Shared Vehicle Obstacle Data for Beyond-Range Perception
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern vehicles lack an effective method to share obstacle data between vehicles and infrastructure, limiting the awareness of obstacles beyond their sensor range, which can impact safety and efficiency, especially for autonomous vehicles.
Innovation Solution
Implementing a system where vehicles can capture and transmit various types of sensor data, such as LIDAR, RADAR, and camera data, to other vehicles and infrastructure, allowing for the sharing of obstacle information and enhancing perception systems, even beyond their immediate sensor range.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If vehicles rely only on their own sensors to detect obstacles, then the vehicle's sensor system remains simple and independent, but the vehicle's awareness of obstacles is limited to its direct sensor range
Solution Approach 1:
The patent combines sensor data from multiple vehicles and infrastructure sources with the local vehicle's sensor data to create a unified perception system. This merging allows the vehicle to access obstacle information beyond its direct sensor range while distributing the sensing burden across the network, resolving the contradiction between information completeness and system complexity.
Solution Approach 2:
The communication system serves multiple functions: it transmits obstacle data between vehicles, receives infrastructure information, and enables collaborative perception. This multi-functionality allows a single communication infrastructure to provide comprehensive obstacle awareness without requiring dedicated specialized systems, balancing information access with system complexity.
2Reliability
If vehicles share sensor data continuously to improve obstacle awareness, then obstacle detection coverage is enhanced, but data transmission bandwidth and processing requirements increase
Solution Approach 1:
The system prioritizes data transmission based on local conditions - vehicles transmit and process sensor data more intensively when obstacles are detected or when operating in environments with poor visibility or high traffic density. This localized intensification improves reliability for critical situations while reducing unnecessary data transmission energy consumption during normal conditions.
Solution Approach 2:
The patent implements selective data sharing where vehicles transmit only relevant obstacle information rather than complete sensor datasets. This partial action approach provides sufficient obstacle detection reliability by sharing only critical safety-related data, significantly reducing the energy required for data transmission and processing compared to continuous full-data sharing.
3Productivity
If autonomous vehicles incorporate data from multiple sources to improve trajectory planning, then safety and efficiency are enhanced, but the complexity of data validation and integration increases
Solution Approach 1:
The system performs preliminary validation and processing of sensor data from external sources before integration into the vehicle's decision-making system. Data is pre-filtered, pre-validated for consistency, and pre-formatted during transmission, which reduces the complexity of real-time data integration and enables more efficient trajectory planning by preparing data in advance.
Solution Approach 2:
The patent introduces an intermediary layer that mediates between raw sensor data from multiple vehicles/infrastructure and the vehicle's trajectory planning system. This intermediary performs data fusion, conflict resolution, and priority management, simplifying the integration process and enabling efficient productivity improvements without directly burdening the core trajectory planning algorithm with complex data validation tasks.
Data Source
AI summary
Systems, methods, and apparatuses described herein are directed to sharing vehicle obstacle data between vehicles and/or between vehicles and a central server. Vehicles may include sensors capturing data including, but not limited to, speed, direction, acceleration, deceleration, LIDAR data, RADAR data, SONAR data, camera data, GPS data, etc. In some implementations, acceleration of a vehicle above a threshold, such as braking or swerving, may trigger the transmission of sensor data to other vehicles and/or infrastructure devices. Vehicles that receive the transmitted data may determine a validity of the data, and may incorporate the data into operations of the receiving vehicle based at least in part on the validity of the data. Validity of the data may be based on sensor type, elapsed time or distance between detection of an obstacle or event and reception of data, a number of retransmissions, duplicative data, independent sources of data, etc.