Terrain-Aware Step Planning for Legged Robot Obstacle Navigation
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, while maintaining speed and efficiency.
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 to avoid obstacles and maintain balance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If real-time navigation and step planning is implemented to avoid obstacles, then collision avoidance capability is improved, but computational complexity and processing time increase
Solution Approach 1:
The navigation problem is divided into separate body path planning and step path planning modules. The body path generator creates a high-level trajectory avoiding obstacles, while the step path generator refines this into specific foot placement commands. This segmentation allows each module to focus on specific aspects of navigation, reducing overall computational complexity while maintaining collision avoidance capability.
Solution Approach 2:
The system pre-generates body paths based on obstacle maps before creating detailed step paths. By establishing the overall navigation route in advance and then refining it into specific steps, the system reduces real-time computational burden while ensuring obstacle avoidance is built into the fundamental path structure.
2Measurement precision
If complex terrain mapping and step planning is performed to navigate constrained environments, then navigation accuracy is improved, but processing speed decreases
Solution Approach 1:
The mapping and planning process is segmented into body path generation (coarse-level navigation) and step path generation (fine-level foot placement). This hierarchical approach allows the system to maintain high navigation accuracy through detailed step planning while improving processing speed by handling coarse navigation separately and less frequently.
Solution Approach 2:
The system generates step paths by adjusting nominal step patterns rather than computing optimal paths from scratch for every movement. This partial action approach maintains navigation accuracy by refining predefined patterns while significantly reducing computational processing time compared to full optimization.
3Reliability
If multiple constraints (body obstacles, step obstacles, balance) are enforced during step planning, then safety and balance are improved, but planning complexity increases
Solution Approach 1:
Different constraints are handled in separate planning stages: body obstacle avoidance is addressed in body path generation, while step obstacle avoidance and balance constraints are enforced in step path generation. This segmentation allows each constraint to be processed with appropriate detail level, reducing overall planning complexity while maintaining safety and balance.
Solution Approach 2:
Body paths are pre-generated to avoid body obstacles before step planning begins. This preliminary action ensures that balance-critical step planning only needs to focus on step-level constraints and balance maintenance, rather than simultaneously handling all constraints, thereby reducing planning complexity.
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.