A Novel Integrated Path Planning and Mode Decision Algorithm for Wheel-Leg Vehicles in Unstructured Environment.

Area of Science:

• Robotics and Autonomous Systems
• Environmental Exploration Technology
• Advanced Navigation

Background:

• Autonomous vehicles are crucial for dangerous, unstructured environments like hills and depressions.
• Traditional wheeled vehicles struggle with terrain passability, limiting their use.
• Wheel-leg vehicles offer superior mobility but require advanced automation for mode selection.

Purpose of the Study:

• To develop an integrated path planning and mode decision algorithm (IPP-MD) for wheel-leg vehicles.
• To enable dynamic and optimal mode selection for enhanced autonomous navigation.
• To overcome limitations of existing algorithms not designed for multimodal vehicle capabilities.

Main Methods:

• Mode decision problem modeled using a Markov Decision Process (MDP).
• Innovative design of state space, action space, and reward function for dynamic mode determination.
• Integration of path planning with mode decision for comprehensive control.

Main Results:

• The proposed IPP-MD algorithm effectively determines the most suitable mode of progression.
• Simulation results show fewer mode-switching occurrences compared to existing methods.
• Demonstrates enhanced exploitation of wheel-leg vehicle multimodal advantages.

Conclusions:

• The IPP-MD algorithm significantly improves autonomous navigation for wheel-leg vehicles in unstructured terrains.
• Dynamic mode selection enhances exploration efficiency and vehicle adaptability.
• This approach unlocks the full potential of wheel-leg vehicles for complex missions.