Adaptive Perception Processing Rate Control for Autonomous Vehicles

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing vehicle object detection systems face challenges in maintaining accurate and timely processing of sensor data, leading to potential delays and inefficiencies in autonomous vehicle operations.

Innovation Solution

A perception processing system with a modular architecture, featuring a global controller and local controllers, that dynamically adjusts processing rates across algorithm stages to ensure efficient data processing and adapt to changing resource availability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the processing rate is increased to improve productivity, then the output per unit time increases, but the system reliability deteriorates due to potential processing errors and instability

Engineering Contradiction:

Improveprocessing rateVSAvoidprocessing stability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system dynamically adjusts the processing rate based on real-time feedback from local controllers monitoring algorithm stage performance. The global controller modifies the processing rate within a range determined by minimum and maximum thresholds, allowing the system to adapt between speed and stability requirements according to actual operating conditions

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

Local controllers continuously monitor the processing rate of each algorithm stage and provide feedback to the global controller. This feedback mechanism enables the system to detect when the processing rate is too high (causing instability) or too low (reducing productivity) and adjust accordingly to maintain optimal balance

Inventive Principle:

Principle #23Feedback

2Reliability

If the processing rate is decreased to improve reliability, then the processing stability increases, but the productivity deteriorates due to slower data processing

Engineering Contradiction:

Improveprocessing stabilityVSAvoidprocessing rate

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system allows dynamic adjustment of the processing rate within an optimized range. Rather than fixed low rate, the global controller can increase the rate when conditions permit, maximizing productivity while maintaining stability through real-time monitoring and adjustment based on algorithm stage performance feedback

Inventive Principle:

Principle #15Dynamics

3Adaptability or versatility

If the processing rate is dynamically adjusted to optimize performance, then the system adaptability improves, but the device complexity increases due to additional control mechanisms

Engineering Contradiction:

Improverate adjustment capabilityVSAvoidcontroller structure

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The control system is segmented into hierarchical levels: local controllers that monitor individual algorithm stages and a global controller that coordinates overall processing rate. This segmentation distributes complexity across multiple simple units rather than requiring one complex controller, making the system more adaptable while managing complexity through modular architecture

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The global controller serves multiple functions: it sets the processing rate, receives feedback from local controllers, determines acceptable rate ranges based on minimum and maximum thresholds, and coordinates adjustments across all algorithm stages. This multi-functionality reduces the need for separate dedicated components, managing complexity through versatile control elements

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS12314771B2Perception processing with multi-level adaptive data processing flow rate control

Publication Date: 2025.05.27 GM GLOBAL TECHNOLOGY OPERATIONS LLC

AI summary

A perception processing system includes a memory and a main controller. The main controller includes modules and implements a data processing pipeline including algorithm stages, which are executed in parallel relative to sets of data and are executed sequentially relative to each of the sets of data. The algorithm stages share resources of the modules and the memory to process the sets of data and generate perception information. One of the modules executes global and local controllers. The global controller sets a processing rate for the local controllers. The local controllers monitor current processing rates of the algorithm stages. When one of the current processing rates is less than the set processing rate, the corresponding one of the local controllers sends a first signal to the global controller and in response the global controller sends a broadcast signal to the local controllers to adjust the current processing rates.