Vehicle Control via Gaze and Speech Input
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing complexity of vehicle controls, such as door, window, air conditioner, and multimedia functions, leads to driver distraction due to the need for multiple gaze movements and operations, as users must select and confirm control items through a display, complicating the control process.
Innovation Solution
A vehicle system that combines gaze or speech input with physical operation to determine control items and sub-items, using an eye tracker or speech recognizer to minimize distractions by allowing users to select controls without extensive physical interaction, with a controller that activates corresponding graphic objects and limits the movement direction of a second input device based on the determined control item.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If various control functions are added to the vehicle, then the functionality and information available to the user increases, but the driver's attention is dispersed and the number of operations increases
Solution Approach 1:
The patent replaces manual mechanical operations with voice recognition and gaze tracking systems. The voice recognition device captures and processes spoken commands, while the gaze tracking device uses cameras and image processing to detect eye direction, substituting physical button presses and display interactions with automated detection systems.
Solution Approach 2:
The patent introduces an intermediary selection process where the gaze tracking device first identifies a target control item, then the voice recognition device confirms the selection through voice input. This two-stage intermediary system reduces direct manipulation steps by using gaze as a preliminary selector and voice as a confirmer.
2Measurement precision
If the user selects and confirms control items through display interaction, then precise control is achieved, but the control process becomes complicated and time-consuming
Solution Approach 1:
The gaze tracking device performs preliminary selection of control items by detecting the user's eye direction and identifying the corresponding target on the display or control panel. This preliminary action pre-selects the intended control item before voice confirmation, eliminating the need for manual navigation through display menus.
Solution Approach 2:
The patent extracts the selection function from the display interaction process itself. Instead of requiring users to navigate display menus with physical inputs, the system extracts selection capability by using gaze tracking to automatically identify and pre-select control items based on where the user is looking.
3Ease of operation
If multiple input methods are integrated, then user convenience is improved, but the device complexity increases
Solution Approach 1:
The patent implements multi-functionality by integrating both gaze tracking and voice recognition capabilities within the vehicle's control system. The system can process both visual attention data from cameras and audio data from microphones, allowing users to interact through multiple modalities depending on their needs and driving conditions.
Data Source
AI summary
A vehicle is configured to enable precise control while minimizing distractions during driving and improving user convenience by receiving a user input that combines the user's gaze or speech with a physical operation. The vehicle includes a first input device configured to receive a first user input by at least one of the user's speech or user's gaze; a second input device configured to receive a second user input by the physical operation of the user; and a controller configured to determine a control item corresponding to the first user input among a plurality of control items when the first input device receives the first user input, and to determine a sub-control item for the determined control item based on the second user input when the second input device receives the second user input.