Occupancy Map Path Planning for Small Moving Objects
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Small moving objects with insufficient hardware resources face challenges in processing high-precision map information and generating paths in real-time due to high processing loads, especially when precise maps are not available in their travel regions.
Innovation Solution
A moving object control system that acquires and processes images to detect obstacles, generates an occupancy map, and uses a cost-based path generation algorithm to create a global path from a current to a target position, considering costs based on distance from the current position, target position, and past path, thereby avoiding obstacles without relying on high-precision maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high-precision map information is used for path planning, then path accuracy is improved, but processing load and hardware resource requirements increase
Solution Approach 1:
The patent divides the environment into discrete grid cells and represents obstacles using occupancy maps with discrete probability values. This segmentation transforms continuous spatial information into discrete, manageable units that can be processed with limited hardware resources while maintaining sufficient path planning accuracy.
Solution Approach 2:
The patent uses lightweight occupancy maps that are continuously updated based on sensor data rather than relying on heavy, pre-stored high-precision maps. These occupancy maps are computationally inexpensive to generate and update, enabling real-time path planning without requiring substantial hardware resources for map storage and processing.
2Reliability
If a wide search range is used in cost function-based path optimization, then obstacle avoidance capability is improved, but processing amount increases
Solution Approach 1:
The patent applies different cost values to different grid cells based on local conditions such as obstacle occupancy probabilities and distances to start and goal positions. This local differentiation allows the algorithm to focus computational effort on critical areas while using simplified calculations in less critical regions, balancing obstacle avoidance capability with processing efficiency.
Solution Approach 2:
The patent pre-calculates distance metrics and occupancy probabilities for all grid cells before performing path optimization. This preliminary processing organizes the data in a way that enables efficient real-time path planning without requiring extensive computational resources during the actual path generation process.
Data Source
AI summary
The present invention directs to a moving object control system comprising acquiring a captured image; detecting an obstacle included in the captured image; dividing a region around a moving object and generate an occupancy map indicating occupancy of the obstacle detected for each of divided regions; and generating a global path from a current position to a target position for avoiding the detected obstacle based on a first cost, a second cost, and a third cost, the first cost being higher as a distance from the current position is longer on the occupancy map, the second cost being higher as a distance from the target position is longer on the occupancy map, and the third cost being higher as a distance from a past path is longer on the occupancy map.