Prioritizing Roadway Pavement Marking Maintenance Using Lane Keep Assist Sensor Data

Mahlberg, Justin; Sakhare, Rahul Suryakant; Li, Howell; Mathew, Jijo K.; Bullock, Darcy M.; Surnilla, Gopi Chandra

doi:10.3390/s21186014

Cited by 12 publications

(8 citation statements)

References 10 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The objective of this study is to determine if lane width measurements from sensors onboard production vehicles can be used to screen public road networks for sections that have less than prescribed lane widths. Previous studies have found many uses for connected vehicle data, including pavement marking evaluation, traffic signal performance, and crash mitigation through surrogate safety measures and hard braking [ 17 , 18 , 19 , 20 , 21 ]. The benefit of using production vehicle data is that it can be crowdsourced and provide ubiquitous coverage across the state without resource-intensive deployments and data collection.…”

Section: Objectivementioning

confidence: 99%

Measuring Roadway Lane Widths Using Connected Vehicle Sensor Data

Mahlberg

Cheng

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

The United States has over three trillion vehicle miles of travel annually on over four million miles of public roadways, which require regular maintenance. To maintain and improve these facilities, agencies often temporarily close lanes, reconfigure lane geometry, or completely close the road depending on the scope of the construction project. Lane widths of less than 11 feet in construction zones can impact highway capacity and crash rates. Crash data can be used to identify locations where the road geometry could be improved. However, this is a manual process that does not scale well. This paper describes findings for using data from onboard sensors in production vehicles for measuring lane widths. Over 200 miles of roadway on US-52, US-41, and I-65 in Indiana were measured using vehicle sensor data and compared with mobile LiDAR point clouds as ground truth and had a root mean square error of approximately 0.24 feet. The novelty of these results is that vehicle sensors can identify when work zones use lane widths substantially narrower than the 11 foot standard at a network level and can be used to aid in the inspection and verification of construction specification conformity. This information would contribute to the construction inspection performed by agencies in a safer, more efficient way.

show abstract

Section: Objectivementioning

confidence: 99%

Measuring Roadway Lane Widths Using Connected Vehicle Sensor Data

Mahlberg

Cheng

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although exact cause of this excess salt is not clear, this often occurs when the hydraulic driven salt spreader on the truck is not properly calibrated. In addition to being costly, creating unnecessary environmental impact, it also can make viewing the lane lines difficult for both human drivers and advanced driver assistance systems (ADAS) that rely on detecting lane markings [13]. The Ohio Department of Transportation found the accuracy for bed scale sensors embedded on its snowplows varied from 2.2% to 8.4% for calibrated and uncalibrated sensors respectively [14].…”

Section: Motivationmentioning

confidence: 99%

Calibration and Confidence in Snowplow Fleet Operations and Fleet Telematics

Mahlberg¹,

Desai²,

Li³

et al. 2022

JTTs

Self Cite

View full text Add to dashboard Cite

The Indiana Department of Transportation (INDOT) spends approximately $30 to $60 million a year on deicing salt and operates a fleet of 1,000 winter operations trucks distributed among 140 locations. The entire fleet is now instrumented with location telematics, and all new trucks have integrated dash cameras, salt spreader application rate and plow up/plow down integrated into the telematics link. When winter storms occur, they have varying regional impacts and INDOT monitors several data sources including National Weather Service (NWS) live doppler, National Severe Storms Laboratory's (NSSL) Multi-Radar Multi-Sensor (MRMS) products, road weather monitoring stations, and connected vehicles (CV) that provide roadway segment operating speeds. This paper discusses how telematics has been integrated to provide a comprehensive view of conditions, truck asset locations, and material distribution maps. The telematics identified widely varying salt spreader rates for the same calibration settings and equipment in preliminary analysis. A calibration box is developed to allow offload calibration to occur within 10 minutes without weighing or transporting the fleet vehicle. The method is deployed across six districts at INDOT for over 1000 snowplows. A sampling of eight trucks in the fleet found the proposed calibration method reduced salt application on average of 45%. This paper describes a series of telematics dashboards for managing winter operations and details the methods developed for 140 geographically distributed truck units to conduct simple, fast, and effective calibration.

show abstract

“…In August 2020, more than 167 billion passenger car trajectory waypoints were collected across 11 states [3]. Granular information received from individual vehicles have been curated for a variety of applications such as work zone monitoring [4] [5] [6], assessment of winter operations [7] [8], performance at intersections [9] [10] [11] and assessment of roadways in general [3] [12] [13] [14].…”

Section: Introductionmentioning

confidence: 99%

Truck and Passenger Car Connected Vehicle Penetration on Indiana Roadways

Sakhare¹,

Hunter²,

Mukai³

et al. 2022

JTTs

Self Cite

View full text Add to dashboard Cite

Commercially available connected vehicle (CV) probe data has been demonstrated to provide scalable and near-real-time methodologies to evaluate the performance of road networks for various applications. However, one of the major concerns of probe data for agencies is data sampling, particularly during low-volume overnight hours. This paper reports on an evaluation that looked at both connected passenger cars and connected trucks. This study analyzed 40 continuous count stations in Indiana that recorded more than 10.8 million vehicles and more than 13 million trips (3 billion records) from CV data over a 1-week period from May 9 th to 15 th in 2022. The average truck penetration was observed to be 3.4% during overnight hours from 1 AM to 5 AM when the connected passenger car penetration was at the lowest. When both connected trucks and connected car penetration were analyzed, the overall CV penetration was 6.32% on interstates and 5.30% on non-interstate roadways. The paper concludes by recommending that both connected car and connected truck data be used by agencies to increase penetration and reduce the hourly variation in CV penetration. This is particularly important during overnight hours.

show abstract

Prioritizing Roadway Pavement Marking Maintenance Using Lane Keep Assist Sensor Data

Cited by 12 publications

References 10 publications

Measuring Roadway Lane Widths Using Connected Vehicle Sensor Data

Measuring Roadway Lane Widths Using Connected Vehicle Sensor Data

Calibration and Confidence in Snowplow Fleet Operations and Fleet Telematics

Truck and Passenger Car Connected Vehicle Penetration on Indiana Roadways

Contact Info

Product

Resources

About