Travel Controller Using Driver Action Recognition at Crosswalk Stops
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing travel controllers struggle to determine whether autonomous driving is permissible, particularly when a driver's intention is unclear, such as when a crossing guard is standing near a crosswalk, leading to unnecessary vehicle stops.
Innovation Solution
A travel controller with circuitry configured to execute an action recognizing process, travel permissible information obtaining process, inquiring process, determination process, and autonomous driving permitting process, which uses image data to recognize the driver's actions and requests instructions through a human interface, allowing autonomous driving when the driver's intention to proceed is confirmed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the controller detects a moving object near a crosswalk and stops the vehicle to ensure safety, then safety is improved, but unnecessary stops occur when the object (e.g., crossing guard) does not intend to cross, reducing productivity
Solution Approach 1:
The system continuously monitors the driver's actions through image recognition and uses this feedback to dynamically adjust the autonomous driving permission. When the driver's intention to proceed is detected, the system permits autonomous driving; when uncertainty remains, it maintains caution. This closed-loop feedback mechanism resolves the contradiction by adapting safety measures to actual driver intent rather than applying fixed stopping rules.
Solution Approach 2:
The patent replaces manual driver input operations with an automated image recognition system that detects driver actions (steering wheel manipulation, pedal operation) to determine driving intention. This substitution eliminates the need for explicit manual commands while accurately capturing the driver's intent, allowing the system to distinguish between cautious monitoring and actual proceeding intention, thereby reducing unnecessary stops.
2Measurement precision
If the controller requires manual input operations from the driver to confirm intention, then determination accuracy is improved, but ease of operation deteriorates as the driver must perform additional manual actions
Solution Approach 1:
The system performs self-service by automatically detecting and interpreting the driver's natural actions through image recognition without requiring the driver to perform separate manual input operations. The driver's existing operational actions (steering, accelerating, braking) are automatically analyzed to determine intention, eliminating the need for additional manual confirmation steps while maintaining high determination accuracy.
Solution Approach 2:
The patent substitutes manual input devices and operations with an optical detection system that captures and analyzes the driver's natural physical actions. Instead of requiring the driver to press buttons or make specific manual inputs, the system uses image data to recognize steering wheel manipulation, pedal operation, and other natural driving actions, thereby maintaining measurement precision while dramatically improving ease of operation.
3Reliability
If the controller stops the vehicle when a person is detected near a crosswalk, then safety is improved, but loss of time increases due to unnecessary stops when the person does not intend to cross
Solution Approach 1:
The system uses continuous feedback from image recognition of driver actions to dynamically determine whether to maintain stopping or permit autonomous driving. When the driver's proceeding intention is detected through action analysis, the system promptly permits autonomous driving, minimizing unnecessary stop time while maintaining safety when uncertainty exists. This real-time feedback mechanism eliminates prolonged unnecessary stops.
Solution Approach 2:
The system performs preliminary detection and analysis of the driver's actions while the vehicle is still stopped, before making the decision to proceed. By continuously monitoring and analyzing driver actions during the stopping period, the system can quickly determine intention and minimize the duration of unnecessary stops, thereby reducing time loss while maintaining safety precautions.
Data Source
AI summary
A travel controller recognizes an action of a driver of a vehicle from image data of the driver. The travel controller obtains information indicating that determination of whether autonomous driving of the vehicle is permissible cannot be given. When the information indicating that determination of whether the autonomous driving of the vehicle is permissible cannot be given is obtained, the travel controller operates a human interface to request the driver for an instruction to drive the vehicle. The travel controller determines whether the driver is giving an instruction to drive the vehicle from an action of the driver recognized in response to the request for an instruction to drive the vehicle. When determined in the determination process that the driver is giving an instruction to drive the vehicle, the travel controller operates a drive system of the vehicle to permit autonomous driving of the vehicle.