Adaptive Sensor Prioritization for Self-Driving Hazard Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in navigating through adverse environmental conditions such as fog, rain, or snow, as existing sensors may impair data accuracy, and increased speed reduces the time to detect hazards, leading to uncomfortable and less enjoyable passenger rides due to frequent braking.

Innovation Solution

A self-driving vehicle equipped with a sensor array and control system that dynamically prioritizes sensor data based on detected conditions, using logic to select and weight sensor data from LIDAR, radar, ultrasonic sensors, and cameras, optimizing performance characteristics for various weather and road conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If sensors are used to detect hazards at higher speeds, then the time to detect hazards is reduced, but the accuracy of sensor data deteriorates in adverse environmental conditions

Engineering Contradiction:
Improvevehicle speedVSAvoidsensor data accuracy
Core Design Contradiction:
SpeedVSMeasurement precision

Solution Approach 1:

The system dynamically adjusts sensor selection and weighting based on detected environmental conditions and vehicle speed. The sensor selection component changes which sensors are prioritized depending on the operating context, making the sensor system adaptive rather than static. This resolves the contradiction by allowing the system to optimize for speed detection at high velocities while maintaining accuracy through conditional sensor switching.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the operational parameters of the sensor system by selectively activating and weighting different sensors based on environmental conditions. In adverse conditions like fog or rain, the system shifts which sensors are prioritized (e.g., radar over LIDAR), effectively changing the sensor configuration parameters to maintain measurement precision across varying speed and environmental conditions.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If sensor data from all sensors is processed equally, then comprehensive hazard detection is achieved, but the system complexity increases

Engineering Contradiction:
Improvehazard detection reliabilityVSAvoidsensor processing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system applies different processing qualities and priorities to different sensors based on local conditions. Rather than treating all sensors uniformly, the sensor selection component assigns different weights and processing levels to individual sensors depending on the detected environmental context. This reduces overall system complexity by selectively processing only the most relevant sensor data for current conditions.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system processes sensor data partially by selecting and prioritizing only the most relevant sensors for current conditions rather than processing all sensor data equally. This partial processing approach maintains hazard detection reliability by focusing computational resources on the most critical and currently most accurate sensors, thereby reducing system complexity.

Inventive Principle:
Principle #16Partial or excessive action

3Reliability

If frequent braking is applied to ensure safety in adverse conditions, then hazard response reliability is improved, but passenger comfort deteriorates

Engineering Contradiction:
Improvehazard response reliabilityVSAvoidpassenger comfort
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system performs preliminary sensor selection and prioritization based on predicted adverse conditions, preparing the optimal sensor configuration before hazards are detected. This allows the system to maintain high hazard response reliability through proactive sensor optimization while enabling smoother, more comfortable braking responses by having sensor data already prepared and weighted appropriately.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses feedback from environmental condition detection to continuously adjust sensor selection and weighting. This feedback loop allows the system to maintain reliability by adapting to actual conditions while optimizing passenger comfort through condition-appropriate sensor prioritization that reduces unnecessary braking events in false or less critical hazard situations.

Inventive Principle:
Principle #23Feedback

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach enhances the accuracy of sensor data, reduces braking events, and provides a more comfortable passenger experience by ensuring reliable navigation and hazard detection across diverse conditions.

Implementation Method 1

A self-driving vehicle equipped with a sensor array and control system that dynamically prioritizes sensor data based on detected conditions, using logic to select and weight sensor data from LIDAR, radar, ultrasonic sensors, and cameras

Methodology Applied
Scientific EffectLIDAR: LIDAR

Implementation Method 2

A self-driving vehicle equipped with a sensor array and control system that dynamically prioritizes sensor data based on detected conditions, using logic to select and weight sensor data from LIDAR, radar, ultrasonic sensors, and cameras

Methodology Applied
Scientific EffectRadar: Radar

Data Source

PatentEP3602220B1Dynamic sensor selection for self-driving vehicles
Publication Date: 2024.04.10 UATC LLC
  • EP3602220B1 patent drawingFigure 1
  • EP3602220B1 patent drawingFigure 2
  • EP3602220B1 patent drawingFigure 3

AI summary

A self-driving vehicle (SDV) can operate by analyzing sensor data to autonomously control acceleration, braking, and steering systems of the SDV along a current route. The SDV includes a number of sensors generating the sensor data and a control system to detect conditions relating to the operation of the SDV, such as vehicle speed and local weather, select a set of sensors based on the detected conditions, and prioritize the sensor data generated from the selected set of sensors to control aspects relating to the operation of the SDV.