Autonomous Travel Control Using Driver Gaze-Based Safety Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing travel controllers for autonomous vehicles do not adequately ensure that drivers feel safe, as they do not account for the driver's attention to specific driving scenarios, potentially leading to uneasy feelings when unexpected objects or situations arise.
Innovation Solution
A travel controller that uses a processor to detect objects from environmental images, determine the driver's looking direction from face images, and associate identified objects with situation conditions to adjust safety standards, ensuring the driver's comfort by modifying vehicle control parameters based on learned safety conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle strictly follows predetermined safety standards, then collision avoidance is improved, but driver comfort deteriorates due to overly conservative behavior in non-critical situations
Solution Approach 1:
The safety standard is changed dynamically based on driver attention state. When the driver is paying attention (looking at relevant objects), the system maintains stricter safety standards. When the driver is not paying attention, the system relaxes safety standards to avoid unnecessary conservative behavior, thereby improving driver comfort while maintaining collision avoidance capability.
Solution Approach 2:
The system changes the safety standard parameter based on the driver's looking direction and attention state. By detecting whether the driver is looking at objects in the environment, the system adjusts the safety standard to appropriate levels, preventing both excessive conservatism and insufficient safety.
2Ease of operation
If the vehicle relaxes safety standards to improve driver comfort, then driver ease of operation is improved, but collision avoidance reliability deteriorates
Solution Approach 1:
The system uses feedback from the driver's looking direction detection to adjust safety standards. By continuously monitoring whether the driver is paying attention to relevant objects, the system receives feedback about driver awareness and adjusts the safety standard accordingly, ensuring reliability is maintained when needed while allowing comfort improvements when safe.
3Ease of operation
If the system monitors driver looking direction and adjusts safety standards dynamically, then driver comfort is improved, but device complexity increases
Solution Approach 1:
The system uses the driver's looking direction as an intermediary indicator of driver attention state. Instead of directly monitoring complex cognitive states, the system uses the easily detectable looking direction as a mediator to infer whether the driver is paying attention, thereby adjusting safety standards without requiring complex monitoring systems.
Data Source
AI summary
A travel controller detects objects from an environmental image representing surroundings of a vehicle capable of traveling under autonomous driving control satisfying a predetermined safety standard; detects a looking direction of a driver of the vehicle from a face image of the driver; identifies an object in the looking direction of the driver out of the objects; stores the identified object and a situation condition indicating the situation at detection of the identified object in a memory in association with each other when a danger avoidance action performed by the driver is detected during travel of the vehicle; and changes the predetermined safety standard so that the driver can feel safer, in the case where an object stored in the memory is detected during travel of the vehicle under the autonomous driving control and where the situation at detection of the object satisfies the situation condition.