Autonomous Driving Object Prioritization for Compute Load Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous vehicle systems inefficiently manage computational resources when classifying and prioritizing objects of interest (AOIs) around the vehicle, leading to excessive processing demands and heat generation, particularly in complex scenarios like traffic intersections or dense traffic areas.
Innovation Solution
Implementing a classification policy that categorizes AOIs based on location and traffic context, assigning different frequencies of attribute updates based on their likelihood of impacting the vehicle's driving operation, thereby optimizing computational resources and reducing processing intensity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the autonomous vehicle analyzes sensor data for all objects around it with equal importance, then the accuracy of attribute determination is maintained, but the computational load and heat generation increase significantly
Solution Approach 1:
The patent applies local quality by differentiating the analysis frequency and computational resources allocated to different objects based on their classification. Critical objects (e.g., emergency vehicles, objects in the same lane) receive high-frequency analysis with full computational resources, while non-critical objects (e.g., objects in distant lanes) receive low-frequency or reduced analysis. This resolves the contradiction by maintaining high measurement precision for critical objects while reducing overall computational load and heat generation through selective resource allocation.
2Productivity
If the autonomous vehicle reduces analysis frequency for non-critical objects, then computational resources are saved, but the detection of potentially important objects may be delayed
Solution Approach 1:
The patent implements dynamics by making the analysis frequency adaptive rather than static. Objects are dynamically reclassified based on changing conditions - for example, an object initially classified as non-critical may be reclassified as critical if it changes lanes, approaches the autonomous vehicle, or if the autonomous vehicle's trajectory changes. This resolves the contradiction by ensuring timely detection of important objects while maintaining computational efficiency through dynamic adjustment of analysis frequency based on real-time conditions.
Data Source
AI summary
An autonomous vehicle can classify and prioritize agent of interest (AOI) objects located around the autonomous vehicle to manage computational resources. An example method performed by an autonomous vehicle includes determining, based on a location of the autonomous vehicle and based on a map, an area in which the autonomous vehicle is operated, determining, based on sensor data received from sensors located on or in the autonomous vehicle, attributes of objects located around the autonomous vehicle, where the attributes include information that describes a status of the objects located around the autonomous vehicle, selecting, based at least on the area, a classification policy that includes a plurality of rules that are associated with a plurality of classifications to classify the objects, and for each of the objects located around the autonomous vehicle: monitoring an object according to a classification of the object based on the classification policy.