
Sensors, Journal Year: 2025, Volume and Issue: 25(9), P. 2888 - 2888
Published: May 3, 2025
Human exploration and rescue in unstructured environments including hill terrain depression are fraught with danger difficulty, making autonomous vehicles a promising alternative these areas. In flat terrain, traditional wheeled demonstrate excellent maneuverability; however, their passability is limited terrains due to the constraints of chassis drivetrain. Considering high efficiency, wheel–leg have garnered increasing attention recent years. automation process vehicles, planning mode decisions crucial components. However, current path decision algorithms mostly designed for cannot determine when adopt which mode, thus limiting full exploitation multimodal advantages vehicles. To address this issue, paper proposes an integrated algorithm (IPP-MD) environments, modeling problem using Markov Decision Process (MDP). The state space, action reward function innovatively dynamically most suitable progression, fully utilizing potential movement. simulation results show that proposed method demonstrates significant terms fewer mode-switching occurrences compared existing methods.
Language: Английский