Driving Characteristics Estimation for Adaptive Collision Warning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional drive assisting systems often misjudge the timing of rear end collision warnings, leading to either delayed warnings for early brake timers or premature warnings for late brake timers, due to variations in driver behavior and environmental factors.

Innovation Solution

A driving characteristics estimating device and system that calculates index values for operation start times, determines probability density ratios based on these values, and weights them to estimate driver tendencies, thereby improving the accuracy of drive assisting interventions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional drive assisting systems use fixed warning timing based on speed and relative distance, then the system structure remains simple, but the warning timing becomes inaccurate for drivers with different braking habits

Engineering Contradiction:
Improvewarning timing accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by storing multiple pieces of operation information (brake operation timings, steering operation timings, accelerator operation timings) before the actual warning is needed. This historical data is accumulated and processed to calculate average values that represent the driver's typical behavior patterns, enabling accurate warning timing without complex real-time analysis

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by comparing the driver's actual operation timing with the pre-calculated average values. When a situation arises requiring a warning, the system references the stored operation information and average values to determine the appropriate warning timing that matches this specific driver's habits, rather than using fixed timing for all drivers

Inventive Principle:
Principle #23Feedback

2Adaptability or versatility

If the system issues warnings based on average operation timings, then it adapts to individual driver characteristics, but requires storing and processing multiple operation parameters

Engineering Contradiction:
Improvedriver characteristic adaptationVSAvoiddata processing load
Core Design Contradiction:
Adaptability or versatilityVSLoss of information

Solution Approach 1:

The system extracts only the essential operation information needed for warning timing determination. It selectively stores brake operation timings, steering operation timings, and accelerator operation timings from multiple situations, and calculates average values for these specific parameters. This extraction approach captures driver characteristics without unnecessarily processing all possible vehicle data

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs preliminary data collection and averaging during normal driving operations. Multiple pieces of operation information are stored and averaged in advance during routine driving, so that when a warning situation occurs, the pre-processed average values are already available for immediate use, minimizing real-time processing requirements

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS10518782B2Driving characteristics estimating device and drive assisting system
Publication Date: 2019.12.31 TOYOTA JIDOSHA KK
  • US10518782B2 patent drawing
  • US10518782B2 patent drawing
  • US10518782B2 patent drawing

AI summary

To provide an operation start index value calculating unit for calculating index values of operation start times according to operation contents of a driver who drives a vehicle, and a driving characteristics estimating unit for determining ratios of probability densities to total value thereof in respective probability density functions in the calculated index values, based on the respective probability density functions of every state of the operation start times to the index values of the operation start times and on the index values of the operation start times calculated by the operation start index value calculating unit, and for estimating the driving characteristics of the driver by weighting the ratios to the total values of the respective probability densities.