In this paper, we present an optimization-based approach for safe, efficient, and resilient autonomous intersection traffic control in realistic vehicle-to-everything (V2X) communication environment. The proposed framework produces the fastest discrete-time trajectory for vehicles who want to cross an intersection. Constraints for safety are designed carefully in the optimization problem formulation to prevent potential collisions during intersection crossings. A novel vehicle-to-intersection (V2I) interaction mechanism is designed to handle imperfect communication characteristics such as packet delivery delay and loss. The proposed intersection management framework is evaluated by running extensive simulations using an open source vehicular network and microscopic traffic simulation software, Veins. The results show that the overall traffic control performance of the proposed framework is substantially better than conventional traffic light control framework, in particular when traffic volume is light and medium, even in situations with a realistic wireless vehicular network setting where packet delivery delays and drops occasionally occur.
11 October 2017 in Journal of Advanced Transportation
This paper proposes an intersection control algorithm which aims to determine an efficient vehicle-passing sequence that allows the emergency vehicle to cross an intersection as soon as possible while the travel times of other vehicles are minimally affected. When there are no emergency vehicles within the intersection area, the vehicles are controlled by the DICA that we proposed in our earlier work. When there are emergency vehicles entering the communication range, we prioritize emergency vehicles through optimal ordering of vehicles. Since the number of possible vehicle-passing sequences increases rapidly with the number of vehicles, finding an efficient sequence of vehicles in a short time is the main challenge of the study. A genetic algorithm is proposed to solve the optimization problem which finds the optimal vehicle sequence that gives the emergency vehicles the highest priority. The efficiency of the proposed approach for expedited crossing of emergency vehicles is validated through comparisons with DICA and a reactive traffic light algorithm through extensive simulations. The results show that the proposed genetic algorithm is able to decrease the travel times of emergency vehicles significantly in light and medium traffic volumes without causing any noticeable performance degradation of normal vehicles.
Despite advances in autonomous driving technology, traffic accidents remain a problem to be solved in the transportation system. More than half of traffic accidents are due to unsafe driving. In addition, aggressive driving behavior can lead to traffic jams. To reduce this, we propose a 4-layer CNN-2 stack LSTM-based driving behavior classification and V2X sharing system that uses time-series data as an input to reflect temporal changes. The proposed system classifies driving behavior into defensive, normal, and aggressive driving using only the 3-axis acceleration of the driving vehicle and shares it with the surroundings. We collect a training dataset by composing a road that reflects various environmental factors using a driving simulator that mimics a real vehicle and IPG CarMaker, an autonomous driving simulation. Additionally, driving behavior datasets are collected by driving real-world DGIST campus to augment training data. The proposed network has the best performance compared to the state-of-the-art CNN, LSTM, and CNN-LSTM. Finally, our system shares the driving behavior classified by 4-layer CNN-2 stacked LSTM with surrounding vehicles through V2X communication. The proposed system has been validated in ACC simulations and real environments. For real world testing, we configure NVIDIA Jetson TX2, IMU, GPS, and V2X devices as one module. We performed the experiments of the driving behavior classification and V2X transmission and reception in a real world by using the prototype module. As a result of the experiment, the driving behavior classification performance was confirmed to be ~98% or more in the simulation test and 97% or more in the real-world test. In addition, the V2X communication delay through the prototype was confirmed to be an average of 4.8 ms. The proposed system can contribute to improving the safety of the transportation system by sharing the driving behaviors of each vehicle.
In this paper, we propose a hybrid time series forecasting model, named as the Adaptive Multivariate Exponential Smoothing – Recurrent Neural Networks (AMES-RNN), which enables accurate prediction for time series data with non-seasonal and additive trend characteristics. To enhance prediction performance, the optimal smoothing parameters of the Exponential Smoothing (ES) model are estimated and updated online. Here, the parameter estimation is performed through a deep learning-based regression model, and a method for training the regression model is presented. In addition, the prediction model utilizes future-implying information as additional input if available in order to improve prediction accuracy. The effectiveness of the proposed model was validated through multistep forecast tests using vehicle driving data that has non-seasonal and additive trend characteristics. The results show that the prediction accuracy of the proposed model was improved at least 23.0% compared to those of the existing prediction model. Additionally, we demonstrated that AMES-RNN requires low computational resources, making it feasible to perform online predictions.
1 January 2016 in Journal of Traffic and Logistics Engineering