Probabilistic Meta-Conv1D Driving Energy Prediction for Mobile Robots in Unstructured Terrains

Abstract

Driving energy consumption plays an important role in the navigation of autonomous mobile robots in off-road scenarios. However, the accuracy of the driving energy predictions is often affected by a high degree of uncertainty due to unknown and constantly varying terrain properties, and the complex wheel-terrain interaction in unstructured terrains. In this paper, a probabilistic deep meta-learning approach is proposed to model the existing uncertainty in the driving energy consumption and efficiently adapt the probabilistic predictions based on a small number of local measurements. The method expands upon an existing deterministic deep-meta learning model that, in contrast, only provided single-point energy estimates. The performance of the proposed method is compared against the deterministic approach in a 3D-body dynamic simulator over several typologies of deformable terrains and unstructured geometries. In this way, the benefits of the proposed method are illustrated to enhance the predictions with informative probabilistic considerations, which can be crucial to the safety of mobile robots traversing challenging, unstructured environments.INDEX TERMS Autonomous mobile robots, deep learning, energy-aware path planning, meta-learning, probabilistic neural networks

A Survey on Path Planning for Autonomous Ground Vehicles in Unstructured Environments

“…In unstructured environments, the variations in energy consumption among different paths are substantial due to the diverse terrain conditions. For resource-constrained contexts, such as military, agriculture, planetary rover, and disaster relief missions, prioritizing the reduction in energy costs is crucial for the successful accomplishment of the tasks [51,66,[82][83][84]. In pursuit of minimizing energy expenses and enhancing operational efficiency, the selection of the shortest distance or time-optimal path is often favored [85,86].…”

“…The energy cost estimation methods of unstructured environments typically fall into two categories: physics model-based methods and data-driven methods [83], as shown in Table 6. [51] Data-driven-Terrain type, elevation, driving operation…”

A review on energy efficiency in autonomous mobile robots

“…In Visca et al (2022), the authors proposed a probabilistic deep meta-learning approach for predicting driving energy consumption of AMRs navigating in complex, unstructured environments. Figure 9 visually demonstrates the difference between meta-learning and multi-task learning.…”

Modeling analysis and experiment for energy system of ocean energy driven unmanned marine vehicle: The Yulang II case study

“…For instance, Visca et al (2021) used an optimized neural network to forecast the energy consumption of robots during exploration tasks, resulting in more efficient task planning. Additionally, Visca et al (2022) proposed a method to forecast the driving energy consumption of robots on nonstructured terrain, resulting in the minimization of robot travel energy consumption.…”

“…used an optimized neural network to forecast the energy consumption of robots during exploration tasks, resulting in more efficient task planning. Additionally,Visca et al (2022) proposed a method to forecast the driving energy consumption of robots on nonstructured terrain, resulting in the minimization of robot travel energy consumption.As a type of mobile robot, called OMVs, they have received less attention in energy modeling research when compared to ground robots. Furthermore, the experimental validation of terrestrial robots is relatively straightforward compared to OMV.…”