Sparse Volumetric Path Planning for Low-Latency 3D Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computer vision and augmented or mixed reality systems face challenges in efficiently processing and rendering large volumetric data sets, leading to latency and increased power consumption, which can cause motion sickness and hinder immersive experiences.
Innovation Solution
The implementation of a sparse volumetric data structure, such as a Sparse Sexaquaternary Tree (SST), that allows for the efficient storage and processing of volumetric data by tagging voxels as 'occupied' or 'empty', reducing storage needs and enabling faster processing and transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If dense volumetric data structures are used for accurate 3D representation, then measurement precision is improved, but processing time increases and productivity decreases
Solution Approach 1:
The patent segments the volumetric space into discrete voxels organized in a hierarchical tree structure, allowing the system to process only relevant portions of the volume at each level. This segmentation enables efficient traversal and rendering by dividing the large volumetric dataset into manageable chunks that can be processed independently and in parallel.
Solution Approach 2:
The patent introduces a hierarchical dimension to the traditional 3D volumetric data structure by organizing voxels in a tree structure with multiple levels of abstraction. This additional hierarchical dimension allows the system to quickly navigate and cull irrelevant volumes before detailed processing, effectively adding a time efficiency dimension without sacrificing spatial accuracy.
2Manufacturing precision
If complete volumetric data is transmitted for high-quality rendering, then image quality is improved, but data transmission time and bandwidth consumption increase
Solution Approach 1:
The patent extracts and transmits only the essential hierarchical structure and occupancy information from the complete volumetric dataset. By taking out only the critical structural data needed for reconstruction rather than transmitting the entire dense voxel grid, the system achieves fast transmission while maintaining the ability to reconstruct high-quality images at the receiving end.
Solution Approach 2:
The patent changes the representation parameters of volumetric data by encoding spatial occupancy and hierarchical relationships in a compressed format. Instead of transmitting raw voxel values, the system transmits transformed parameters that describe the spatial structure, which can then be decoded into high-quality volumetric representations at the destination.
3Measurement precision
If high-resolution volumetric maps are maintained for accurate path planning, then measurement precision is improved, but memory consumption and processing power increase
Solution Approach 1:
The patent segments the high-resolution volumetric map into a hierarchical tree structure where only occupied or relevant voxels are explicitly stored at each level. This segmentation allows the system to maintain accurate path planning data for only the necessary portions of the environment, reducing overall memory consumption and processing requirements while preserving measurement precision for path-critical regions.
Solution Approach 2:
The patent implements partial action by maintaining full resolution volumetric detail only in regions that are currently relevant for path planning, while using coarser representations for distant or irrelevant areas. This approach provides sufficient accuracy for navigation decisions without the excessive computational burden of maintaining high resolution throughout the entire volumetric space.
Data Source
AI summary
A view of geometry captured in image data generated by an imaging sensor is compared with a description of the geometry in a volumetric data structure. The volumetric data structure describes the volume at a plurality of levels of detail and includes entries describing voxels defining subvolumes of the volume at multiple levels of detail. The volumetric data structure includes a first entry to describe voxels at a lowest one of the levels of detail and further includes a number of second entries to describe voxels at a higher, second level of detail, the voxels at the second level of detail representing subvolumes of the voxels at the first level of detail. Each of these entries include bits to indicate whether a corresponding one of the voxels is at least partially occupied with the geometry. One or more of these entries are used in the comparison with the image data.