Vehicle Occupancy Grid Fusion With Sensor Conflict Arbitration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle environment mapping techniques face limitations in accurately combining multi-sensor data to create unified occupancy grid maps, particularly in scenarios with conflicting sensor readings, leading to suboptimal obstacle detection and drivable space estimation.
Innovation Solution
A method involving temporal fusion processing of sensor data from multiple sources, followed by data fusion and arbitration to resolve conflicts, resulting in an arbitrated fused occupancy grid map that accurately represents drivable spaces, using adaptive sensor weights and techniques like Bayesian Occupancy Filter and Dempster-Shafer Theory for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional occupancy grid mapping is used with equal sensor weights, then the mapping process is simple, but the accuracy deteriorates in scenarios with conflicting sensor readings
Solution Approach 1:
The patent applies parameter changes by dynamically adjusting sensor weights based on reading consistency rather than using fixed equal weights. The system modifies the weighting parameter (alpha) according to the degree of agreement among sensor readings, thereby improving occupancy grid map accuracy in conflicting scenarios without requiring complex manual calibration
Solution Approach 2:
The patent implements feedback by using sensor reading consistency as a metric to adjust weighting parameters. The system continuously monitors whether sensor readings agree or conflict and feeds this information back into the weighting mechanism, creating a closed-loop system that adapts to varying sensor reliability in different environmental conditions
2Reliability
If adaptive sensor weights are applied to resolve conflicts, then the reliability of occupancy grid maps improves, but the processing complexity increases
Solution Approach 1:
The patent changes the weighting parameter dynamically based on sensor agreement levels. When sensors agree, higher weights are applied to their readings; when they conflict, weights are adjusted to reduce the impact of unreliable sensors. This parameter adaptation improves reliability without requiring complex arbitration logic
Solution Approach 2:
The system performs self-service by automatically detecting sensor conflicts and adjusting weights without external intervention. The arbitration mechanism autonomously evaluates reading consistency and modifies sensor weights accordingly, eliminating the need for manual calibration or complex external control systems
3Measurement precision
If equal sensor weights are used, then the processing is computationally efficient, but the accuracy of obstacle detection deteriorates in complex environments
Solution Approach 1:
The patent applies parameter changes by adjusting sensor weights based on reading consistency rather than using fixed equal weights. This dynamic parameter adjustment improves obstacle detection accuracy in complex environments while maintaining computational efficiency through simple weight modification rather than complex processing algorithms
Data Source
AI summary
A method for vehicle (V) environment mapping, comprising the operations of: receiving a set of input values from a plurality of sensors, applying temporal fusion processing to the set of input values, resulting in a respective set of occupancy grid maps, applying data fusion processing to the set of occupancy grid maps, resulting in at least one fused occupancy grid map, detecting discrepancies by comparing occupancy grid maps in the set of maps, resulting in a set of detected discrepancies, processing the at least one fused occupancy grid map and outputting a fused occupancy grid map of drivable spaces. The processing operation includes the step of performing an arbitration of conflict in the at least one fused occupancy grid map. The compound fused occupancy grid map of drivable spaces is supplied (IA) to a user circuit, such as a drive assistance interface.