In-Vehicle Voice Control Using Gaze and Risk-Based Wake Word Omission
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional voice-operated electronic device technologies, such as in vehicles, risk impairing driving safety when drivers omit wake words to operate in-vehicle devices, leading to insufficient attention to the road ahead, especially in high-risk situations.
Innovation Solution
An information processing apparatus with a line-of-sight acquisition unit, voice acquisition unit, operation reception unit, and risk level calculation unit that allows operation instruction reception without a wake word if the driver maintains gaze on a predetermined range and within a safe threshold, disabling the function in high-risk scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the wake word omission function is enabled to allow voice operation without wake words, then ease of operation is improved, but driving safety deteriorates due to insufficient driver attention to the road
Solution Approach 1:
The system dynamically adjusts the wake word omission function based on real-time driving conditions. When the vehicle is stationary or moving at low speeds, the function is enabled to improve ease of operation. When the vehicle exceeds a threshold speed, the function is disabled to ensure driving safety. This dynamic adaptation resolves the contradiction by making the system flexible rather than fixed.
Solution Approach 2:
The system changes the operational parameter (wake word requirement) based on the vehicle's speed parameter. By monitoring speed as a control parameter, the system switches between two operational modes: requiring wake words at high speeds for safety, and allowing wake word omission at low speeds for convenience. This parameter-based control resolves the contradiction between ease of operation and driving safety.
2Reliability
If the wake word omission function is disabled to ensure driving safety, then driving safety is improved, but ease of operation deteriorates due to mandatory wake word utterance
Solution Approach 1:
The system dynamically switches between requiring and not requiring wake words based on vehicle speed. At low speeds, the system is more lenient and allows wake word omission for easier operation. At high speeds, the system becomes stricter and requires wake words to ensure safety. This dynamic behavior resolves the contradiction by adapting the operational strictness to the driving context.
Solution Approach 2:
The system uses vehicle speed as a threshold parameter to change the operational mode. When speed is below the threshold, wake word omission is permitted for ease of operation. When speed exceeds the threshold, wake word requirement is enforced for safety. This parameter-driven mode switching resolves the contradiction between safety and ease of operation.
3Reliability
If the system continuously monitors driver line of sight and vehicle speed to control wake word omission, then driving safety is improved, but device complexity increases
Solution Approach 1:
The system uses a speed threshold parameter that serves multiple functions: it determines when to enable/disable wake word omission, it simplifies the control logic, and it provides a clear, objective criterion for safety assessment. This universal parameter approach reduces complexity while maintaining safety effectiveness.
Solution Approach 2:
The system monitors multiple parameters (speed, line of sight) but uses a simple speed threshold as the primary control parameter. This simplifies the decision-making process and reduces computational complexity while still effectively ensuring driving safety. The parameter-based approach balances safety requirements with system simplicity.
Data Source
AI summary
An information processing apparatus according to the present disclosure includes: a line-of-sight acquisition unit that acquires line-of-sight information of a driver from a line-of-sight detection unit that detects a line of sight of the driver; a voice acquisition unit that acquires voice information of the driver from a sound collection unit; an operation reception unit; and a risk level calculation unit. The operation reception unit receives an operation instruction uttered by the driver when a predetermined wake word is included in a voice of the driver. The risk level calculation unit calculates a risk level of a vehicle driven by the driver and the surroundings of the vehicle. The operation reception unit has a wake word omission function of receiving the operation instruction uttered by the driver even if the wake word is not included in the voice of the driver while the driver continuously views a predetermined range in the vehicle, and disables the wake word omission function when the risk level calculated by the risk level calculation unit is equal to or higher than a predetermined threshold.