Remote Takeover Control for Autonomous Vehicle Critical Events

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face limitations in detecting and managing critical events on their route, leading to potential errors in piloting actions due to rapid analysis and limited possibilities for sudden changes in direction or braking, especially in unforeseen situations like accidents or adverse weather conditions.

Innovation Solution

A method that involves predictive detection of critical events by a remote control center using combined data from traffic lane conditions, weather, and vehicle sensors, allowing an operator to take temporary remote control of the vehicle to implement optimal steering actions, with a risk assessment algorithm and data weighting to prioritize critical conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If the autonomous driving system performs rapid analysis of the environment using sensors and AI algorithms, then the vehicle can detect and respond to unforeseen situations quickly, but this rapid analysis can lead to misinterpretations and inappropriate driver actions

Engineering Contradiction:
Improveresponse speedVSAvoidaccuracy of event interpretation
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The system performs preliminary detection and classification of events upstream before the vehicle reaches them. By analyzing traffic lane conditions, weather data, and sensor information in advance, the system prepares appropriate piloting actions beforehand, allowing slower but more accurate human-like decision-making rather than forced rapid responses

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary layer between sensor detection and autonomous response by comparing sensor data with pre-acquired reference data from maps and databases. This intermediary verification step helps prevent misinterpretations by cross-checking detected events against known environmental information before triggering autonomous piloting actions

Inventive Principle:
Principle #24Intermediary (Mediator)

2Extent of automation

If the autonomous driving system relies solely on onboard sensors and rapid AI analysis, then the system maintains full automation without human intervention, but the system has limited possibilities for sudden changes in direction or braking when facing critical events

Engineering Contradiction:
Improveautonomous driving capabilityVSAvoidflexibility in piloting actions
Core Design Contradiction:
Extent of automationVSAdaptability or versatility

Solution Approach 1:

The system introduces a remote control center as an intermediary between the autonomous vehicle and human operators. When critical events are detected upstream, the system can transfer control to a human operator who provides flexible, adaptive piloting actions that complement the autonomous system's capabilities

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system dynamically adjusts the level of automation based on the situation. For routine operations, full automation is maintained. When upstream detection identifies critical events requiring complex judgment or sudden maneuvers, the system dynamically transitions to human-operated mode, creating a flexible hybrid control architecture

Inventive Principle:
Principle #15Dynamics

3Loss of time

If the system detects critical events only in the immediate vicinity of the vehicle, then the response time is minimized, but the possibilities for driver intervention are limited and misinterpretations occur more frequently

Engineering Contradiction:
Improvedetection timeVSAvoidaccuracy of event detection
Core Design Contradiction:
Loss of timeVSReliability

Solution Approach 1:

The system performs preliminary detection of critical events upstream along the vehicle's route using traffic lane condition data, weather information, and sensor data from other vehicles. By detecting events before the vehicle reaches them, the system gains both early warning time and the opportunity to verify event accuracy through multiple data sources before triggering responses

Inventive Principle:
Principle #10Preliminary action

4Productivity

If the autonomous driving system makes independent driving decisions in real-world traffic conditions, then the vehicle can operate autonomously without driver intervention, but errors in interpreting critical events can lead to inappropriate piloting actions

Engineering Contradiction:
Improveautonomous operation efficiencyVSAvoidaccuracy of piloting decisions
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system incorporates feedback loops where detected events are cross-validated against reference data from maps and databases before triggering autonomous responses. This feedback mechanism allows the system to verify event authenticity and adjust its interpretation, reducing errors while maintaining autonomous operation

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

By performing preliminary analysis of traffic conditions, weather, and sensor data upstream, the system prepares accurate event interpretations in advance. This preliminary processing reduces the cognitive load during actual response moments and minimizes interpretation errors while maintaining efficient autonomous operation

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3903158B1Method and system for assisting an autonomous motor vehicle
Publication Date: 2023.06.07 VULOG
  • EP3903158B1 patent drawingFigure 1

AI summary

The invention relates to a method for assisting an autonomous motor vehicle, comprising the following steps: - using an autonomous motor vehicle equipped with an automatic driving device which is adapted to decide driving actions to be carried out on said vehicle in order to autonomously circulate said vehicle on a route, - connecting the automatic driving device to a computer server of a remote control center, said connection being produced through a wireless communication network, - determining the geographical position of the vehicle by means of the computer server, characterized in that: - the method comprises a step of predictive detection of a critical event on the route upstream of the geographical position of the vehicle, which detection results in the handgrip of the driving device by an operator of the control center, so that said operator takes temporarily the control of the remote vehicle and decides driving actions, - predictive detection of the critical event resulting from the combined analysis of data by the computer server, which data comprises: - data on the state of the traffic lanes taken on the route upstream of the geographical position of the vehicle, and - data on the road conditions on the route upstream of the geographical position of the vehicle, and - data on the meteorological conditions on the route upstream of the geographical position of the vehicle, and - data coming from sensors installed on the vehicle.