skip to main content
Explore Scholarly Publications and Datasets in the NSF-PAR

Title: Graph Convolution Networks for Probabilistic Modeling of Driving Acceleration
The ability to model and predict ego-vehicle's surrounding traffic is crucial for autonomous pilots and intelligent driver-assistance systems. Acceleration prediction is important as one of the major components of traffic prediction. This paper proposes novel approaches to the acceleration prediction problem. By representing spatial relationships between vehicles with a graph model, we build a generalized acceleration prediction framework. This paper studies the effectiveness of proposed Graph Convolution Networks, which operate on graphs predicting the acceleration distribution for vehicles driving on highways. We further investigate prediction improvement through integrating of Recurrent Neural Networks to disentangle the temporal complexity inherent in the traffic data. Results from simulation with comprehensive performance metrics support that our proposed networks outperform state-of-the-art methods in generating realistic trajectories over a prediction horizon.
Authors:
; ; ;
Award ID(s):
1650512
Publication Date:
NSF-PAR ID:
10323254
Journal Name:
2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ( , Transportation research)
    Motivated by connected and automated vehicle (CAV) technologies, this paper proposes a data-driven optimization-based Model Predictive Control (MPC) modeling framework for the Cooperative Adaptive Cruise Control (CACC) of a string of CAVs under uncertain traffic conditions. The proposed data-driven optimization-based MPC modeling framework aims to improve the stability, robustness, and safety of longitudinal cooperative automated driving involving a string of CAVs under uncertain traffic conditions using Vehicle-to-Vehicle (V2V) data. Based on an online learning-based driving dynamics prediction model, we predict the uncertain driving states of the vehicles preceding the controlled CAVs. With the predicted driving states of the preceding vehicles, we solve a constrained Finite-Horizon Optimal Control problem to predict the uncertain driving states of the controlled CAVs. To obtain the optimal acceleration or deceleration commands for the CAVs under uncertainties, we formulate a Distributionally Robust Stochastic Optimization (DRSO) model (i.e. a special case of data-driven optimization models under moment bounds) with a Distributionally Robust Chance Constraint (DRCC). The predicted uncertain driving states of the immediately preceding vehicles and the controlled CAVs will be utilized in the safety constraint and the reference driving states of the DRSO-DRCC model. To solve the minimax program of the DRSO-DRCC model, we reformulate themore »relaxed dual problem as a Semidefinite Program (SDP) of the original DRSO-DRCC model based on the strong duality theory and the Semidefinite Relaxation technique. In addition, we propose two methods for solving the relaxed SDP problem. We use Next Generation Simulation (NGSIM) data to demonstrate the proposed model in numerical experiments. The experimental results and analyses demonstrate that the proposed model can obtain string-stable, robust, and safe longitudinal cooperative automated driving control of CAVs by proper settings, including the driving-dynamics prediction model, prediction horizon lengths, and time headways. Computational analyses are conducted to validate the efficiency of the proposed methods for solving the DRSO-DRCC model for real-time automated driving applications within proper settings.« less
  2. ; ( , Transportation research)
    For energy-efficient Connected and Automated Vehicle (CAV) Eco-driving control on signalized arterials under uncertain traffic conditions, this paper explicitly considers traffic control devices (e.g., road markings, traffic signs, and traffic signals) and road geometry (e.g., road shapes, road boundaries, and road grades) constraints in a data-driven optimization-based Model Predictive Control (MPC) modeling framework. This modeling framework uses real-time vehicle driving and traffic signal data via Vehicle-to-Infrastructure (V2I) and Vehicle-to-Vehicle (V2V) communications. In the MPC-based control model, this paper mathematically formulates location-based traffic control devices and road geometry constraints using the geographic information from High-Definition (HD) maps. The location-based traffic control devices and road geometry constraints have the potential to improve the safety, energy, efficiency, driving comfort, and robustness of connected and automated driving on real roads by considering interrupted flow facility locations and road geometry in the formulation. We predict a set of uncertain driving states for the preceding vehicles through an online learning-based driving dynamics prediction model. We then solve a constrained finite-horizon optimal control problem with the predicted driving states to obtain a set of Eco-driving references for the controlled vehicle. To obtain the optimal acceleration or deceleration commands for the controlled vehicle with the set of Eco-drivingmore »references, we formulate a Distributionally Robust Stochastic Optimization (DRSO) model (i.e., a special case of data-driven optimization models under moment bounds) with Distributionally Robust Chance Constraints (DRCC) with location-based traffic control devices and road geometry constraints. We design experiments to demonstrate the proposed model under different traffic conditions using real-world connected vehicle trajectory data and Signal Phasing and Timing (SPaT) data on a coordinated arterial with six actuated intersections on Fuller Road in Ann Arbor, Michigan from the Safety Pilot Model Deployment (SPMD) project.« less
  3. ; ; ; ; ; ; ; ( , 2021 IEEE Intelligent Transportation Systems Conference (ITSC))
    In this paper, we investigated the performance of cooperative adaptive cruise control (CACC) algorithms in mixed traffic environments featuring connected automated vehicles (CAVs) and unconnected vehicles. For CAVs, we tested the recently proposed linear feedback control approach (Linear- CACCu) and adaptive model predictive control approach (A- MPC-CACCu) which have been tailored to extend CACC to mixed traffic environments. In contrast to most literature where CACC design and evaluation are performed on freeways, we focused on urban arterial roads using the CACC Field Operation Test Dataset from the Netherlands. We compared the performances of Linear-CACCu and A-MPC-CACCu to regular adaptive cruise control (ACC), where automated vehicles do not rely on connectivity, as well as human drivers. Performance comparison was done in terms of ego vehicle’s spacing error, acceleration, and energy consumption which relate to safety, driving comfort, and energy efficiency, respectively. Simulation results showed that CACCu algorithms significantly outper- formed the ACC and human drivers in these metrics. Moreover, we found that the fluctuations of the lead vehicle’s behavior due to changes in traffic signal phase have a significant impact on which CACCu is optimal (i.e., A-MPC-CACCu or Linear- CACCu). Thus, the CACC mode could be switched based on the expectationmore »of traffic signal phase changes to assure better performance.« less
  4. ; ; ( , Transportation Research Record: Journal of the Transportation Research Board)

