An ensemble deep learning approach for driver lane change intention inference

Abstract

With the rapid development of intelligent vehicles, drivers are increasingly likely to share their control authorities with the intelligent control unit. For building an efficient Advanced Driver Assistance Systems (ADAS) and shared-control systems, the vehicle needs to understand the drivers' intent and their activities to generate assistant and collaborative control strategies. In this study, a driver intention inference system that focuses on the highway lane change maneuvers is proposed. First, a high-level driver intention mechanism and framework are introduced. Then, a vision-based intention inference system is proposed, which captures the multi-modal signals based on multiple low-cost cameras and the VBOX vehicle data acquisition system. A novel ensemble bi-directional recurrent neural network (RNN) model with Long Short-Term Memory (LSTM) units is proposed to deal with the time-series driving sequence and the temporal behavioral patterns. Naturalistic highway driving data that consists of lane-keeping, left and right lane change maneuvers are collected and used for model construction and evaluation. Furthermore, the driver's pre-maneuver activities are statistically analyzed. It is found that for situation-aware, drivers usually check the mirrors for more than six seconds before they initiate the lane change maneuver, and the time interval between steering the handwheel and crossing the lane is about 2 s on average. Finally, hypothesis testing is conducted to show the significant improvement of the proposed algorithm over existing ones. With five-fold cross-validation, the EBiLSTM model achieves an average accuracy of 96.1% for the intention that is inferred 0.5 s before the maneuver starts.

Differences in Driving Intention Transitions Caused by Driver’s Emotion Evolutions

“…We used the approximate normal distribution method to calculate the confidence of the prediction accuracy [ 31 ], and the 95% confidence intervals of recognition accuracy for Int1, Int2 and Int3 were (0.761, 0.825), (0.845, 0.889) and (0.783, 0.849), respectively. The result showed that the accuracy of the driving intention prediction model proposed in this paper was acceptable compared with many existing driving intention prediction algorithms (the prediction accuracy is generally between 75% and 90%) [ 32 , 33 , 34 ].…”

Inferring the Driver’s Lane Change Intention through LiDAR-Based Environment Analysis Using Convolutional Neural Networks

“…These CI techniques have been used quite successfully in the problem of lane changing. Some studies address precisely the problem of identifying the intent to change lanes, achieving and average intention inference accuracy above 90%, but they usually address the problem using simulators [ 27 ] or few examples in simple environments such as highways [ 28 , 29 ].…”

HCF: A Hybrid CNN Framework for Behavior Detection of Distracted Drivers

“…Among these, distracted driving has become an increasingly important cause of traffic accidents in recent years. For example, distracted driving can cause wrong lane changes, which will lead to serious traffic accidents [4] [5]. According to the preliminary definition of the International Organization for Standardization (ISO) [6], distracted driving is "attention given to a non-driving related activity, typically to the detriment of driving performance" The National Highway Traffic Safety Administration (NHTSA) defines distracted driving as "any activity that diverts attention from driving, including talking or texting on the phone, eating and drinking, etc."…”