Occupancy Grid Map Updating With Asynchronous Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional occupancy grid maps in AI applications, such as self-driving vehicles, are inaccurately updated due to the limitations of laser radars, including short range and sparse detection, leading to nondeterministic updates and potential failures when the laser radar malfunctions.
Innovation Solution
A method and apparatus for creating an occupancy grid map using multiple sensors with an asynchronous updating policy, combining environment perception information from various sensors like cameras and laser radars to improve accuracy and timeliness, ensuring continuous and stable map updates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If laser radar is used as the sole sensor for occupancy grid map updates, then the system structure is simple, but the detection precision and reliability deteriorate due to short range and sparse detection
Solution Approach 1:
The patent combines multiple sensors (laser radar, cameras, millimeter-wave radar) into a unified sensor system for occupancy grid map updates. Different sensors complement each other's weaknesses: laser radar provides high precision but short range, cameras provide wide coverage but suffer from lighting conditions, and millimeter-wave radar provides all-weather capability. The fusion of these sensors resolves the contradiction by maintaining simple system architecture while achieving superior detection precision through multi-sensor data integration.
Solution Approach 2:
The patent implements a multi-functional sensor system where each sensor type serves multiple purposes in different operating conditions. The system can switch between or combine sensor modes depending on environmental conditions, making the system universally applicable across various scenarios while maintaining high detection precision without requiring complex specialized hardware for each condition.
2Device complexity
If laser radar is used as the sole sensor, then the device complexity is low, but the reliability deteriorates when the laser radar malfunctions
Solution Approach 1:
The patent implements redundancy by deploying multiple sensor types that can compensate for each other's failures. Before a malfunction occurs, the system is already configured with alternative sensing capabilities. If laser radar fails, the system can rely on camera or millimeter-wave radar data to maintain occupancy grid map updates, thereby cushioning against the reliability deterioration without requiring complex reconfiguration or additional hardware.
3Device complexity
If synchronous updating policy is used with multiple sensors, then the system coordination is simple, but the productivity deteriorates due to waiting for all sensors
Solution Approach 1:
The patent implements a dynamic updating policy where the occupancy grid map can be updated at different rates depending on sensor availability and environmental conditions. Rather than rigidly waiting for all sensors to synchronize, the system dynamically adjusts update frequency based on which sensors are currently providing data, allowing faster updates when possible and slower updates when necessary, thereby maintaining simple coordination logic while significantly improving overall productivity and map update frequency.
4Productivity
If asynchronous updating policy is used with multiple sensors, then the productivity improves with more frequent updates, but the device complexity increases
Solution Approach 1:
The patent manages the complexity of asynchronous updating by implementing dynamic adjustment mechanisms that adapt to current system conditions. The updating policy dynamically determines which sensors to process and when, based on data quality, sensor availability, and computational load. This dynamic approach allows the system to achieve high productivity through frequent updates while keeping coordination complexity manageable through adaptive decision-making rather than rigid complex scheduling.
Data Source
AI summary
The present disclosure provides a method and an apparatus for creating an occupancy grid map, as well as a processing apparatus. The method includes: creating a current occupancy grid map based on a location of the vehicle and a previous occupancy grid map; and determining a current probability that each grid in the current occupancy grid map belongs to each of occupancy categories based on last environment perception information received from the sensors and updating an occupancy category to which each grid in the current occupancy grid map belongs based on the current probability that the grid belongs to each of the occupancy categories, in accordance with an asynchronous updating policy.