Risk-based merging decisions for autonomous vehicles

Safety assessment for autonomous vehicles: A reference driver model for highway merging scenarios

Driver models are crucial for the safety assessment of autonomous vehicles (AVs) because of their role as reference models. Specifically, an AV is expected to achieve at least the same level of safety performance as a careful and competent driver model. To make this comparison possible, quantitative modeling of careful and competent driver models is essential. Thus, the UNECE Regulation No. 157 proposes two driver models as benchmarks for AVs, enabling safety assessment of AV longitudinal behaviors. However, these two driver models are unable to be applied in non-car-following scenarios, limiting their applications in scenarios such as highway merging. To this end, we propose a careful and competent driver model for highway merging (CCDM2) scenarios using interpretable reinforcement learning-based decision-making and safety constraint control. We compare our model's safe driving capabilities with human drivers in challenging merging scenarios and demonstrate the "careful" and "competent" characteristics of our model while ensuring its interpretability. The results indicate the model's capability to handle merging scenarios with even better safety performance than human drivers. This model is of great value for AV safety assessment in merging scenarios and contributes to future reference driver models to be included in AV safety regulations.

Enhancing autonomous vehicle hyperawareness in busy traffic environments: A machine learning approach

As autonomous vehicles (AVs) advance from theory into practice, their safety and operational impacts are being more closely studied. This study aims to contribute to the ever-evolving algorithms used by AVs during travel in busy urban districts, as well as explore the potential utilization of AV sensor data to identify safety hazards to surrounding road users in real time. Accordingly, the study incorporates AV data collected from multiple cities in the United States to detect and categorize traffic conflicts that involve the source AVs, as well as conflicts that involve other surrounding road users. Then, a machine learning conflict prediction model is trained with Isolation Forest - Convolutional Neural Network - Long Short-Term Memory (IF-CNN-LSTM) layers. The model receives data in real time in the form of road user trajectories and headings to make an informed prediction of the potential frequency and severity of conflicts three seconds into the future. In addition, the transferability of the trained model to new data and locations is explored to understand the potential compromise in accuracy compared to the effort and cost of retraining. The results show that the proposed model is capable of predicting the possibility of conflict occurrence and conflict severity with high accuracy (sensitivity = 83.5 % and fallout = 11 %). The reported sensitivity of AV conflict prediction ranged between 89 % and 95 %, depending on conflict type, which outperforms most of the existing conflict prediction models. The model is also capable of predicting hazardous conflicts of surrounding road users in real time, with sensitivity values ranging between 82 % and 87 %, affirming the promising capabilities of onboard vehicle sensors in undertaking real-time safety applications. The model also retains good performance when transferred to different data, with the potential to retain nearly 97 % of the source model's performance if sufficient tuning data exists.

Risk-based merging decisions for autonomous vehicles

INTRODUCTION

The safe freeway merging operation for fully Autonomous Vehicles (AVs) in mixed traffic (i.e., the presence of AVs and non-AVs in a traffic stream) is a challenging task. Under a mixed traffic environment, an AV merging operation could significantly increase conflict risks and reduce operational efficiency.

METHOD

This study quantifies the freeway merging conflict risk and develops a freeway merging decision strategy based on conflict risk assessment for an AV attempting to merge to a traffic stream with non-AVs on the freeway. The performance of the risk-based merging decision strategy is evaluated in uncongested, near-congested, and congested traffic conditions.

RESULTS

The analyses show that the risk-based merging strategy causes less abrupt deceleration of an AV's immediate upstream vehicle in the target lane on the freeway compared to the based models (i.e., two models based on gap acceptance concepts and a safe gap model based on a surrogate measure, 'Time-to-Collision (TTC)'). The risk-based merging strategy meets the minimum safe gap between an AV intending to merge and its immediate downstream vehicle in the target lane. The risk-based merging strategy produces lower conflict risk in terms of 'Time Exposed Time-to-Collision (TET)' and 'Time Integrated Time-to-Collision (TIT)' compared to the base models. Moreover, the risk-based merging strategy has a lower impact on the average speed of traffic in the target lane compared to the base models considered in this study.

CONCLUSIONS

The risk-based merging strategy shows higher safety benefits for an AV's merging operation compared to base models.

PRACTICAL APPLICATIONS

The findings of this research would help design AV controllers for improving the safety of an AV merging operation in a mixed traffic stream.