Construction Zone Detection Using Multi-Sensor Fusion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in detecting construction zones on roads, as existing navigation systems may not reflect recent changes due to construction, which can lead to unsafe driving conditions.

Innovation Solution

A computing device receives information from multiple sources, assigns reliability metrics to each source, determines the likelihood of a construction zone's existence, and modifies the vehicle's control strategy to ensure safe navigation through the zone.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If navigation systems rely on pre-stored road map data, then the system structure is simple and easy to operate, but the system cannot detect recent construction zone changes leading to unsafe driving conditions

Engineering Contradiction:
Improvedetection accuracy of construction zonesVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent combines multiple information sources (road map data, image recognition from cameras, LIDAR point cloud data, RADAR signals) into a unified construction zone detection system. This merging of diverse data sources enables reliable detection of construction zones while maintaining system manageability through modular integration of each sensing component.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The computing device acts as an intermediary that receives, processes, and integrates information from multiple sources. It compares detected features against road map data and determines construction zone likelihood, serving as the central mediator that reconciles pre-stored map information with real-time sensor data to improve detection reliability.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If the system uses multiple information sources with reliability metrics, then the detection reliability improves, but the computational complexity and processing time increase

Engineering Contradiction:
Improveconfidence level of construction zone detectionVSAvoidprocessing time for multi-source data integration
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-storing road map data and establishing detection frameworks before actual construction zone detection is needed. This allows the computing device to quickly compare real-time sensor data against pre-prepared reference information, reducing processing time while maintaining high reliability through pre-established evaluation criteria.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements a likelihood determination that can operate with partial information from multiple sources. By assigning reliability metrics to each source and determining construction zone likelihood based on available data quality, the system avoids requiring complete data from all sources, thus reducing processing time while maintaining detection reliability through selective use of the most reliable available information.

Inventive Principle:
Principle #16Partial or excessive action

3Reliability

If the system modifies control strategy based on construction zone detection, then the safety of vehicle navigation improves, but the complexity of control system increases

Engineering Contradiction:
Improvesafety of vehicle navigation through construction zonesVSAvoidcontrol strategy complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The control system dynamically adapts its strategy based on detected construction zone conditions. The computing device modifies control parameters in real-time according to the determined construction zone likelihood, enabling safe navigation through construction zones while maintaining operational simplicity through rule-based dynamic adjustment rather than complex predetermined control sequences.

Inventive Principle:
Principle #15Dynamics

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

The system effectively detects construction zones using a combination of image-based, LIDAR-based, and RADAR-based information, allowing the vehicle to adjust its driving behavior and control strategy to navigate safely through the area.

Implementation Method 1

from a light detection and ranging (LIDAR) sensor coupled to the computing device, LIDAR-based information comprising (i) a three-dimensional (3D) point cloud of a vicinity of a road

Methodology Applied
Scientific EffectLIDAR: LIDAR

Implementation Method 2

from a radio detection and ranging (RADAR) sensor coupled to the computing device, RADAR-based information comprising dimensional characteristics of an object

Methodology Applied
Scientific EffectRADAR: Radar

Data Source

PatentEP2879929B1Construction zone detection using a plurality of information sources
Publication Date: 2016.10.12 WAYMO LLC
  • EP2879929B1 patent drawingFigure 1
  • EP2879929B1 patent drawingFigure 2
  • EP2879929B1 patent drawingFigure 3

AI summary

Methods and systems for detection of a construction zone using information from a plurality of sources are described. In an example, a computing device, configured to control the vehicle, may be configured to receive information, from a plurality of sources, relating to detection of a construction zone on the road on which the vehicle is travelling. Also, the computing device may be configured to determine a likelihood of existence of the construction zone on the road, based on the information. Further the computing device may be configured to modify a control strategy associated with a driving behavior of the vehicle, based on the likelihood; and control the vehicle based on the modified control strategy.