Legged Robot Foot Trajectory Control for Complex Terrain Stability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Legged robots struggle with poor terrain adaptability and stability in complex environments, such as quincuncial piles and terrains with gaps, due to limited flexibility in motion control.
Innovation Solution
A legged robot control method utilizing proprioceptive and external perception information, processed by a deep neural network, to adjust trajectory generation parameters of a foot trajectory generator, enhancing motion control flexibility and stability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a foot trajectory generator is used for motion control, then the legged robot can maintain robustness in simple terrains, but the terrain adaptability deteriorates in complex environments
Solution Approach 1:
The patent applies dynamics by making the trajectory generation parameters adjustable and adaptive rather than fixed. The foot trajectory generator dynamically modifies its parameters based on real-time terrain perception information, allowing the system to transition from static robustness to dynamic adaptability across varying terrain conditions.
Solution Approach 2:
The patent implements parameter changes by modifying the trajectory generation parameters based on terrain conditions. The system perceives terrain features and adjusts parameters such as foot placement position, step length, and trajectory shape, enabling the legged robot to adapt to complex terrains while maintaining motion robustness.
2Device complexity
If the legged robot uses fixed motion control parameters, then the control system remains simple, but the flexibility and stability deteriorate in complex terrains
Solution Approach 1:
The patent applies feedback by implementing a closed-loop control system where terrain perception information is continuously fed back to the trajectory generator. This feedback mechanism allows the system to automatically adjust motion parameters based on actual terrain conditions, improving flexibility without requiring complex manual intervention.
Solution Approach 2:
The patent implements self-service by enabling the legged robot to autonomously perceive terrain conditions and adjust its own motion parameters. The system serves itself by integrating perception and control functions, where the robot independently adapts to terrain changes without external assistance, enhancing both flexibility and stability.
3Adaptability or versatility
If the legged robot perceives detailed terrain information, then the terrain adaptability improves, but the information processing complexity increases
Solution Approach 1:
The patent applies extraction by selectively extracting only the essential terrain features needed for motion control from the full set of perceived information. Rather than processing all available terrain data, the system identifies and extracts critical parameters such as terrain height, slope, and surface type, reducing processing complexity while maintaining adaptability.
Solution Approach 2:
The patent implements segmentation by dividing the terrain perception and control process into distinct modules. The terrain perception module separates different terrain features, and the trajectory generator processes each feature type independently, allowing complex terrain information to be handled through modular, manageable segments rather than as a monolithic processing task.
Data Source
AI summary
A legged robot control method performed by a legged robot includes obtaining proprioceptive information and external perception information, the proprioceptive information being configured for characterizing a motion state of the legged robot, and the external perception information being configured for characterizing environment information around the legged robot; inputting the proprioceptive information and the external perception information into a deep neural network, to obtain a first predicted residual outputted by the deep neural network, the first predicted residual being configured for correcting a trajectory generation parameter of a foot trajectory generator; adjusting the trajectory generation parameter of the foot trajectory generator based on the first predicted residual; and controlling the motion state of the legged robot based on a joint motion parameter outputted by the foot trajectory generator after the trajectory generation parameter is adjusted.