Automatic Driving System Dual Plan Reliability

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing automatic driving systems face challenges in continuing safe vehicle control when recognition reliability decreases, leading to difficulties in maintaining automatic driving operations and necessitating timely driver intervention.

Innovation Solution

The system generates two traveling plans: a primary plan using comprehensive recognition data and a secondary plan with reduced reliance on unreliable data, allowing for continued automatic driving control by selecting the plan with higher reliability and minimizing disruptions during driver takeover.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If the system uses comprehensive recognition data to generate the first traveling plan, then the plan quality is improved, but the reliability decreases when recognition accuracy is low

Engineering Contradiction:
Improvetraveling plan qualityVSAvoidautomatic driving control reliability
Core Design Contradiction:
Manufacturing precisionVSReliability

Solution Approach 1:

The system segments the traveling plan generation into two distinct plans: a first traveling plan using comprehensive recognition data for high quality, and a second traveling plan using limited recognition data for high reliability. The system selectively switches between these segmented plans based on recognition accuracy conditions, resolving the contradiction between plan quality and reliability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system changes the parameter of data usage comprehensiveness based on recognition accuracy conditions. When recognition accuracy is high, the system uses comprehensive data (first traveling plan). When recognition accuracy is low, the system switches to using limited data (second traveling plan), thereby maintaining reliability while adapting plan quality to current conditions.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If the system switches to manual control when recognition reliability decreases, then safety is improved, but the time for driver takeover is reduced

Engineering Contradiction:
Improvedriving safetyVSAvoiddriver takeover time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary action by pre-calculating the second traveling plan using limited recognition data before the first traveling plan becomes invalid. This preliminary preparation ensures that when the system switches from automatic to manual control, the driver has adequate time to respond, as the fallback plan is already computed and ready.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system provides beforehand cushioning by maintaining the second traveling plan as a backup option that is computationally simpler and faster to execute. This cushioning mechanism ensures that even when recognition reliability decreases, the system can smoothly transition to manual control with sufficient time, as the fallback plan requires minimal computation.

Inventive Principle:
Principle #11Beforehand cushioning (Prior cushioning)

3Reliability

If the system generates a second traveling plan with reduced data usage, then the reliability is improved, but the plan comprehensiveness is reduced

Engineering Contradiction:
Improvetraveling plan reliabilityVSAvoidrecognition data utilization
Core Design Contradiction:
ReliabilityVSLoss of information

Solution Approach 1:

The system dynamically adjusts the amount of recognition data used for traveling plan generation based on current recognition accuracy conditions. The first traveling plan uses comprehensive data when conditions are favorable, while the second traveling plan uses limited data when conditions are poor. This dynamic adaptation allows the system to maintain reliability by adjusting information usage to match current operational conditions.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS10095227B2Automatic driving system
Publication Date: 2018.10.09 TOYOTA JIDOSHA KK
  • US10095227B2 patent drawing
  • US10095227B2 patent drawing
  • US10095227B2 patent drawing

AI summary

An automatic driving system includes an actuator and an electronic control unit. The electronic control unit is configured to recognize a position, a surrounding environment, a state of the vehicle. The electronic control unit is configured to generate a first traveling plan based on the recognized position, the recognized surrounding environment, and the recognized state of the vehicle and calculate reliability of the first traveling plan. The electronic control unit is configured to generate a second traveling plan of the vehicle based on one or two of the recognized position, the recognized surrounding environment, and the recognized state of the vehicle and calculate reliability of the second traveling plan. The electronic control unit is configured to select a traveling plan having the higher reliability out of the first traveling plan and the second traveling plan, and control the traveling of the vehicle by the actuator.