Auto-Encoder Sensor Throttling for Autonomous Vehicle Resource Management

Solution Overview

Problem

Advanced vehicles with autonomous features require substantial processing and memory resources for sensor data, leading to significant power consumption and memory storage challenges, particularly in electric and hybrid vehicles where power efficiency is critical.

Innovation Solution

Implementing an auto-encoder framework to dynamically throttle processing and memory consumption by adjusting the frame rate and resolution of sensor data capture based on context, using machine learning to optimize power consumption and reduce redundant data storage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If sensor data is captured at high frame rate and high resolution to maintain autonomous vehicle control, then measurement precision and reliability are improved, but power consumption and memory usage increase substantially

Engineering Contradiction:

Improvesensor data qualityVSAvoidpower consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent implements dynamic adjustment of sensor frame rates based on real-time driving conditions and context. The system transitions from static high frame rate capture to dynamic variable frame rate capture, adjusting the sampling rate according to environmental complexity, vehicle speed, and autonomous driving mode, thereby reducing power consumption while maintaining necessary measurement precision.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the parameter of frame rate dynamically based on contextual analysis. By monitoring environmental complexity and driving conditions, the system adjusts the sensor data capture rate parameter to optimize the balance between measurement quality and power consumption, implementing parameter adaptation rather than fixed operation.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If sensor data is captured at high frame rate to improve autonomous vehicle control, then reliability is improved, but memory usage and processing capacity requirements increase

Engineering Contradiction:

Improveautonomous vehicle controlVSAvoidmemory usage

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The patent implements dynamic adjustment of sensor frame rates based on real-time driving conditions and context. The system transitions from static high frame rate capture to dynamic variable frame rate capture, adjusting the sampling rate according to environmental complexity, vehicle speed, and autonomous driving mode, thereby reducing power consumption while maintaining necessary measurement precision.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the parameter of frame rate dynamically based on contextual analysis. By monitoring environmental complexity and driving conditions, the system adjusts the sensor data capture rate parameter to optimize the balance between measurement quality and power consumption, implementing parameter adaptation rather than fixed operation.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If road geometry modelling is performed with high detail for 3D map creation, then measurement precision is improved, but processing capacity and memory requirements increase substantially

Engineering Contradiction:

Improveroad geometry modelling accuracyVSAvoidprocessing capacity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies local quality by adjusting the level of detail in road geometry modeling based on the specific characteristics of different road segments. High-detail modeling is applied only where necessary (complex intersections, construction zones, unfamiliar areas), while simpler modeling is used for well-known, straightforward road segments, thereby reducing overall processing requirements while maintaining necessary accuracy.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system dynamically adjusts the complexity of road geometry modeling based on real-time conditions, vehicle location, and map update requirements, transitioning from static high-detail processing to dynamic adaptive processing that optimizes computational resources.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11290326B2Method and apparatus for regulating resource consumption by one or more sensors of a sensor array

Publication Date: 2022.03.29 HERE GLOBAL BV

AI summary

A method is provided for dynamically throttling processing and memory consumption of sensors based on context. Methods may include: receiving first sensor data from a first sensor, where the first sensor data includes data associated with an environment of the sensor; applying an auto-encoder framework to the first sensor data to establish a data difference score between frames of the first sensor data, where a relatively high data difference score corresponds to substantial differences between frames of the first sensor data, and wherein a relatively low data difference score corresponds to insubstantial differences between frames of the first sensor data; reducing a frame rate of data capture of the first sensor in response to the data difference score between frames of the first sensor data being relatively low; capturing first sensor data from the first sensor at the reduced frame rate; and providing for storage of the first sensor data.