ADS Event Buffer Prioritization for Critical Scene Retention
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in efficiently storing and prioritizing valuable operational data in event buffers of autonomous driving systems due to limited buffer resources and the risk of losing important events when the buffer is full.
Innovation Solution
A buffer resources prioritizing system that determines current operational conditions, predicts upcoming scenes, and assigns storage priority scores to events based on their predicted relevance, ensuring valuable events are captured and prioritized for storage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If the event buffer continuously collects all operational data, then the buffer capacity is fully utilized, but important events may be lost when the buffer is full
Solution Approach 1:
The patent applies local quality by assigning different storage priorities to different events based on their importance. Critical events receive higher priority and are guaranteed buffer space, while less important events are stored only when buffer resources are available. This resolves the contradiction by ensuring that important events are never lost (reliability) while still utilizing buffer capacity for storing additional events (quantity).
Solution Approach 2:
The system performs preliminary action by pre-calculating and assigning storage priority scores to different event types before actual storage occurs. This allows the buffer management system to proactively reserve space for high-priority events and make informed decisions about what to store when the buffer is full, preventing loss of critical data while maximizing buffer utilization.
2Quantity of substance
If additional storage devices are used for pertinent storage, then more events can be stored, but product cost increases and equipment degradation occurs from repeated writing
Solution Approach 1:
The patent applies partial action by using the event buffer to store only the most critical events rather than attempting to store all events. By selectively freezing only high-priority events in the buffer, the system achieves adequate storage of pertinent data without requiring additional expensive storage devices, thus resolving the contradiction between storage capacity and product cost.
3Productivity
If the buffer is highly utilized to maximize data collection, then buffer resources are efficiently used, but there is not enough buffer resources to properly log new events
Solution Approach 1:
The system applies dynamics by making the buffer allocation flexible and adaptive. Instead of static allocation, the buffer dynamically adjusts space allocation based on event priority. High-priority events can dynamically expand their buffer space at the expense of lower-priority events, ensuring that the buffer remains efficiently utilized while reliably logging all critical events.
Data Source
AI summary
The present disclosure relates to a method performed by a buffer resources prioritizing system for storage prioritization in an event buffer configured to continuously collect operational data of an Automated Driving System, ADS, of a vehicle. The buffer resources prioritizing system obtains sensor data of one or more sensors onboard the vehicle. The buffer resources prioritizing system further determines, at least partly based on the sensor data, current ADS-related operational conditions at least comprising states of vehicle surroundings and internal states of the vehicle. Moreover, the buffer resources prioritizing system determines an upcoming scene predicted to evolve from the current operational conditions. Furthermore, the buffer resources prioritizing system deduces based on assessment of the predicted scene, a storage priority score thereof reflecting predicted relevance of freezing event data of the predicted scene in the event buffer. The disclosure also relates to a buffer resources prioritizing system.