Obstacle Inflation Mapping for Faster Autonomous Path Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current obstacle avoidance systems for autonomous mobile devices (AMDs) are computationally intensive and inefficient, requiring significant resources and time to generate navigation maps, leading to increased latency and potential collisions due to the simplification of the AMD as a single point for path planning.
Innovation Solution
A highly efficient inflation process for generating navigation maps by skipping over cells previously designated as obstacles, using an ordered set of candidate cells to quickly determine and inflate the apparent size of obstacles, reducing computational resources and latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional obstacle avoidance systems process all cells in the occupancy map to generate navigation maps, then complete obstacle detection is achieved, but computational resources and time are excessively consumed
Solution Approach 1:
The patent segments the occupancy map processing into two distinct phases: a fast sampling phase that processes only a subset of cells to identify potential obstacles, and a subsequent refinement phase that processes only the identified obstacle regions. This segmentation allows the system to achieve complete obstacle detection while dramatically reducing the computational time and resources required compared to processing all cells uniformly.
Solution Approach 2:
The patent implements partial action by processing only a sampled subset of cells in the occupancy map during the initial obstacle detection phase. Instead of exhaustively processing every cell, the system performs partial processing on representative samples, identifies obstacle regions, and then focuses computational resources only on those specific regions, thereby reducing overall processing time while maintaining detection completeness.
2Device complexity
If the AMD is simplified as a single point for path planning, then computational complexity is reduced, but collision avoidance accuracy deteriorates
Solution Approach 1:
The patent applies local quality by using different levels of detail in different regions of the navigation space. The AMD is represented as a single point for general path planning in open areas, but the system dynamically expands the representation to include the AMD's full dimensions and footprint when approaching identified obstacle regions. This localized increase in detail maintains collision avoidance accuracy while keeping overall computational complexity manageable.
Solution Approach 2:
The patent implements a dynamic representation of the AMD that transitions between simplified and detailed models based on the operational context. During normal navigation, the AMD is represented as a single point for computational efficiency. When the sampled cell analysis indicates proximity to obstacles, the system dynamically switches to a more detailed geometric representation that accounts for the AMD's physical dimensions, ensuring accurate collision avoidance only when necessary.
3Reliability
If comprehensive path planning considering AMD dimensions is performed, then collision avoidance accuracy is improved, but computational resources and latency increase
Solution Approach 1:
The patent segments the path planning computation into a fast initial phase using sampled cells to identify obstacle regions, and a subsequent detailed phase that applies comprehensive AMD dimension considerations only to those specific obstacle regions. This segmentation enables the system to maintain high navigation map generation speed while achieving accurate collision avoidance where it matters most.
Solution Approach 2:
The patent dynamically changes the level of computational detail based on the operational context. When sampled cell analysis indicates safe navigation conditions, the system uses simplified parameters for fast path planning. When obstacles are detected in sampled regions, the system changes parameters to include detailed AMD dimensional data, thereby optimizing the balance between computational speed and collision avoidance accuracy adaptively.
Data Source
AI summary
An autonomous mobile device (AMD) moves through a physical space without human intervention. Data from sensors on the AMD are used to determine an occupancy map indicative of obstacles and their locations in the physical space. A navigation map is created from the occupancy map by inflating the apparent size of the obstacles indicated by the occupancy map. In one implementation the inflation process dynamically skips some portions of the occupancy map based on the presence of an obstacle and a designated inflation distance. The extent of the inflation is based on a size of the AMD. The navigation map is then used for path planning.