Autonomous Vehicle Control Combining AI and Rule-Based Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic driving technologies rely on machine learning and artificial intelligence for vehicle control, which can fail to predict accurately, leading to safety concerns and difficulties in ensuring compliance with traffic rules and driving morals.
Innovation Solution
An automatic driving device that combines a dynamically changing algorithm using machine learning or artificial intelligence with a prescribed algorithm based on traffic rules and driving morals, ensuring safety and compliance by dynamically adjusting vehicle control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If machine learning or artificial intelligence is used for vehicle control, then adaptability and natural automatic driving are improved, but reliability deteriorates due to prediction failures
Solution Approach 1:
The patent combines machine learning algorithms with prescribed algorithms (traffic rules and driving morals) into a unified control system. The ECU executes both types of algorithms simultaneously, allowing the system to leverage the adaptability of machine learning while maintaining the reliability of rule-based control, thereby resolving the contradiction between adaptability and reliability
Solution Approach 2:
The patent applies different algorithm types to different control aspects: machine learning is used for aspects requiring adaptability and natural driving behavior, while prescribed algorithms are used for safety-critical and rule-based aspects. This localized application of different algorithm qualities ensures reliability where needed while maintaining adaptability where beneficial
2Reliability
If prescribed algorithm is used for vehicle control, then reliability is improved, but adaptability deteriorates
Solution Approach 1:
The system merges prescribed algorithms with machine learning algorithms, allowing the prescribed algorithm to ensure reliability through rule-based control while the machine learning component provides adaptability for natural and flexible driving behavior, resolving the contradiction between reliability and adaptability
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Achieving safety and natural automatic driving needs a control platform using intelligence (such as learning function and artificial intelligence), but it is difficult to ensure operations suited for the behavior of a vehicle by the output of intelligence. An automatic driving device according to the present invention includes a control program for inputting outside information and vehicle information, and outputting a target control value for a vehicle. The control program has a first program for generating a first target control amount on the basis of a dynamically changing algorithm (which outputs operations based on learning function or artificial intelligence), and a second program for generating a second target control amount on the basis of a prescribed algorithm (which outputs operations according to traffic rules or driving morals).