Intelligent driving intelligence test for autonomous vehicles with naturalistic and adversarial environment

Feng, Shuo; Yan, Xintao; Sun, Haitian; Feng, Yiheng; Liu, Henry

doi:10.1038/s41467-021-21007-8

Cited by 219 publications

(119 citation statements)

References 28 publications

Supporting

Mentioning

117

Contrasting

Unclassified

Order By: Relevance

“…To solve the overvalue problem of worst cases, Feng et al (38)(39)(40)(41) proposed a new definition of scenario criticality, which can be computed as a combination of maneuver challenge and exposure frequency, and generated critical cases using optimization methods and reinforcement learning techniques on various environment settings, including cut-in scenarios and car-following scenarios. To further address the challenge brought by the high dimensionality of complex environments (e.g., highway driving), Feng et al (12) proposed a framework of generating a naturalistic and adversarial driving environment by adding sparse but adversarial adjustments to the NDE. Akagi et al (42) use a self-defined risky index and NDD to sample critical cut-in scenarios.…”

Section: Corner Case Generation For Vehicle Decision-makingmentioning

confidence: 99%

“…To comprehensively evaluate the performance of CAVs, it is crucial to test the CAVs in different scenarios, especially the safety-critical ones. In a naturalistic driving environment (NDE), however, safety-critical scenarios rarely happen, so it is very time-consuming and inefficient to collect corner cases from either on-road test or simulation test of NDE (12,13). Therefore, how to purposely and systematically generate corner cases becomes an important problem.…”

mentioning

confidence: 99%

“…Using naturalistic driving data (NDD), the empirical distributions of BV's actions can be obtained for every state. By sampling actions of BVs from the distributions at each time step, the NDE can be generated (12,13). Based on this formulation, the corner case generation problem of the driving environment is equivalent to optimizing the behavior policy of BVs to improve the probability of corner cases.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Corner Case Generation and Analysis for Safety Assessment of Autonomous Vehicles

Sun

Feng

Yan

et al. 2021

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Corner Case Generation For Vehicle Decision-makingmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Corner Case Generation and Analysis for Safety Assessment of Autonomous Vehicles

Sun

Feng

Yan

et al. 2021

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

show abstract

“…The development of autonomous vehicles will depend on the detection system design [14,15] and processor speed [16,17], which are high-tech products. In order to achieve this development, it is also important to support sensor production and logistically.…”

Section: Introductionmentioning

confidence: 99%

Automatic decision making system with environmental and traffic data

Ersoy¹,

Waqar²,

Toptaş³

2021

Math. models, eng.

View full text Add to dashboard Cite

By using computer vision and machine learning methods, driving lane detection and tracking, the position of the vehicles in the vicinity, their speed and direction will be determined through real-time processing of images taken from the traffic camera. Processing of the collected data using artificial intelligence and fuzzy logic and to calculate the data within the scope of "game theory" and to implement the dynamic control of the vehicle in the light of calculated data is planned. In addition to that, the designed system can also function as a driver assistant for non-autonomous vehicles with an appropriate user interface. First, the positions of the vehicles and driving lanes will be detected and monitored using computer vision and machine learning methods. Then, the vehicle speeds will be calculated by taking advantage of the historical data of the vehicle positions in the surrounding area from the previous observations, and the location estimation will be made by creating probability distributions of where each vehicle will be in the future. With the position estimation and the obtained speed information, it will be ensured that the vehicle is in the safest position in the transportation process to the destination and that it travels again at the safest speed.

show abstract

“…Although there has been significant work undertaken to develop real-world simulation environments for testing AVs 12 , field testing on public roads provides real-world insights that could also help inform the development of simulation environments. This study leverages the Waymo open dataset, providing access to a significant range of autonomous miles driven 9,13 across different environments and interactions.…”

Section: Introductionmentioning

confidence: 99%

Interactions Between Human-Driven and Autonomous Vehicles on Public Roads

Sinha

Radwan²,

Dixit

2021

Preprint

View full text Add to dashboard Cite

To achieve the level of safety and efficiencies promised by autonomous vehicles (AVs), understanding of interactions between human driven vehicles and AVs is crucial. The limited access to publicly available AV data in the field has been the main source of challenge to explore these questions. Using recently released annotated AV data released by Waymo, we investigate interactions between AVs with Human-driven manual vehicles (MVs) in a public road environment. A scalable methodology is presented to study interactions between AVs and MVs. This research reports two main findings (a) AVs tend to be more conservative than MVs at higher speeds on arterials and at lower speeds on freeways (b) No statistical differences in the mean reaction times between MVs and AVs, however, MVs following MVs were found to have statistically significantly lower variance in reaction times. These findings demonstrate the broader impacts of AVs on traffic flow and capacity.

show abstract

Intelligent driving intelligence test for autonomous vehicles with naturalistic and adversarial environment

Cited by 219 publications

References 28 publications

Corner Case Generation and Analysis for Safety Assessment of Autonomous Vehicles

Corner Case Generation and Analysis for Safety Assessment of Autonomous Vehicles

Automatic decision making system with environmental and traffic data

Interactions Between Human-Driven and Autonomous Vehicles on Public Roads

Contact Info

Product

Resources

About