Predictive Comfort Model for Autonomous Vehicle Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous and semi-autonomous vehicles lack the ability to account for individual passenger preferences in ride comfort, leading to uncomfortable experiences due to centralized decision-making based on limited designer opinions, which is subjective and cannot adapt to diverse passenger comfort levels.
Innovation Solution
A predictive model is generated to predict the subjective comfort level of passengers by using past vehicle action data, passenger feedback, and environmental data, allowing the vehicle to select actions that optimize comfort based on individual preferences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a centralized approach is used to create vehicle operational decisions based on designer opinions, then the decision-making process is simplified and consistent, but the ride comfort becomes subjective and cannot adapt to diverse passenger preferences
Solution Approach 1:
The system implements feedback loops where passenger comfort evaluations are collected and used to iteratively refine vehicle operational rules. This allows the centralized system to adapt to diverse passenger preferences while maintaining consistent decision-making frameworks through structured feedback integration
Solution Approach 2:
The operational rules are transformed from static designer specifications to dynamic parameters that can be adjusted based on collected passenger feedback. This enables the system to adapt ride comfort parameters while maintaining a centralized decision-making structure
2Reliability
If detailed rules for acceleration and braking are specified to improve ride comfort, then passenger comfort may be enhanced, but the system lacks the ability to account for individual passenger preferences
Solution Approach 1:
The system applies different operational parameters tailored to individual passenger preferences for each ride. By collecting and analyzing individual feedback, the system customizes acceleration and braking profiles to match specific passenger comfort requirements while maintaining overall system reliability
Solution Approach 2:
The system dynamically adjusts operational parameters such as acceleration rates and braking forces based on individual passenger preferences. These parameter changes are made within a structured framework that maintains safety and reliability while accommodating diverse comfort requirements
Data Source
AI summary
In one embodiment, a method by a computing system of a vehicle includes determining an environment of the vehicle. The method includes generating, based on the environment, multiple proposed vehicle actions with associated operational data. The method includes determining a comfort level for each proposed vehicle action by processing the environment and operational data using a model for predicting comfort levels of vehicle actions. The model is trained using records of performed vehicle actions. The record for each performed vehicle action includes environment data, operational data, and a perceived passenger comfort level for the performed vehicle action. The method includes selecting a vehicle action from the proposed vehicle actions based on the determined comfort level. The method includes causing the vehicle to perform the selected vehicle action.