skip to main content


Title: On-Bicycle Vehicle Tracking at Traffic Intersections Using Inexpensive Low-Density Lidar
This paper explores the challenges in developing an inexpensive on-bicycle sensing system to track vehicles at a traffic intersection. In particular, opposing traffic with vehicles that can travel straight or turn left are considered. The estimated vehicle trajectories can be used for collision prevention between bicycles and left-turning vehicles. A compact solid-state 2-D low-density Lidar is mounted at the front of a bicycle to obtain distance measurements from vehicles. Vehicle tracking can be achieved by clustering based approaches for assigning measurement points to individual vehicles, introducing a correction term for position measurement refinement, and by exploiting data association and interacting multiple model Kalman filtering approaches for multi-target tracking. The tracking performance of the developed system is evaluated by both simulation and experimental results. Two types of scenarios that involve straight driving and left turning vehicles are considered. Experimental results show that the developed system can successfully track cars in these scenarios accurately in spite of the low measurement density of the sensor.  more » « less
Award ID(s):
1631133
NSF-PAR ID:
10198604
Author(s) / Creator(s):
;
Date Published:
Journal Name:
2019 American Control Conference
Page Range / eLocation ID:
593 to 598
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. This paper develops an active sensing system for a bicycle to accurately track rear vehicles that can have two-dimensional motion. The active sensing system consists of a single-beam laser sensor mounted on a rotationally controlled platform. The sensing system is inexpensive, small, lightweight, consumes low power, and is thus ideally suited for the bicycle application. The rotational orientation of the laser sensor needs to be actively controlled in real-time in order to continue to focus on a rear vehicle, as the vehicle’s lateral and longitudinal distances change. This tracking problem requires controlling the real-time angular position of the laser sensor without knowing the future trajectory of the vehicle. The challenge is addressed using a novel receding horizon framework for active control and an interacting multiple model framework for estimation. The features and benefits of this active sensing system are illustrated first using simulation results. Then, preliminary experimental results are presented using an instrumented bicycle to show the feasibility of the system in tracking rear vehicles during both straight and turning maneuvers. 
    more » « less
  2. Restricting left turns throughout a network improves overall flow capacity by eliminating conflicts between left-turning and through-moving vehicles. However, doing so requires vehicles to travel longer distances. Implementing left-turn restrictions at only a subset of locations can help balance this tradeoff between increased capacity and longer trips. Unfortunately, identifying exactly where these restrictions should be implemented is a complex problem because of the many configurations that must be considered and interdependencies between left-turn restriction decisions at adjacent intersections. This paper compares three heuristic solution algorithms to identify optimal location of left-turn restrictions at individual intersections in perfect and imperfect grid networks. Scenarios are tested in which restriction decisions are the same for all intersection approaches and only the same for approaches in the same direction. The latter case is particularly complex as it increases the number of potential configurations exponentially. The results suggest all methods tested can be effectively used to solve this problem, although the hybrid method proposed in this paper appears to perform the best under scenarios with larger solution spaces. The proposed framework and procedures can be applied to realistic city networks to identify where left-turn restrictions should be implemented to improve overall network operations. Application of these methods to square grid networks under uniform demand patterns reveal a general pattern in which left turns should be restricted at central intersections that carry larger vehicle flows but allowed otherwise. Such findings can be used as a starting point for where to restrict left turns in more realistic networks. 
    more » « less
  3. Bicycling has become an increasingly popular and environmentally friendly active transportation modality for many commuters across the nation. Consequently, as ridership increases so does the rate of bicycle–motor vehicle crashes, many of which are caused by reduced bicycle visibility and driver inattention. Therefore, one effective solution to improve bicyclist safety may be through the use of an audible bicycle alarm system to alert both the driver and the rider. A study was conducted to determine whether a unique auditory alert would be effective at reducing crash rates and whether a localized alert (i.e., an alert presented from the driver’s perspective) would improve the driver’s responsiveness in avoiding a potential collision. A driving simulator study tested car horn sounds, an experimental bike alert, and no auditory alert in different potential collision scenarios to measure collision rates and other collision avoidance metrics. Findings indicated that the experimental bike alert contributed to fewer relative crashes than the horn sound and no sound on bicycles, motor vehicles were struck more frequently than bicycles, collisions were more likely to occur from the front than the sides, and collisions were more likely for drivers going straight than when making turns. Taken together, the findings suggest that an alarm designed to be specifically compatible with bicycles is more effective than auditory alerts from other sources.

     
    more » « less
  4. Real-time traffic data at intersections is significant for development of adaptive traffic light control systems. Sensors such as infrared radiation and GPS are not capable of providing detailed traffic information. Compared with these sensors, surveillance cameras have the potential to provide real scenes for traffic analysis. In this research, a You Only Look Once (YOLO)-based algorithm is employed to detect and track vehicles from traffic videos, and a predefined road mask is used to determine traffic flow and turning events in different roads. A Kalman filter is used to estimate and predict vehicle speed and location under the condition of background occlusion. The result shows that the proposed algorithm can identify traffic flow and turning events at a root mean square error (RMSE) of 10. The result shows that a Kalman filter with an intersection of union (IOU)-based tracker performs well at the condition of background occlusion. Also, the proposed algorithm can detect and track vehicles at different optical conditions. Bad weather and night-time will influence the detecting and tracking process in areas far from traffic cameras. The traffic flow extracted from traffic videos contains road information, so it can not only help with single intersection control, but also provides information for a road network. The temporal characteristic of observed traffic flow gives the potential to predict traffic flow based on detected traffic flow, which will make the traffic light control more efficient. 
    more » « less
  5. null (Ed.)
    Network macroscopic fundamental diagrams (MFDs) have recently been shown to exist in real-world urban traffic networks. The existence of an MFD facilitates the modeling of urban traffic network dynamics at a regional level, which can be used to identify and refine large-scale network-wide control strategies. To be useful, MFD-based modeling frameworks require an estimate of the functional form of a network’s MFD. Analytical methods have been proposed to estimate a network’s MFD by abstracting the network as a single ring-road or corridor and modeling the flow–density relationship on that simplified element. However, these existing methods cannot account for the impact of turning traffic, as only a single corridor is considered. This paper proposes a method to estimate a network’s MFD when vehicles are allowed to turn into or out of a corridor. A two-ring abstraction is first used to analyze how turning will affect vehicle travel in a more general network, and then the model is further approximated using a single ring-road or corridor. This approximation is useful as it facilitates the application of existing variational theory-based methods (the stochastic method of cuts) to estimate the flow–density relationship on the corridor, while accounting for the stochastic nature of turning. Results of the approximation compared with a more realistic simulation that includes features that cannot be captured using variational theory—such as internal origins and destinations—suggest that this approximation works to estimate a network’s MFD when turning traffic is present. 
    more » « less