Constrained Mobility Mapping With Voxel Updates for Robot Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robotic devices face challenges in navigating constrained environments without colliding with obstacles while maintaining balance and speed, leading to inefficient and arduous movement.
Innovation Solution
The method involves generating voxel maps and spherical depth maps using sensor data to identify obstacles and update the voxel map in real-time, creating body obstacle maps for obstacle avoidance, ground height maps for leg placement, and no-step maps to prevent collisions, all while maintaining balance and fluid movement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If robotic devices navigate constrained environments using traditional methods, then they can avoid obstacles, but their movement becomes inefficient and arduous
Solution Approach 1:
The system performs preliminary actions by generating multiple candidate step plans before execution, evaluating them against constraints, and selecting the optimal plan in advance. This allows the robot to navigate efficiently through constrained environments without making difficult decisions during movement, thereby improving navigation efficiency while maintaining movement smoothness.
Solution Approach 2:
The step planning system is dynamic and adaptive, continuously updating voxel maps with current sensor data, re-evaluating constraints based on changing environmental conditions, and generating new step plans as needed. This dynamic approach enables efficient navigation while adapting to maintain smooth movement throughout the navigation process.
2Measurement precision
If real-time sensor data is processed to update voxel maps, then obstacle detection accuracy improves, but computational complexity increases
Solution Approach 1:
The system segments the environment into discrete voxel units and processes sensor data by updating only the relevant voxel regions that have changed. This segmentation approach maintains high obstacle detection accuracy by precisely tracking environmental changes while reducing computational complexity by avoiding redundant processing of entire maps.
Solution Approach 2:
The system merges historical voxel map data with current sensor data to create updated representations of the environment. By combining previously processed information with new sensor inputs, the system achieves accurate obstacle detection without requiring complete reprocessing of all environmental data, thereby managing computational complexity effectively.
3Adaptability or versatility
If multiple map types are generated for navigation (voxel maps, depth maps, body obstacle maps, ground height maps, no-step maps), then navigation capability improves, but system complexity increases
Solution Approach 1:
The voxel map serves as a universal data structure that supports multiple navigation functions simultaneously. The same voxel map infrastructure is used for generating body obstacle maps, ground height maps, and no-step maps, allowing the system to achieve versatile navigation capability while avoiding the complexity of maintaining separate independent systems for each function.
Solution Approach 2:
The system implements a nested map structure where body obstacle maps, ground height maps, and no-step maps are derived from and nested within the primary voxel map framework. This nesting approach enables comprehensive navigation capability by layering specialized information on top of the fundamental voxel representation, while managing system complexity through a hierarchical organization rather than separate systems.
Data Source
AI summary
A method of constrained mobility mapping includes receiving from at least one sensor of a robot at least one original set of sensor data and a current set of sensor data. Here, each of the at least one original set of sensor data and the current set of sensor data corresponds to an environment about the robot. The method further includes generating a voxel map including a plurality of voxels based on the at least one original set of sensor data. The method also includes generating a spherical depth map based on the current set of sensor data and determining that a change has occurred to an obstacle represented by the voxel map based on a comparison between the voxel map and the spherical depth map. The method additional includes updating the voxel map to reflect the change to the obstacle.