After the COVID-19 pandemic, leisure activities and cultures have undergone significant transformations. Particularly, there has been an increased demand for outdoor camping. Consequently, the need for capabilities that allow vehicles to navigate not only paved roads but also unpaved and rugged terrains has arisen. In this study, we aim to address this demand by utilizing AI to introduce a 'Stuck Probability Estimation Algorithm' for vehicles on off-road.
To estimate the 'Stuck Probability' of a vehicle, a mathematical model representing vehicle behavior is essential. The behavior of off-road driving vehicles can be characterized in two main aspects: firstly, the harshness of the terrain (how uneven and rugged it is), and secondly, the extent of wheel slip affecting the vehicle's traction.
To achieve this, we constructed two AI learning models to quantify each aspect of vehicle behavior, and integrated them into a single computational meta-model to create the 'Stuck Score Calculation Model.' For this purpose, we used internal vehicle signals as inputs to the AI models.
We conducted 'Stuck Probability Estimation' evaluations while vehicles were driving on selected off-road terrains. The accuracy of the first model, the 'Road Depth Estimation Model,' reached 97.1%, and the second model, the 'Off-road Vehicle Slip Estimation Model,' achieved an MAE of 2.98%. The decision time result of 'Stuck Probability Estimation' using these two models is less than 13.9 seconds (5.5 seconds for sand, 13.9 seconds for pebble road).