    Imputing missing data is a critical task in data-driven intelligent transportation systems. During recent decades there has been a considerable investment in developing various types of sensors and smart systems, including stationary devices (e.g., loop detectors) and floating vehicles equipped with global positioning system (GPS) trackers to collect large-scale traffic data. However, collected data may not include observations from all road segments in a traffic network for different reasons, including sensor failure, transmission error, and because GPS-equipped vehicles may not always travel through all road segments. The first step toward developing real-time traffic monitoring and disruption prediction models is to estimate missing values through a systematic data imputation process. Many of the existing data imputation methods are based on matrix completion techniques that utilize the inherent spatiotemporal characteristics of traffic data. However, these methods may not fully capture the clustered structure of the data. This paper addresses this issue by developing a novel data imputation method using PARATUCK2 decomposition. The proposed method captures both spatial and temporal information of traffic data and constructs a low-dimensional and clustered representation of traffic patterns. The identified spatiotemporal clusters are used to recover network traffic profiles and estimate missing values. The proposed method ismore »implemented using traffic data in the road network of Manhattan in New York City. The performance of the proposed method is evaluated in comparison with two state-of-the-art benchmark methods. The outcomes indicate that the proposed method outperforms the existing state-of-the-art imputation methods in complex and large-scale traffic networks.

    « less
  5. ; ( , Transportation Research Record: Journal of the Transportation Research Board)
    The existence of spatiotemporal correlations in traffic behavior on links in a transportation network is potentially very useful. However, traffic metrics are often strongly correlated simply because of natural variations in travel demand patterns and these temporal trends might obstruct more meaningful relationships caused by the physics of traffic. To overcome this challenge, the present paper proposes a non-parametric, moving average detrending method that can be used to remove these background trends, even during non-stationary periods in which traffic states are changing with time. Cross-correlations performed on the detrended data are then used to identify more meaningful trends. The proposed method can also incorporate temporal lags in correlations between individual links, which accounts for the time it takes for information to travel between them. Links that exhibit strong correlations after detrending can then be grouped into communities which behave together using graph theory methods, and this community structure can be leveraged to improve prediction of link performance when information is missing. The proposed methodology is applied to a case study network using real-time link travel speeds obtained from probe vehicles. The results reveal that the 40 links in the network can be grouped into between eight and 12 communities, dependingmore »on the day of the week. This suggests that only a handful of links may need to be monitored to estimate travel speeds across the entire network. Furthermore, the significant overlap in the community structure across these days reveals that the network structure plays a large role in spatiotemporal correlations in link travel speeds in a network.« less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email