Automated Driving System Driver Intent Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Automated driving systems often frustrate drivers by incorrectly determining control, either taking over when the driver intends to control the vehicle or failing to take control when the driver is not actively engaged, due to inaccuracies in single sensor inputs.

Innovation Solution

The system uses a combination of sensor signals from multiple sensors, such as torque and hold sensors, to accurately determine driver intent, managing transitions between operating states to prevent incorrect control handovers and ensure safe driving features.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If single sensor input is used to determine driver intent, then device complexity is reduced, but measurement precision deteriorates leading to incorrect control decisions

Engineering Contradiction:
Improvesensor system complexityVSAvoiddriver intent determination accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent combines multiple sensor inputs (torque sensor, hold sensor, and potentially other sensors) to determine driver intent. By merging the data from these different sensors, the system achieves more accurate measurement of driver intent while maintaining reasonable system complexity through integrated processing.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The control system is designed to handle multiple sensor types and process their inputs universally through a single control module. This multi-functional approach allows the same system to process various sensor signals (torque, hold, and other potential sensors) to determine driver intent across different operating conditions.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Extent of automation

If automated driving system takes control based on inaccurate sensor interpretation, then automation extent increases, but reliability deteriorates due to incorrect control handovers

Engineering Contradiction:
Improveautomated control engagementVSAvoidcontrol handover accuracy
Core Design Contradiction:
Extent of automationVSReliability

Solution Approach 1:

The system continuously monitors sensor inputs and adjusts control decisions based on real-time feedback from multiple sensors. By monitoring torque sensor signals, hold sensor signals, and other sensor data, the system can detect when the driver intends to take control and adjust automation engagement accordingly, improving the reliability of control handovers.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system uses sensor signals to predict driver intent before actual control actions are taken. By analyzing torque sensor and hold sensor signals in advance, the system can prepare for upcoming control handovers, ensuring smoother and more reliable transitions between automated and manual control modes.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS10046793B2Methods and systems for automated driving
Publication Date: 2018.08.14 GM GLOBAL TECHNOLOGY OPERATIONS LLC
  • US10046793B2 patent drawing
  • US10046793B2 patent drawing
  • US10046793B2 patent drawing

AI summary

Methods and systems for controlling a driving feature for an automated driving system are provided. In one embodiment, a method includes: receiving a first sensor signal from a first sensor; receiving a second sensor signal from a second sensor; selectively determining a driver intent based on at least one of the first sensor signal and the second sensor signal; and controlling the driving feature based on the driver intent.