Vehicle Occupancy Grid Mapping With Adaptive Sensor Arbitration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle environment mapping techniques using multi-sensor data fusion struggle with accurately combining information from diverse sensors, leading to conflicts and uncertainties in obstacle detection and drivable space estimation, particularly in dynamic environments.
Innovation Solution
The method employs adaptive sensor weights and arbitration stages to iteratively refine fused occupancy grid maps, using Bayesian Occupancy Filter and Dempster-Shafer Theory for data fusion, and conflict resolution to harmonize sensor data, ensuring accurate obstacle detection and path planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If traditional equal-weight sensor fusion is used, then the system is simple to implement, but the accuracy of obstacle detection and drivable space estimation deteriorates in dynamic environments
Solution Approach 1:
The patent applies dynamics by transitioning from static equal-weight sensor fusion to dynamic adaptive weight assignment. The system continuously adjusts sensor weights based on real-time environmental conditions, sensor performance metrics, and data quality assessments, allowing the fusion algorithm to adapt to changing driving scenarios and maintain high detection accuracy across diverse conditions.
Solution Approach 2:
The patent implements parameter changes by modifying the weight parameters assigned to different sensors based on their performance characteristics and environmental suitability. The system dynamically adjusts these parameters using arbitration mechanisms that evaluate sensor reliability, leading to optimized fusion results that balance simplicity with improved measurement precision.
2Reliability
If multiple sensors are fused to improve mapping accuracy, then the reliability of obstacle detection improves, but conflicts and uncertainties in sensor data increase
Solution Approach 1:
The patent introduces an arbitration mechanism as an intermediary layer between individual sensor inputs and the final fused occupancy grid map. This arbitration stage resolves conflicts between contradictory sensor readings by evaluating data quality metrics and sensor reliability, thereby managing the complexity of multi-sensor fusion while maintaining high detection reliability through systematic conflict resolution.
3Measurement precision
If adaptive sensor weights are applied to resolve sensor conflicts, then the accuracy of fused grid maps improves, but the computational complexity increases
Solution Approach 1:
The patent applies partial action by implementing adaptive weight adjustment only for sensors exhibiting conflicts or uncertainties, rather than continuously optimizing all sensor weights. The arbitration mechanism selectively applies computational resources to resolve specific conflicts in the fused grid map, thereby improving accuracy while limiting the increase in computational complexity to only when and where needed.
Data Source
Figure 1
Figure 2~3
Figure 4a1~4b4
AI summary
A method (1000) for vehicle (V) environment mapping, comprising the operations of: - receiving (1010) a set of input values from a plurality of sensors, - applying (1030) temporal fusion processing to the set of input values, resulting in a respective set of occupancy grid maps, applying (1040, 1050, 1060) data fusion processing to the set of occupancy grid maps, resulting in at least one fused occupancy grid map, characterized in that it comprises: detecting (1070) discrepancies by comparing occupancy grid maps in the set of maps, resulting in a set of detected discrepancies, processing (1090) the at least one fused occupancy grid map, outputting a fused occupancy grid map of drivable spaces, the processing operation comprising performing an arbitration (1090a, 1090b) of conflict in the at least one fused occupancy grid map. The compound fused occupancy grid map of drivable spaces is supplied (IA) to user circuit, such as a drive assistance interface.