Personalized Adaptive Cruise Control Steady-State Data Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing personalized adaptive cruise control (ACC) systems face reduced accuracy and unsuitability for real-time online applications due to reliance on vast amounts of raw vehicle trajectory data, which is contaminated with transition state data, leading to slow learning processes and inaccurate representation of driver preferences.
Innovation Solution
The system utilizes only vehicle dynamics data from periods of steady-state operation to train a machine learning model, identifying steady-state periods through manual intervention events and storing relevant data to learn the driver's preferred following gap and vehicle speed relationship, enabling real-time online incremental learning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If vast amounts of raw vehicle trajectory data are used to train the machine learning model, then the model can learn driver preferences, but the learning process becomes slow and accuracy decreases due to contamination with transition state data
Solution Approach 1:
The patent extracts only the useful portion of vehicle trajectory data by identifying and selecting steady-state operation periods, excluding transition state data. This is achieved by detecting steady-state criteria (constant speed, constant following distance, ACC system activated) and using only data from these periods to train the machine learning model, thereby improving both accuracy and learning speed
Solution Approach 2:
The patent applies different quality criteria to different portions of the trajectory data by assigning higher weight to steady-state data and excluding transition state data. The machine learning model is trained selectively on high-quality steady-state portions rather than uniformly processing all raw data, enhancing learning efficiency and accuracy
2Quantity of substance
If raw vehicle trajectory data including transition states is used, then more data is available for training, but the data quality deteriorates leading to inaccurate representation of driver preferences
Solution Approach 1:
The patent extracts only the useful portion of vehicle trajectory data by identifying and selecting steady-state operation periods, excluding transition state data. This is achieved by detecting steady-state criteria (constant speed, constant following distance, ACC system activated) and using only data from these periods to train the machine learning model, thereby improving both accuracy and learning speed
3Adaptability or versatility
If the system continuously learns from all driving data, then the model can be continuously refined, but the system complexity and computational burden increase
Solution Approach 1:
The patent extracts only the useful portion of vehicle trajectory data by identifying and selecting steady-state operation periods, excluding transition state data. This is achieved by detecting steady-state criteria (constant speed, constant following distance, ACC system activated) and using only data from these periods to train the machine learning model, thereby improving both accuracy and learning speed
Solution Approach 2:
The patent performs preliminary filtering and classification of trajectory data into steady-state and transition-state portions before training the machine learning model. By pre-identifying steady-state periods using defined criteria, the system prepares high-quality training data in advance, reducing computational complexity during the actual learning process
Data Source
AI summary
A personalized adaptive cruise control (P-ACC) system and associated algorithm are disclosed for determining a driver's preferred following gap in relation to vehicle speed based on periods of steady-state operation of a vehicle. While the P-ACC system is activated, vehicle transition states initiated by driver manual interventions such as takeover or overwrite events are used to identify subsequent periods of vehicle steady-state operation. Vehicle dynamics data captured during periods of steady-state operation is stored as steady-state data, which is then used to train a machine learning model to learn the driver's preferred following gap. This learned relationship is fed into second-order vehicle dynamics to determine a target acceleration for achieving the desired following gap while the P-ACC system is activated. Upon achieving the desired following gap, the vehicle speed may be held constant to maintain the following gap unless a change in lead vehicle speed necessitates updating the following gap.