A Hybrid Approach for Turning Intention Prediction Based on Time Series Forecasting and Deep Learning
At an intersection with complex traffic flow, the early detection of the intention of drivers in surrounding vehicles can enable advanced driver assistance systems (ADAS) to warn the driver in advance or prompt its subsystems to assess the risk and intervene early. Although different drivers show va...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/17/4887 |
| _version_ | 1827707348971421696 |
|---|---|
| author | Hailun Zhang Rui Fu |
| author_facet | Hailun Zhang Rui Fu |
| author_sort | Hailun Zhang |
| collection | DOAJ |
| description | At an intersection with complex traffic flow, the early detection of the intention of drivers in surrounding vehicles can enable advanced driver assistance systems (ADAS) to warn the driver in advance or prompt its subsystems to assess the risk and intervene early. Although different drivers show various driving characteristics, the kinematic parameters of human-driven vehicles can be used as a predictor for predicting the driver’s intention within a short time. In this paper, we propose a new hybrid approach for vehicle behavior recognition at intersections based on time series prediction and deep learning networks. First, the lateral position, longitudinal position, speed, and acceleration of the vehicle are predicted using the online autoregressive integrated moving average (ARIMA) algorithm. Next, a variant of the long short-term memory network, called the bidirectional long short-term memory (Bi-LSTM) network, is used to detect the vehicle’s turning behavior using the predicted parameters, as well as the derived parameters, i.e., the lateral velocity, lateral acceleration, and heading angle. The validity of the proposed method is verified at real intersections using the public driving data of the next generation simulation (NGSIM) project. The results of the turning behavior detection show that the proposed hybrid approach exhibits significant improvement over a conventional algorithm; the average recognition rates are 94.2% and 93.5% at 2 s and 1 s, respectively, before initiating the turning maneuver. |
| first_indexed | 2024-03-10T16:44:25Z |
| format | Article |
| id | doaj.art-f9eb8cc412784472a5bf7e6bae76c5fd |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T16:44:25Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f9eb8cc412784472a5bf7e6bae76c5fd2023-11-20T11:47:06ZengMDPI AGSensors1424-82202020-08-012017488710.3390/s20174887A Hybrid Approach for Turning Intention Prediction Based on Time Series Forecasting and Deep LearningHailun Zhang0Rui Fu1School of Automobile, Chang’an University, Xi’an 710064, ChinaSchool of Automobile, Chang’an University, Xi’an 710064, ChinaAt an intersection with complex traffic flow, the early detection of the intention of drivers in surrounding vehicles can enable advanced driver assistance systems (ADAS) to warn the driver in advance or prompt its subsystems to assess the risk and intervene early. Although different drivers show various driving characteristics, the kinematic parameters of human-driven vehicles can be used as a predictor for predicting the driver’s intention within a short time. In this paper, we propose a new hybrid approach for vehicle behavior recognition at intersections based on time series prediction and deep learning networks. First, the lateral position, longitudinal position, speed, and acceleration of the vehicle are predicted using the online autoregressive integrated moving average (ARIMA) algorithm. Next, a variant of the long short-term memory network, called the bidirectional long short-term memory (Bi-LSTM) network, is used to detect the vehicle’s turning behavior using the predicted parameters, as well as the derived parameters, i.e., the lateral velocity, lateral acceleration, and heading angle. The validity of the proposed method is verified at real intersections using the public driving data of the next generation simulation (NGSIM) project. The results of the turning behavior detection show that the proposed hybrid approach exhibits significant improvement over a conventional algorithm; the average recognition rates are 94.2% and 93.5% at 2 s and 1 s, respectively, before initiating the turning maneuver.https://www.mdpi.com/1424-8220/20/17/4887advanced driver assistance systemautonomous vehicledriving intention predictiononline time series predictionbidirectional long short-term memory network |
| spellingShingle | Hailun Zhang Rui Fu A Hybrid Approach for Turning Intention Prediction Based on Time Series Forecasting and Deep Learning Sensors advanced driver assistance system autonomous vehicle driving intention prediction online time series prediction bidirectional long short-term memory network |
| title | A Hybrid Approach for Turning Intention Prediction Based on Time Series Forecasting and Deep Learning |
| title_full | A Hybrid Approach for Turning Intention Prediction Based on Time Series Forecasting and Deep Learning |
| title_fullStr | A Hybrid Approach for Turning Intention Prediction Based on Time Series Forecasting and Deep Learning |
| title_full_unstemmed | A Hybrid Approach for Turning Intention Prediction Based on Time Series Forecasting and Deep Learning |
| title_short | A Hybrid Approach for Turning Intention Prediction Based on Time Series Forecasting and Deep Learning |
| title_sort | hybrid approach for turning intention prediction based on time series forecasting and deep learning |
| topic | advanced driver assistance system autonomous vehicle driving intention prediction online time series prediction bidirectional long short-term memory network |
| url | https://www.mdpi.com/1424-8220/20/17/4887 |
| work_keys_str_mv | AT hailunzhang ahybridapproachforturningintentionpredictionbasedontimeseriesforecastinganddeeplearning AT ruifu ahybridapproachforturningintentionpredictionbasedontimeseriesforecastinganddeeplearning AT hailunzhang hybridapproachforturningintentionpredictionbasedontimeseriesforecastinganddeeplearning AT ruifu hybridapproachforturningintentionpredictionbasedontimeseriesforecastinganddeeplearning |