Occupancy Grid Map Blending for Vehicle Environment Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle traveling environment recognition systems face inaccuracies due to reliance on map data, which is less accurate than real-time detection by cameras or radar devices, leading to deviations in spatial positioning and suboptimal vehicle control.
Innovation Solution
A traveling environment recognition device that determines the vehicle's position and direction in an absolute coordinate system using sensors, generates an occupancy grid map by calculating and blending occupancy probabilities from radar, communication, and map data using Bayesian inference, enhancing accuracy and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If map data is used to determine traveling environment, then coverage area is extended, but measurement precision deteriorates
Solution Approach 1:
The patent merges multiple information sources (radar detection results, communication device data, and map data) into a unified occupancy grid map. Each source contributes to calculating occupancy probabilities for different cells, combining the wide coverage of map data with the high precision of radar and communication data through probabilistic blending.
Solution Approach 2:
The patent transforms map data from a static, low-precision source into a probabilistic representation within the occupancy grid framework. By converting map-based spatial information into occupancy probabilities and blending them with sensor-based probabilities, the system changes the parameter representation to achieve both coverage and precision.
2Measurement precision
If multiple detection sources are combined, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The occupancy grid map serves as an intermediary data structure that standardizes and integrates information from multiple detection sources (radar, communication devices, map data). By converting all inputs into occupancy probabilities for grid cells, the system provides a unified interface that simplifies the integration complexity while maintaining high measurement precision.
Solution Approach 2:
The patent changes the representation parameters of each detection source into a common probabilistic framework. Radar detection results, communication device positional information, and map data are all transformed into occupancy probabilities for corresponding grid cells, enabling straightforward blending through parameter normalization rather than complex multi-source integration.
3Loss of information
If map data is used in combination with detection results, then information completeness is improved, but reliability deteriorates due to deviation from actual spatial position
Solution Approach 1:
The patent transforms map data from a deterministic spatial representation into a probabilistic occupancy representation. By expressing map-based spatial information as occupancy probabilities rather than fixed coordinates, the system maintains information completeness while reducing the negative impact of map data inaccuracies through probabilistic blending with sensor-based detection results.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The device provides a more accurate representation of the traveling environment by blending occupancy probabilities from multiple sources, improving vehicle control systems like Adaptive Cruise Control and Pre-Crash Safety by minimizing the influence of less accurate map data and enhancing collision avoidance capabilities.
Implementation Method 1
information from a radar device that detects a forward object of the own vehicle
Implementation Method 2
information from a communication device that receives positional information transmitted from another vehicle around the own vehicle
Data Source
AI summary
A traveling environment recognition device capable of accurately recognizing a traveling environment of a vehicle. An occupancy grid map that stores an occupancy probability of each obstacle to traveling of the own vehicle for each cell of the occupancy grid map is generated, and the occupancy probability for each cell is updated according to Bayesian inference. More specifically, for each cell of the occupancy grid map, the occupancy probability calculated from information from a radar device, the occupancy probability calculated from information from a communication device, and the occupancy probability calculated from information from a storage device that stores map data are blended to provide an occupancy probability of the obstacles to traveling of the own vehicle, which leads to more accurate traveling environment recognition.