Interpretable Vehicle Speed Estimation Based on Dual Attention Network for 4WD Off-Road Vehicles

Abstract

The difficulty of calculating the speed of Four Wheel Drive (4WD) vehicles in off-road terrain is well known, especially at a low speed. This difficulty stems from the common occurrence of wheel slippage because all wheels are driven and the unpaved terrain interacts with the vehicle during driving. To address this issue, this article presents a robust vehicle speed estimation algorithm based on dual attention networks for 4WD off-road vehicles. The algorithm identifies important signals and time in order to capture the interaction between the vehicle and the terrain. Instead of estimating vehicle speed directly, the algorithm estimates wheel slip ratios, which are then used to calculate the vehicle speed, providing interpretability and comprehension of how the vehicle speed is obtained. The effectiveness of the proposed method is demonstrated through real-world driving data collected in various off-road terrains, such as sand, mud, and rock, and verified through comparative studies and real-time estimation. Additionally, the proposed algorithm is capable of estimating vehicle speed without the need for external sensors, reducing costs.