Bayesian Target Determination for Vehicle HMI Gestures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Human-machine interaction (HMI) systems face challenges in accurately determining the intended target of a pointing gesture, especially in moving vehicles, due to erratic user input and increased user attention requirements, leading to reduced usability and accuracy.
Innovation Solution
A method and apparatus that determine the three-dimensional location of an object at multiple time intervals, calculate metrics indicative of the intended target using various models, and employ Bayesian reasoning to identify the target, incorporating filtering to smooth trajectories and reduce noise, thereby improving accuracy and reducing user effort.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If pointing gestures are used in moving vehicles, then user interaction with the system is enabled, but erratic and unpredictable perturbations in user input occur resulting in erroneous selections
Solution Approach 1:
The system performs preliminary actions by tracking the pointing object's trajectory through multiple time intervals and using Bayesian reasoning to predict the intended target before the user completes the pointing gesture. This allows the system to anticipate the user's intent and prepare for selection, reducing the impact of perturbations that occur during the gesture.
Solution Approach 2:
The system implements feedback by continuously monitoring the pointing object's location at multiple time intervals and using this information to update the probability distribution of potential targets. The Bayesian reasoning process incorporates this feedback to refine the prediction of the intended target, allowing the system to adapt to the user's actual pointing behavior rather than relying on static models.
2Measurement precision
If traditional target determination methods are used, then the system can identify targets, but user attention and effort are increased
Solution Approach 1:
The system performs preliminary target identification by analyzing the pointing object's trajectory and predicting the intended target before the user completes the gesture. This preliminary action allows the system to present potential targets to the user in advance, reducing the time and attention required for final target confirmation and selection.
Solution Approach 2:
The system provides self-service by automatically tracking the pointing object, calculating trajectories, and determining the most likely intended target without requiring continuous user input or attention. The Bayesian reasoning process autonomously processes the trajectory data and identifies targets, freeing the user from the need to maintain constant focus on the interaction.
3Ease of operation
If pointing gestures are used in moving vehicles, then user interaction is enabled, but an undesirable amount of user attention is tied up
Solution Approach 1:
The system performs self-service by autonomously tracking the pointing object through multiple time intervals and using Bayesian reasoning to determine the intended target without requiring continuous user attention. The system handles the complex trajectory analysis and target identification tasks automatically, enabling interactivity while minimizing the user's attentional burden.
Solution Approach 2:
The system performs preliminary target determination by analyzing the pointing trajectory in advance and identifying potential targets before the user completes the gesture. This preliminary action reduces the duration of required user attention by preparing target options ahead of time, allowing the user to maintain lower levels of attention during the interaction.
Data Source
AI summary
Embodiments of the present invention provide a human-machine interaction method of determining an intended target of an object in relation to a user interface, comprising determining a three-dimensional location of the object at a plurality of time intervals, determining a metric associated with each of a plurality of items of the user interface, the metric indicative of the respective item being the intended target of the object, wherein the metric is determined based upon a model and the location of the object in three dimensions at the plurality of time intervals, and determining, using a Bayesian reasoning process, the intended target from the plurality of items of the user interface based on the metric associated with each of the plurality of items.