Terrain-Aware Step Planning for Legged Robots in Constrained Spaces
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robotic systems face challenges in navigating constrained environments, such as cluttered rooms or staircases, without colliding with obstacles or losing balance.
Innovation Solution
A method for planning a sequence of steps in constrained environments, involving the use of image data from sensors to generate body-obstacle, ground height, and step-obstacle maps, which guide the generation of body and step paths for the robot to navigate safely and efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If real-time navigation and step planning is implemented to avoid obstacles, then collision avoidance and safety are improved, but computational complexity and processing time increase
Solution Approach 1:
The navigation problem is segmented into two independent sub-problems: body path planning (avoiding body obstacles) and step path planning (avoiding step obstacles). This segmentation allows each sub-problem to be solved separately with simplified computations, reducing overall computational complexity while maintaining collision avoidance reliability.
Solution Approach 2:
The system performs preliminary classification of obstacles into body obstacles and step obstacles before path planning. By pre-processing the environment data and categorizing obstacles according to their impact on different robot components, the system prepares structured information that simplifies subsequent path planning computations.
2Measurement precision
If multiple maps (body-obstacle map, ground height map, step-obstacle map) are generated from image data, then navigation accuracy and obstacle avoidance are improved, but data processing time and computational load increase
Solution Approach 1:
The environment mapping process is segmented into three specialized maps: body-obstacle map for body collision avoidance, ground height map for terrain information, and step-obstacle map for step collision avoidance. Each map captures specific environmental features needed for different aspects of navigation, improving overall navigation accuracy while allowing parallel processing of map generation.
Solution Approach 2:
The system transforms three-dimensional point cloud data from image sensors into multiple two-dimensional maps representing different aspects of the environment. This dimensional transformation allows complex 3D spatial information to be processed and stored in simplified 2D formats, reducing computational load while preserving essential navigation information.
3Adaptability or versatility
If the robot navigates through constrained environments with multiple obstacles, then task completion capability is improved, but balance maintenance and stability are compromised
Solution Approach 1:
The path planning is segmented into body path planning that ensures body obstacle avoidance and step path planning that ensures proper foot placement. This segmentation allows independent optimization of body trajectory and leg movements, maintaining balance by ensuring that step placements are carefully planned to support body stability while navigating constrained environments.
Solution Approach 2:
The system applies different planning criteria to different parts of the robot: body path planning focuses on overall navigation and avoiding body obstacles, while step path planning focuses on local foot placement and maintaining balance. This local quality approach allows the body to navigate through constrained environments while each step is carefully planned to maintain stability.
Data Source
AI summary
A method for terrain and constraint planning a step plan includes receiving, at data processing hardware of a robot, image data of an environment about the robot from at least one image sensor. The robot includes a body and legs. The method also includes generating, by the data processing hardware, a body-obstacle map, a ground height map, and a step-obstacle map based on the image data and generating, by the data processing hardware, a body path for movement of the body of the robot while maneuvering in the environment based on the body-obstacle map. The method also includes generating, by the data processing hardware, a step path for the legs of the robot while maneuvering in the environment based on the body path, the body-obstacle map, the ground height map, and the step-obstacle map.