Vehicle Control Processing Split for Safety and Power Balance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control devices face a trade-off between power consumption and safety, as AI-only models provide high safety but high power consumption, while rule-based models offer low power consumption but lower safety, with hybrid models falling in between.
Innovation Solution
A vehicle control device that dynamically adjusts the processing ratio between AI-only and rule-based processing units based on vehicle conditions, including speed, environment complexity, and terrain, to ensure safety while minimizing power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If AI-only model is used for vehicle control, then vehicle safety is improved, but power consumption increases
Solution Approach 1:
The system dynamically switches between AI-only model and rule-based model based on real-time vehicle conditions, environment complexity, and terrain factors. This dynamic adaptation allows the system to use the computationally intensive AI model only when necessary for safety-critical decisions, while relying on lighter rule-based models during normal operations, thus resolving the contradiction between safety and power consumption
Solution Approach 2:
The system changes the processing parameters by adjusting the complexity of the control model based on environmental conditions. When environment complexity or terrain difficulty increases, the system transitions to using the AI-only model with higher computational parameters. When conditions are favorable, it switches to rule-based models with lower computational parameters, thereby optimizing the balance between safety and energy usage
2Use of energy by moving object
If hybrid model is used for vehicle control, then power consumption is reduced compared to AI-only model, but vehicle safety decreases
Solution Approach 1:
The control system is segmented into multiple processing paths: AI-only processing for safety-critical functions, rule-based processing for routine functions, and hybrid processing for intermediate cases. This segmentation allows the system to allocate computational resources efficiently, ensuring that safety-critical operations always use the most reliable AI model while less critical operations can use lighter rule-based models, thus maintaining overall safety while reducing average power consumption
3Use of energy by moving object
If rule-based model is used for vehicle control, then power consumption is minimized, but vehicle safety is reduced
Solution Approach 1:
The system introduces an intermediary decision-making layer that determines when to use rule-based models and when to escalate to AI-only models. This intermediary evaluates environmental complexity, terrain conditions, and vehicle state to mediate between the low-power rule-based approach and the high-safety AI approach, selecting the appropriate processing mode to balance safety and power consumption in real-time
Data Source
AI summary
A vehicle control device has a first processing device that generates an output signal using only a machine learning-trained classifier, a second processing device that has lower power consumption than the first processing device and generates an output signal without using a machine learning-trained classifier, and a processor configured to decide a processing ratio between a portion processed by the first processing device and a portion processed by the second processing device, based on at least one information from among vehicle information representing a state of a vehicle, environment information representing surrounding environment of the vehicle, and terrain information representing a terrain including a current location of the vehicle.