Autonomous Driving Control Device Learning Driver Intent
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control systems struggle to accurately match autonomous driving mode to a driver's intentions and senses, leading to potential safety and operational inefficiencies.
Innovation Solution
A vehicle control device and method that learns and reflects a driver's operations during autonomous driving mode, using sensors and feedback mechanisms to adjust control parameters and switch between autonomous and manual modes based on driver inputs, ensuring the driving mode aligns with the driver's intentions and environmental conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If control parameters learned in manual driving mode are reflected in autonomous driving mode, then travel characteristics reflecting driver intention are achieved, but the travel state differs between modes causing mismatch with driver senses
Solution Approach 1:
Instead of learning from manual driving mode and applying to autonomous mode, the patent inverts the approach by learning from autonomous driving mode and applying corrections back to autonomous mode. This ensures the learning context matches the application context, resolving the travel state mismatch problem.
Solution Approach 2:
The patent implements feedback by detecting driver operations during autonomous driving mode and using this information to correct control parameters. The feedback loop ensures that learned corrections are continuously applied to improve autonomous driving performance while matching driver expectations.
2Measurement precision
If driver operations are learned during autonomous driving mode, then matching accuracy to driver senses is improved, but system complexity increases
Solution Approach 1:
The autonomous driving control device performs self-learning and self-correction by automatically detecting driver operations and adjusting its own control parameters. This self-service approach reduces the need for external calibration systems and simplifies the overall system architecture.
Solution Approach 2:
The patent changes the parameters being learned from general travel characteristics to specific control parameter corrections. This focused parameter adjustment approach simplifies the learning process while maintaining high accuracy in matching driver senses.
Data Source
AI summary
A vehicle control device includes a travel environment recognition device configured to recognize travel environment, a vehicle travel state detection device, and an autonomous/manual driving mode controller. The autonomous/manual driving mode controller includes a learning correction unit configured to store at least one of a plurality of control parameters indicating the vehicle travel state by operation of the driver in the autonomous driving mode, and to correct the control parameter in the autonomous driving mode according to the stored control parameter. When the stored control parameter is the control parameter changed by an operation by the driver midway in passing or after passing, the learning correction unit is configured to correct the control parameter in the autonomous driving mode so that an acceleration level or the deceleration level is increased midway in passing or after passing.