Driver Intention Prediction Research Articles

Driver intention prediction based on multi-dimensional cross-modality information interaction

Driver intention prediction based on multi-dimensional cross-modality information interaction

FedPRM: Federated Personalized Mixture Representation for Driver Intention Prediction

FedPRM: Federated Personalized Mixture Representation for Driver Intention Prediction

DIPNet: Driver intention prediction for a safe takeover transition in autonomous vehicles

AbstractFollowing the successful development of advanced driver assistance systems (ADAS), the current research directions focus on highely automated vehicles aiming at reducing human driving tasks, and extending the operational design domain, while maintaining a higher level of safety. Currently, there are high research demands in academia and industry to predict driver intention and understating driver readiness, e.g. in response to a “take‐over request” when a transition from automated driving mode to human mode is needed. A driver intention prediction system can assess the driver's readiness for a safe takeover transition. In this study, a novel deep neural network framework is developed by adopting and adapting the DenseNet, long short‐term memory, attention, FlowNet2, and RAFT models to anticipate the diver maneuver intention. Using the public “Brain4Cars” dataset, the driver maneuver intention will be predicted up to 4 s in advance, before the commencement of the driver's action. The driver intention prediction is assessed based on 1) in‐cabin 2) out‐cabin (road) and 3) both in‐out cabin video data. Utilizing K‐fold cross‐validation, the performance of the model is evaluated using accuracy, precision, recall, and F1‐score metrics. The experiments show the proposed DIPNet model outperforms the state‐of‐the‐art in the majority of the driving scenarios.

Driver Intent Prediction and Collision Avoidance With Barrier Functions

For autonomous vehicles and driver assist systems, path planning and collision avoidance algorithms benefit from accurate predictions of future location of other vehicles and intent of their drivers. In the literature, the algorithms that provide driver intent belong to two categories: those that use physics based models with some type of filtering, and machine learning based approaches. In this paper we employ barrier functions (BF) to decide driver intent. BFs are typically used to prove safety by establishing forward invariance of an admissible set. Here, we decide if the “target” vehicle is violating one or more possibly fictitious (i.e., non-physical) barrier constraints determined based on the context provided by the road geometry. The algorithm has a very small computational footprint and better false positive and negative rates than some of the alternatives. The predicted intent is then used by a control barrier function (CBF) based collision avoidance system to prevent unnecessary interventions, for either an autonomous or human-driven vehicle.

Haptic Assistive Control With Learning-Based Driver Intent Recognition for Semi-Autonomous Vehicles

Semi-autonomous vehicles equipped with assistive control systems may experience degraded lateral behaviors when aggressive driver steering commands compete with high levels of autonomy. This challenge can be mitigated with effective operator intent recognition, which can configure automated systems in context-specific situations where the driver intends to perform a steering maneuver. In this article, an ensemble learning-based driver intent recognition strategy has been developed. A nonlinear model predictive control algorithm has been designed and implemented to generate haptic feedback for lateral vehicle guidance, assisting the drivers in accomplishing their intended action. To validate the framework, operator-in-the-loop testing with 30 human subjects was conducted on a steer-by-wire platform with a virtual reality driving environment. The roadway scenarios included lane change, obstacle avoidance, intersection turns, and highway exit. The automated system with learning-based driver intent recognition was compared to both the automated system with a finite state machine-based driver intent estimator and the automated system without any driver intent prediction for all driving events. Test results demonstrate that semi-autonomous vehicle performance can be enhanced by up to 74.1% with a learning-based intent predictor. Further, the learning-based model has a 30.9% higher driver intent recognition accuracy than the finite state machine-based method. The holistic framework that integrates human intelligence, machine learning algorithms, and vehicle control can help solve the driver-system conflict problem leading to safer operation.

A comprehensive lateral motion prediction method of surrounding vehicles integrating driver intention prediction and vehicle behavior recognition

In order to solve the accuracy problem of the future motion prediction of the surrounding vehicles with different types of drivers, this paper proposes a comprehensive lateral motion prediction method that combines driver intention prediction and vehicle behavior recognition. For different drivers, different driver optimization models are established: personal optimal model and system optimal model. Then, the driver’s intention prediction probability is obtained through the game theory. Different from the traditional game theory, we apply different model for different driver on the premise of getting the type of driver instead of using the Nash equilibrium for all players. According to the results of driver intention prediction and the vehicle behavior recognition, the optimized polynomial trajectory is used to obtain the driver’s intention prediction trajectory and the vehicle behavior recognition trajectory. Next, the Nash-optimization function of the intention prediction trajectory and the behavior recognition trajectory are established respectively according to the trajectory error, and the balance between the two is our comprehensive trajectory. In order to verify the effectiveness of the proposed method, we conducted simulations under mandatory lane changing and discretionary lane changing conditions. The simulation results show that our algorithm can accurately predict the future motion of the vehicle under different drivers, different speeds and different gaps between vehicles. Its prediction performance is much better than other algorithms.

Dipnet: Driver Intention Prediction for a Safe Takeover Transition in Automated Vehicles

Dipnet: Driver Intention Prediction for a Safe Takeover Transition in Automated Vehicles

Driver intention prediction using model-added Bayesian network

The autonomous driving technology requires reliable detection and prediction of the surrounding environment. Predicting the lane change intention of the surrounding traffic is critical to evaluate the potential threat around the host vehicle. This paper develops a lane change maneuver prediction algorithm based on a newly proposed driver model combined with a Bayesian network. The innovation of the proposed algorithm is the utilization of the driver model while calibrating and executing the Bayesian network. The prediction algorithm can provide not only the driver’s intention but also the probability associated with the intention. The Next-Generation Simulation data sets are used to develop and validate the prediction model. In total, there are more than 2000 lane change events used in this paper. The result shows that the proposed prediction algorithm can provide an accurate prediction of the surrounding vehicle’s lane change maneuver.

