Polar Coordinate Map Filtering for Autonomous Obstacle Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems converting polar coordinate maps to rectangular coordinate maps experience significant reduction in occupancy reliability due to coordinate transformation, leading to inaccurate obstacle detection in obstacle mapping for autonomous systems.
Innovation Solution
An information processing apparatus that acquires a polar coordinate map, performs filtering using distance-dependent filtering windows, and converts the filtered map into a rectangular coordinate space to maintain occupancy reliability, employing filtering and coordinate transformation techniques to suppress occupancy reduction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If coordinate transformation is performed from polar coordinate space to rectangular coordinate space, then the obstacle map can be used for autonomous systems, but the occupancy reliability is significantly reduced
Solution Approach 1:
The patent applies preliminary action by performing filtering on the polar coordinate map before coordinate transformation to rectangular coordinate space. The filtering process uses distance-dependent filtering windows to preserve occupancy information in advance, preventing marked reduction during the subsequent transformation process. This ensures that occupancy reliability is maintained throughout the coordinate system conversion.
2Device complexity
If filtering is performed without distance-dependent filtering windows, then the processing is simpler, but occupancy values are markedly reduced during coordinate transformation
Solution Approach 1:
The patent applies local quality by using distance-dependent filtering windows where the filtering characteristics vary based on the distance from the reference position. Different regions of the polar coordinate map undergo different filtering treatments - closer regions use one filtering approach while farther regions use another. This localized filtering strategy preserves occupancy information effectively without requiring uniformly complex processing across the entire map.
Data Source
AI summary
An information processing apparatus according to an embodiment includes a memory and one or more processors configured to function as a map acquisition unit, a filtering unit and a converting unit. The map acquisition unit acquires a polar coordinate map specifying first occupancy of a target in a polar coordinate space. The filtering unit performs filtering on the polar coordinate map using filtering windows of sizes corresponding to a distance from a reference position. The converting unit converts the filtered polar coordinate map into a rectangular coordinate space.