AV Perception Sensor Layout Using Safety-Aware Occupancy Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle (AV) perception systems lack an optimized configuration process that considers safety and risk assessment capabilities, leading to inefficiencies in sensor placement and performance.
Innovation Solution
A system and method for optimizing AV perception sensor configuration using a Binary Integer Program (BIP) to maximize safety-aware information-gain, considering sensor location, orientation, and type, constrained by sensor capacity, and utilizing ground-truth information to calculate probabilistic occupancy grids and safety-aware metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If perception sensor configuration is optimized using traditional methods, then sensor placement efficiency may be improved, but safety and risk assessment capabilities are not considered
Solution Approach 1:
The patent transforms the sensor configuration optimization problem from a geometric placement problem into a safety-aware optimization problem by changing the evaluation parameters from simple coverage metrics to safety metrics including risk assessment, occupancy probability, and critical event detection capability. This allows simultaneous improvement of placement efficiency and safety assessment capability.
Solution Approach 2:
The patent introduces ground-truth information and simulated sensor data as intermediary elements that enable the evaluation of safety metrics without requiring real-world deployment. This intermediary layer allows optimization of sensor configuration while considering safety and risk assessment capabilities that would be difficult to measure directly.
2Measurement precision
If sensor configuration is optimized for maximum coverage, then perception capability is improved, but computational expense increases
Solution Approach 1:
The patent extracts only the essential safety-relevant information from sensor data by focusing on occupancy probability calculation and critical event detection rather than processing all sensor data for complete environmental understanding. This selective extraction maintains perception capability while reducing computational expense.
Solution Approach 2:
The patent applies partial action by calculating occupancy probability and safety metrics for only the most critical regions and events rather than performing exhaustive analysis of all sensor data. This approach maintains adequate perception capability while significantly reducing computational requirements.
3Ease of manufacture
If sensor placement follows conventional patterns, then installation is simplified, but safety performance is suboptimal
Solution Approach 1:
The patent segments the sensor configuration optimization into discrete evaluable components including individual sensor placement options, occupancy probability calculations for different regions, and critical event scenarios. This segmentation allows systematic evaluation of safety performance for different configuration options while maintaining clear installation guidelines.
Data Source
AI summary
A method, computer-readable media, and computer system for receiving perception sensor input data of an autonomous vehicle, the perception sensor input data corresponding to respective measured location, orientation, and type of each of a plurality of perception sensors of the autonomous vehicle; receiving ground-truth information input data of the autonomous vehicle, the ground-truth information input data corresponding to respective ideal simulated location, ideal orientation, and ideal type of a plurality of perception sensors of the autonomous vehicle; determining, via a processor configured to execute instructions stored in a memory, based on the perception sensor input data and the ground-truth information input data, a safety occupancy of at least one obstacle within an area around the autonomous vehicle; and outputting, via the processor, a safety-aware occupancy signal based on the safety occupancy.