Search Content

Growing traffic on US roadways and heavy construction machinery on road construction sites pose a critical safety threat to construction workers. This report summarizes the design and development of a worker safety system using Dedicated Short Range Communication (DSRC) to specifically address the workers' safety for the workers working around the heavy machinery. The proposed system has dual objectives. First objective is to improve workers' safety by providing visual guidance to the operators of the construction vehicles about the workers' presence in the vicinity. This visual guidance keeps the operators of the heavy machinery well informed about the whereabouts of the workers in close proximity while operating the heavy vehicle. The second objective of the proposed system is to improve the work-zone traffic mobility by dynamically posting suitable speed limits and other warning messages on the DSRC-equipped variable message signs (VMSs) depending on the workers' presence in an active work-zone to appropriately warn the drivers of the passing-by vehicles. A prototype was developed and field tests were conducted to demonstrate and evaluate the performance of the proposed system. The evaluation test results show that the system can successfully show the presence of workers around a construction vehicle on an Android tablet with acceptable distance (1.5 -- 2 m) and direction (15 -- 20 degrees) accuracies. Furthermore, the test results show that a DSRC-equipped VMS can successfully post a suitable speed limit corresponding to the presence of workers in its vicinity.

A lane departure warning system (LDWS) has significant potential to reduce crashes on roads. Most existing commercial LDWSs use some kind of image processing techniques with or without Global Positioning System (GPS) technology and/or high-resolution digital maps to detect unintentional lane departures. However, the performance of such systems is compromised in unfavorable weather or road conditions, e.g., fog, snow, or irregular road markings. Previously, we proposed and developed an LDWS using a standard GPS receiver without any high-resolution digital maps. The previously developed LDWS relies on a road reference heading (RRH) of a given road extracted from an open-source, low-resolution mapping database to detect an unintentional lane departure. This method can detect true lane departures accurately but occasionally gives false alarms, i.e., it can issue lane departure warnings even when a vehicle is within its lane. The false alarms occur due to the inaccuracy of how the RRH originated from an inherent lateral error in open-source, low-resolution maps. To overcome this problem, we proposed and developed a novel algorithm to generate an accurate RRH for a given road using a vehicle's past trajectories on that road. The newly developed algorithm that generates an accurate RRH for any given road has been integrated with the previously developed LDWS and extensively evaluated in the field for detection of unintentional lane departures. The field test results showed that the newly developed RRH Generation algorithm significantly improved the performance of the previously developed LDWS by accurately detecting all true lane departures while practically reducing the frequency of false alarms to zero.

A Lane-Departure Warning System (LDWS) and Advance Curve-Warning System (ACWS) are critical among several Advanced Driver-Assistance Systems (ADAS) functions; having significant potential to reduce crashes. Generally; LDWS use different image processing or optical scanning techniques to detect a lane departure. Such LDWS have some limitations such as harsh weather or irregular lane markings can influence their performance. Other LDWS use a GPS receiver with access to digital maps with lane-level resolution to improve the system's efficiency but make the overall system more complex and expensive. In this report; a lane-departure detection method is proposed; which uses a standard GPS receiver to determine the lateral shift of a vehicle by comparing a vehicle's trajectory to a reference road direction without the need of any digital maps with lane-level resolution. This method only needs road-level information from a standard digital mapping database. Furthermore; the system estimates the road curvature and provides advisory speed for a given curve simultaneously. The field test results show that the proposed system can detect a true lane departure with an accuracy of almost 100%. Although no true lane departure was left undetected; occasional false lane departures were detected about 10% of the time when the vehicle did not actually depart its lane. Furthermore; system always issues the curve warning with an advisory speed at a safe distance well ahead of time.

Unintentional lane departure is a significant safety risk. Currently, available commercial lane departure warning systems use vision-based or GPS technology with lane-level resolution. These techniques have their own performance limitations in poor weather conditions. We have previously developed a lane departure detection (LDD) algorithm using standard GPS technology. Our algorithm acquires the trajectory of a moving vehicle in real-time from a standard GPS receiver and compares it with a road reference heading (RRH) to detect any potential lane departure. The necessary RRH is obtained from one or more past trajectories using our RRH generation algorithm. This approach has a significant limitation due to its dependency on past trajectories. To overcome this limitation, we have integrated Google routes in addition to past trajectories to extract the RRH of any given road. This advancement has been incorporated into a newly developed smartphone app, which now combines our previously developed LDD algorithm with the enhanced RRH generation algorithm. The app effectively detects lane departures and provides real-time audible warnings to drivers. Additionally, we have designed the app's database structure and completed the programming of the necessary algorithms. To evaluate the performance of the newly developed smartphone app, we perform many field tests on a freeway. Our field test results show that our smartphone app can accurately detect all lane departures on long straight sections of the freeway irrespective of whether the RRH is generated from a Google route or past trajectory.