2 February 2021 in Nature Communications
Driving intelligence tests are critical to the development and deployment of autonomous vehicles. The prevailing approach tests autonomous vehicles in life-like simulations of the naturalistic driving environment. However, due to the high dimensionality of the environment and the rareness of safety-critical events, hundreds of millions of miles would be required to demonstrate the safety performance of autonomous vehicles, which is severely inefficient. We discover that sparse but adversarial adjustments to the naturalistic driving environment, resulting in the naturalistic and adversarial driving environment, can significantly reduce the required test miles without loss of evaluation unbiasedness. By training the background vehicles to learn when to execute what adversarial maneuver, the proposed environment becomes an intelligent environment for driving intelligence testing. We demonstrate the effectiveness of the proposed environment in a highway-driving simulation. Comparing with the naturalistic driving environment, the proposed environment can accelerate the evaluation process by multiple orders of magnitude.
11 April 2023 in Nature Communications
For simulation to be an effective tool for the development and testing of autonomous vehicles, the simulator must be able to produce realistic safety-critical scenarios with distribution-level accuracy. However, due to the high dimensionality of real-world driving environments and the rarity of long-tail safety-critical events, how to achieve statistical realism in simulation is a long-standing problem. In this paper, we develop NeuralNDE, a deep learning-based framework to learn multi-agent interaction behavior from vehicle trajectory data, and propose a conflict critic model and a safety mapping network to refine the generation process of safety-critical events, following real-world occurring frequencies and patterns. The results show that NeuralNDE can achieve both accurate safety-critical driving statistics (e.g., crash rate/type/severity and near-miss statistics, etc.) and normal driving statistics (e.g., vehicle speed/distance/yielding behavior distributions, etc.), as demonstrated in the simulation of urban driving environments. To the best of our knowledge, this is the first time that a simulation model can reproduce the real-world driving environment with statistical realism, particularly for safety-critical situations.
2 July 2021 in Transportation Research Record: Journal of the Transportation Research Board
Testing and evaluation is a crucial step in the development and deployment of connected and automated vehicles (CAVs). To comprehensively evaluate the performance of CAVs, it is necessary to test the CAVs in safety-critical scenarios, which rarely happen in a naturalistic driving environment. Therefore, how to purposely and systematically generate these corner cases becomes an important problem. Most existing studies focus on generating adversarial examples for perception systems of CAVs, whereas limited efforts have been put into decision-making systems, which is the highlight of this paper. As the CAVs need to interact with numerous background vehicles (BVs) for a long duration, variables that define the corner cases are usually high-dimensional, which makes the generation a challenging problem. In this paper, a unified framework is proposed to generate corner cases for decision-making systems. To address the challenge brought by high dimensionality, the driving environment is formulated based on the Markov decision process, and the deep reinforcement learning techniques are applied to learn the behavior policy of BVs. With the learned policy, BVs behave and interact with the CAVs more aggressively, resulting in more corner cases. To further analyze the generated corner cases, the techniques of feature extraction and clustering are utilized. By selecting representative cases of each cluster and outliers, the valuable corner cases can be identified from all generated corner cases. Simulation results of a highway driving environment show that the proposed methods can effectively generate and identify the valuable corner cases.
27 September 2023 in IEEE Transactions on Intelligent Transportation Systems
Safety performance evaluation is critical for developing and deploying connected and automated vehicles (CAVs). One prevailing way is to design testing scenarios using prior knowledge of CAVs, test CAVs in these scenarios, and then evaluate their safety performances. However, significant differences between CAVs and prior knowledge could severely reduce the evaluation efficiency. Towards addressing this issue, most existing studies focus on the adaptive design of testing scenarios during the CAV testing process, but so far they cannot be applied to high-dimensional scenarios. In this paper, we focus on the adaptive safety performance evaluation by leveraging the testing results, after the CAV testing process. It can significantly improve the evaluation efficiency and be applied to high-dimensional scenarios. Specifically, instead of directly evaluating the unknown quantity (e.g., crash rates) of CAV safety performances, we evaluate the differences between the unknown quantity and known quantity (i.e., control variates). By leveraging the testing results, the control variates could be well-designed and optimized such that the differences are close to zero, so the evaluation variance could be dramatically reduced for different CAVs. To handle the high-dimensional scenarios, we propose the sparse control variates method, where the control variates are designed only for the sparse and critical variables of scenarios. According to the number of critical variables in each scenario, the control variates are stratified into strata and optimized within each stratum using multiple linear regression techniques. We justify the proposed method’s effectiveness by rigorous theoretical analysis and empirical study of high-dimensional overtaking scenarios.
2 June 2025 in IEEE Transactions on Intelligent Transportation Systems
Microscopic traffic simulation provides a controllable, repeatable, and efficient testing environment for autonomous vehicles (AVs). To evaluate AVs’ safety performance unbiasedly, the probability distributions of environment statistics in the simulated naturalistic driving environment (NDE) need to be consistent with those from the real-world driving environment. However, although human driving behaviors have been extensively investigated in the transportation engineering field, most existing models were developed for traffic flow analysis without considering the distributional consistency of driving behaviors, which could cause significant evaluation biasedness for AV testing. To fill this research gap, a distributionally consistent NDE modeling framework is proposed in this paper. Using large-scale naturalistic driving data, empirical distributions are obtained to construct the stochastic human driving behavior models under different conditions. To address the error accumulation problem during the simulation, an optimization-based method is further designed to refine the empirical behavior models. Specifically, the vehicle state evolution is modeled as a Markov chain and its stationary distribution is twisted to match the distribution from the real-world driving environment. The framework is evaluated in the case study of a multi-lane highway driving simulation, where the distributional accuracy of the generated NDE is validated and the safety performance of an AV model is effectively evaluated.
25 February 2026 in Nature Communications
Autonomous vehicles remain commercially limited largely due to safety performance stagnation. Existing deep learning, heavily reliant on failure data from rare safety-critical events, suffers from the seesaw effect—improvement in some scenarios causes regression in others. We introduce an innovative dense learning approach that prioritizes both informative failures and successes, informed by theoretical findings. Data is sampled proportionally to its contribution to the policy gradient and exposure frequency, excluding non-informative samples. This densifies the training dataset’s information, significantly reducing learning variance without bias, enabling tasks intractable for existing methods. To validate this, we trained a safety-critical driving agent for a highly automated vehicle using mixed reality on an urban test track. Results demonstrate that our approach breaks the performance stagnation, enhancing the model’s overall safety performance by one to two orders of magnitude. This marks a significant stride towards achieving human-level safety and widespread adoption for autonomous vehicles.