Wheel-legged robot steering control method, device, equipment and storage medium
By acquiring environmental perception information and current state information, and using a target reinforcement learning network to select an appropriate steering mode, the problem of balancing efficiency and stability in the steering control of wheeled robots is solved. This enables efficient and stable steering in different terrains, improving the robot's maneuverability and environmental adaptability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN XUANJI POWER TECHNOLOGY CO LTD
- Filing Date
- 2026-01-20
- Publication Date
- 2026-06-05
AI Technical Summary
In existing wheeled robot steering control methods, the robot can only switch between two modes by relying on fixed preset rules, and cannot make flexible adjustments according to dynamic changes in the environment. This makes it difficult to balance efficiency and stability, thus limiting its ability to be applied in multiple scenarios.
By acquiring environmental perception information and the current state information of the wheeled robot, a target reinforcement learning network is used to determine the terrain complexity index. Based on the pattern interpolation control variable, wheeled differential steering, leg-lifting steering, or hybrid steering mode is selected to achieve intelligent switching of steering mode and ensure efficient and stable steering control under different terrains.
It realizes universal steering control for wheeled robots in various terrains, improves the robot's mobility and environmental adaptability, and balances high efficiency on flat terrain and stability on complex terrain, avoiding the problem of difficulty in balancing efficiency and stability in the traditional single steering mode.
Smart Images

Figure CN122151619A_ABST