Enhancing multi-scenario applicability of freeway variable speed limit control strategies using continual learning.

Variable speed limit (VSL) control benefits freeway operations through dynamic speed limit adjustment strategies for specific operation scenarios, such as traffic jams, secondary crash prevention, etc. To develop optimal strategies, deep reinforcement learning (DRL) has been employed to map the traffic operation status to speed limits with the corresponding control effects. Then, VSL control strategies were obtained based upon memories of these complex mapping relationships. However, under multi-scenario conditions, DRL trained VSL faces the challenge of performance decay, where the control strategy effects drop sharply for early trained "old scenarios". This so-called scenario forgetting problem is attributed to the fact that DRL would forget the learned old scenario mapping memories after new scenario trainings. To tackle this issue, a continual learning approach has been introduced in this study to enhance the multi-scenario applicability of VSL control strategies. Specifically, a gradient projection memory (GPM) based neural network parameter updating method was proposed to keep the mapping memories of old scenarios during new scenario trainings by imposing constraints on the direction of gradient updates for new tasks. The proposed method was evaluated using three typical freeway operation scenarios developed in the simulation platform SUMO. Experimental results showed that the continual learning approach has substantially reduced the performance decay in old scenarios by 17.76% (valued using backward transfer metrics). Furthermore, the multi-scenario VSL control strategies successfully reduced the speed standard deviation and average travel time by 28.77% and 7.25% respectively. Moreover, the generalization of the proposed continual learning based VSL approach were evaluated and discussed.

High-risk event prone driver identification considering driving behavior temporal covariate shift.

Drivers who perform frequent high-risk events (e.g., hard braking maneuvers) pose a significant threat to traffic safety. Existing studies commonly estimated high-risk event occurrence probabilities based upon the assumption that data collected from different time periods are independent and identically distributed (referred to as i.i.d. assumption). Such approach ignored the issue of driving behavior temporal covariate shift, where the distributions of driving behavior factors vary over time. To fill the gap, this study targets at obtaining time-invariant driving behavior features and establishing their relationships with high-risk event occurrence probability. Specifically, a generalized modeling framework consisting of distribution characterization (DC) and distribution matching (DM) modules was proposed. The DC module split the whole dataset into several segments with the largest distribution gaps, while the DM module identified time-invariant driving behavior features through learning common knowledge among different segments. Then, gated recurrent unit (GRU) was employed to conduct time-invariant driving behavior feature mining for high-risk event occurrence probability estimation. Moreover, modified loss functions were introduced for imbalanced data learning caused by the rarity of high-risk events. The empirical analyses were conducted utilizing online ride-hailing services data. Experiment results showed that the proposed generalized modeling framework provided a 7.2% higher average precision compared to the traditional i.i.d. assumption based approach. The modified loss functions further improved the model performance by 3.8%. Finally, benefits for the driver management program improvement have been explored by a case study, demonstrating a 33.34% enhancement in the identification precision of high-risk event prone drivers.

Critical safety management driver identification based upon temporal variation characteristics of driving behavior.

Identifying critical safety management drivers with high driver-level risks is essential for traffic safety improvement. Previous studies commonly evaluated driver-level risks based upon aggregated statistical characteristics (e.g., driving exposure and driving behavior), which were obtained from long-period driving monitoring data. However, given the great advancements of the connected vehicle and in-vehicle data instrumentation technologies, there has been a notable increase in the collection of short-period driving data, which has emerged as a prominent data source for analysis. In this data environment, traditionally employed aggregated behavior characteristics are unstable due to the time-varying feature of driving behavior coupled with insufficient data sampling periods. Thus, traditional modeling methods based upon aggregated statistical characteristics are no longer feasible. Instead of utilizing such unreliable statistical information to represent driver-level risks, this study employed temporal variation characteristics of driving behavior to identify critical safety management drivers in the short-period driving data environment. Specifically, the relationships between driving behavior temporal variation characteristics and individual crash occurrence probability were developed. To eliminate the impacts of drivers' driving behavior heterogeneity on model performance, "traffic entropy" index that could quantify the abnormal degrees of driving behavior was proposed. Deep learning models including convolutional neural network (CNN) and long short-term memory (LSTM) were employed to conduct the temporal variation feature mining. Empirical analyses were conducted using data obtained from online ride-hailing services. Experiment results showed that temporal variation characteristics based models outperformed traditional aggregated statistical characteristics based models. The area under the curve (AUC) index was improved by 4.1%. And the proposed traffic entropy index further enhanced the model performance by 5.3%. The best model achieved an AUC of 0.754, comparable to existing approaches utilizing long-period driving data. Finally, applications of the proposed method in driver management program development and its further investigations have been discussed.

Personalized driving assistance algorithms: Case study of federated learning based forward collision warning.

Current designs of advanced driving assistance systems (ADAS) mainly developed uniform collision warning algorithms, which ignore the heterogeneity of driving behaviors, thus lead to low drivers' trust in. To address this issue, developing personalized driving assistance algorithms is a promising approach. However, current personalization systems were mainly implemented through manually adjusting warning trigger thresholds, which would be less feasible for overall drivers as certain domain expertise is required to set personal thresholds accurately. Other personalization techniques exploited individual drivers' data to build personalized models. Such approach could learn personal behavior but requires impractical large-scale individual data collections. To fill up the gaps, self-adaptive algorithms for personalized forward collision warning (FCW) based on federated learning were proposed in this study. A baseline model was developed by long short-term memory (LSTM) for FCW. Federated learning framework was then introduced to collect knowledge from multiple drivers with privacy preserving. Specifically, a general cloud server model was trained by collecting updated parameters from individual vehicle server models rather than collecting raw data. Besides, a driver-specific batch normalization (BN) layer was added into each vehicle server model to address the heterogeneity of driving behaviors. Experiments show empirically that the proposed federated-based personalized models with the BN layer showed to have the best performance. The average modeling accuracy has reached 84.88% and the performance is comparable to conventional total data collection training approach, where the additional BN layer could increase the accuracy by 3.48%. Finally, applications of the proposed framework and its further investigations have been discussed.