeatable, and interpretable energy predictions suitable for integration into digital twin platforms and downstream industrial scheduling.

Regarding autonomous vehicle navigation, reinforcement learning is a technique that has demonstrated significant results. Nevertheless, it is a technique with a high number of parameters that need to be optimised without prior information, and correctly performing this is a complicated task. In this research study, a system based on the principles of reinforcement learning, specifically on the concept of rewards, is presented. A mathematical expression was proposed to control the vehicle’s direction based on its position, the obstacles in the environment and the destination. In this equation proposal, there was only one unknown parameter that regulated the degree of the action to be taken, and this was optimised through the genetic algorithm. In this way, a less computationally expensive navigation algorithm was presented, as it avoided the use of neural networks. The controller’s time to obtain the navigation instructions was around 6.201·10⁻⁴ s. This algorithm is an efficient and accurate system which manages not to collide with obstacles and to reach the destination from any position. Moreover, in most cases, it has been found that the proposed navigations are also optimal.