Behavior Prediction Device with Deviation Reason Estimation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing behavior prediction systems for moving objects around a host vehicle are prone to errors due to inaccurate behavior data, leading to incorrect predictions, and there is a need to determine when data updates are necessary to maintain accurate predictions.

Innovation Solution

A behavior prediction device that includes a moving object behavior detection unit, a behavior prediction model database, a prediction deviation determination unit, a deviation occurrence reason estimation unit, and an update necessity determination unit to assess prediction deviations and determine the necessity of updating the behavior prediction model based on the deviation occurrence reason.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If behavior data is continuously updated to improve prediction accuracy, then prediction reliability is improved, but system complexity and data management burden increase

Engineering Contradiction:
Improveprediction accuracyVSAvoiddata management complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system changes the parameter of data freshness by comparing detection timestamps with current time to determine whether behavior data should be updated. This parameter-based approach allows automatic determination of update necessity without complex manual intervention, resolving the contradiction between maintaining accurate predictions and managing data update complexity.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If behavior prediction model is frequently updated to maintain accuracy, then prediction reliability is improved, but processing time and computational resources increase

Engineering Contradiction:
Improveprediction accuracyVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-calculating and storing behavior data with detection results and timestamps before predictions are needed. When a prediction is required, the system can quickly retrieve and compare pre-processed data without performing complex calculations in real-time, thus maintaining accuracy while reducing processing time.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The behavior prediction system performs self-service by automatically determining whether updates are necessary through timestamp comparison and deviation detection, without requiring external intervention or complex decision-making processes. This automation reduces the time and computational resources needed for model updates.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If strict deviation thresholds are used to detect prediction errors, then measurement precision is improved, but false positive rate increases leading to unnecessary updates

Engineering Contradiction:
Improvedeviation detection accuracyVSAvoidupdate necessity accuracy
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The system uses parameter changes in the form of deviation thresholds that can be adjusted based on the specific prediction context. By allowing the threshold parameter to vary, the system can achieve precise deviation detection while minimizing false positives that would trigger unnecessary updates, thus resolving the contradiction between detection precision and update reliability.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS11498577B2Behavior prediction device
Publication Date: 2022.11.15 TOYOTA JIDOSHA KK
  • US11498577B2 patent drawing
  • US11498577B2 patent drawing
  • US11498577B2 patent drawing

AI summary

A behavior prediction device comprising: a moving object behavior detection unit configured to detect moving object behavior, a behavior prediction model database that stores a behavior prediction model, a behavior prediction calculation unit configured to calculate a behavior prediction of the moving object using the behavior prediction model, a prediction deviation determination unit configured to determine whether a prediction deviation occurs based on the behavior prediction and a detection result of the moving object behavior corresponding to the behavior prediction, a deviation occurrence reason estimation unit configured to estimate a deviation occurrence reason when determination is made that the prediction deviation occurs, and an update necessity determination unit configured to determine a necessity of an update of the behavior prediction model database based on the deviation occurrence reason when the determination is made that the prediction deviation occurs.