Personalised neural networks for a driver intention prediction: communication as enabler for automated driving

Abstract In everyday traffic, pedestrians rely on informal communication with other road users. In case of automated vehicles, this communication can be replaced by light signals, which need to be learned beforehand. Prior to an extensive introduction of automated vehicles, a learning phase for these light signals can be set up in manual driving with help of a driver intention prediction. Therefore, a three-staged algorithm consisting of a neural network, a random forest and a conditional stage, is implemented. Using this algorithm, a true-positive rate (TPR) of 94.0% for a 5.0% false-positive rate (FPR) can be achieved. To improve this process, a personalization procedure is implemented, using driver-specific behaviours, resulting in TPRs ranging from 91.5 to 96.6% for a FPR of 5.0%. Transfer learning of neural networks improves the prediction accuracy of almost all drivers. In order to introduce the implemented algorithm in today’s traffic, especially the FPR has to be improved considerably.

Trajectory Clustering Aided Personalized Driver Intention Prediction for Intelligent Vehicles

Early driver intention prediction plays a significant role in intelligent vehicles. Drivers exhibit various driving characteristics impairing the performance of conventional algorithms using all drivers’ data indiscriminatingly. This paper develops a personalized driver intention prediction system at unsignalized T intersections by seamlessly integrating clustering and classification. Polynomial regression mixture (PRM) clustering and Akaike's information criterion are applied to individual drivers trajectories for learning in-depth driving behaviors. Then, various classifiers are evaluated to link low-level vehicle states to high-level driving behaviors. CART classifier with Bayesian optimization excels others in accuracy and computation. The proposed system is validated by a real-world driving dataset. Comparative experimental results indicate that PRM clustering can discover more in-depth driving behaviors than manually defined maneuver due to its fine ability in accounting for both spatial and temporal information; the proposed framework integrating PRM clustering and CART classification provides promising intention prediction performance and is adaptive to different drivers.

Study on driver’s braking intention identification based on functional near-infrared spectroscopy

Purpose Cooperative driving refers to a notion that intelligent system sharing controlling with human driver and completing driving task together. One of the key technologies is that the intelligent system can identify the driver’s driving intention in real time to implement consistent driving decisions. The purpose of this study is to establish a driver intention prediction model. Design/methodology/approach The authors used the NIRx device to measure the cerebral cortex activities for identifying the driver’s braking intention. The experiment was carried out in a virtual reality environment. During the experiment, the driving simulator recorded the driving data and the functional near-infrared spectroscopy (fNIRS) device recorded the changes in hemoglobin concentration in the cerebral cortex. After the experiment, the driver’s braking intention identification model was established through the principal component analysis and back propagation neural network. Findings The research results showed that the accuracy of the model established in this paper was 80.39 per cent. And, the model could identify the driver’s braking intent prior to his braking operation. Research limitations/implications The limitation of this study was that the experimental environment was ideal and did not consider the surrounding traffic. At the same time, other actions of the driver were not taken into account when establishing the braking intention recognition model. Besides, the verification results obtained in this paper could only reflect the results of a few drivers’ identification of braking intention. Practical implications This study can be used as a reference for future research on driving intention through fNIRS, and it also has a positive effect on the research of brain-controlled driving. At the same time, it has developed new frontiers for intention recognition of cooperative driving. Social implications This study explores new directions for future brain-controlled driving and wheelchairs. Originality/value The driver’s driving intention was predicted through the fNIRS device for the first time.

A novel digital twin-centric approach for driver intention prediction and traffic congestion avoidance

Road traffic has been exponentially growing with surging people and vehicle population. Road connectivity infrastructure has not been growing correspondingly and hence the research endeavors for optimal resource allocation and utilization of connectivity resources has gained a lot these days. Therefore, insights-driven real-time traffic management is turning out to be an important component in establishing and sustaining smarter cities across the globe. IT solution and service organizations have come forth with a number of automated traffic management solutions and the primary problem with them is they are unfortunately reactive and hence an inefficient solution for the increasingly connected and dynamic city environments. Therefore, unveiling real-time, adaptive, precision-centric and predictive traffic monitoring, measurement, management and enhancement solutions are being insisted as an indispensable requirement toward sustainable cities. We have come out with a novel approach leveraging a few potential and promising technologies and tools such as a reliable and reusable virtual model for vehicles, a machine learning model, the IoT fog or edge data analytics, a data lake for traffic and vehicle data on public cloud environments, and 5G communication. The paper details all these in a cogent fashion and how these technological advancements come handy in avoiding the frequent traffic congestions and snarls due to various reasons.

The Warrigal Dataset: Multi-Vehicle Trajectories and V2V Communications

Intelligent Transportation Systems rely on understanding, predicting and affecting the interactions between vehicles. Development of such systems must be based upon data derived from actual interactions if they are to be effective when used in real world applications. Increasingly, systems are being developed that are based on radio communication of state and intent between vehicles. Understanding of how these interactions occur is also necessary to creating robust systems. In order to test and compare new techniques, approaches and algorithms it is necessary to have a rich dataset to experiment with. This paper presents a detailed dataset useful for members of the Intelligent Transportation Systems community. It contains vehicle state information, vehicle-to-vehicle communications and road maps at high temporal resolution for large numbers of interacting vehicles over a long time period. This data set has already been used for a number of Intelligent Transportation Systems projects such as road mapping, driver intent prediction and collision avoidance among others.