Test Scenario Generation and Optimization Technology for Intelligent Driving Systems

Duan, Jianli; Gao, Feng; He, Yingdong

doi:10.1109/mits.2019.2926269

Cited by 66 publications

(22 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, a systematic approach based on the topological model set up in Section 3 is presented to realize improvement by analysis of the importance of technical factors with EWM [17,18] and evaluation of both technical and untechnical factors together using AHP [19,20].…”

Section: Model-based Analysis and Improvementmentioning

confidence: 99%

“…Other aspects are subjective and difficult to be evaluated quantitatively. To make full use of the engineer's experience, meanwhile eliminate the influence of subjectivity as far as possible, the Delphi method is adopted [19][20][21]. By this approach, the elements at the same layer are evaluated comparatively and can be graded by the nine-points method (1 for lowest priority and 9 for highest priority).…”

Section: Improvement Solution Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Model-Based Analysis and Improvement of Vehicle Radiation Emissions at Low Frequency

Gao

Wang

Xiong³

2021

Applied Sciences

Self Cite

View full text Add to dashboard Cite

With the development of electrification and intelligence, the electromagnetic environment of intelligent and electric vehicles becomes complicated and critical because of the high voltage/current of power components, the computation units with high frequency and the dense radio systems. These pose great challenges for the design of vehicle radiation emissions. To improve the development efficiency, a model-based analysis and improvement strategy is proposed. Firstly, a topological approach is presented to decouple and model the vehicle-level radiation problem. By this topological model, each technical factor is analyzed from both of its contribution and sensitivity to the radiation emission, which are further integrated together using the entropy weight method to generate the technical evaluation score. Then, other untechnical factors, i.e., the cost and application difficulty, are further combined with the technical evaluation results by the analytic hierarchy process to determine the final solution. This strategy has been applied to solve a radiation problem of an electric vehicle at low frequency to validate its effectiveness and show some application details.

show abstract

Section: Model-based Analysis and Improvementmentioning

confidence: 99%

Section: Improvement Solution Selectionmentioning

confidence: 99%

Model-Based Analysis and Improvement of Vehicle Radiation Emissions at Low Frequency

Gao

Wang

Xiong³

2021

Applied Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…The two detectors: the proposed hybrid detector and the single CNN detector with 19 layers, which have same performance on training dataset in Table 3 have been directly tested with our development platform of automatic driving as shown in Fig. 8 [35]. The high definition camera installed on the vehicle roof outputs the image and the detection algorithm runs in an industrial process computer (CPU I7 6700TE, GPU NVIDIA GeForce GTX1050) fixed in the trunk.…”

Section: Experimental Validation and Analysismentioning

confidence: 99%

Hybrid strategy for traffic light detection by combining classical and self‐learning detectors

Gao

Wang

2020

IET Intelligent Transport Systems

Self Cite

View full text Add to dashboard Cite

“…To analyze the influence of driving style on UD and train the driver model, a driver in loop test platform was set up and used to acquire the driving data for safety, efficiency and cost. The driver simulator is set up as FIGURE 2 (a), where the commercial software for the simulation evaluation of automatic driving systems, Prescan, is adopted to simulate the traffic scenario and the vehicle dynamical behavior is provided by a real-time simulator from dSPACE including the hardware system, MicroLab, and the vehicle dynamical model, ASM [39]. Here, the driver simulator is used to acquire the driving data and validate the proposed cooperation strategy in consideration of the following factors:…”

Section: A Driver Simulator and Test Scenariomentioning

confidence: 99%

Driving Capability-Based Transition Strategy for Cooperative Driving: From Manual to Automatic

2020

Self Cite

View full text Add to dashboard Cite

In open traffic environments, humans still have to remain in the control loop of vehicle due to the insufficient of the existing technologies and their high costs. For the realization of cooperation between the human and the automatic driving system, the determination of the time when automatic driving is necessary is very important. To avoid unnecessary intervention when the driver has the control authority of vehicle, a new driving capability-based transition strategy was proposed, which comprehensively considers the driver's correction ability and the driving risk. The transition time from the human driver to the automatic driving system is determined by an unreliable domain (UD), whose boundary is modeled according to the driving data recorded by a driving simulator and statistically described by a log-normal distribution. Furthermore, an adaptive algorithm is designed to update the parameters of UD boundary online to make this strategy suitable for different drivers. This UD-based transition strategy is validated by several tests on the driving simulator. The bench test results show that the individual driving characteristic can be identified by the adaptive algorithm in time, the transition time determined by UD is more accurate, and sufficient time is reserved for the correction carried out by the automatic driving system. INDEX TERMS Automatic driving, human-machine cooperation, driving capability, correction ability, driving risk.

show abstract

Test Scenario Generation and Optimization Technology for Intelligent Driving Systems

Cited by 66 publications

References 36 publications

Model-Based Analysis and Improvement of Vehicle Radiation Emissions at Low Frequency

Model-Based Analysis and Improvement of Vehicle Radiation Emissions at Low Frequency

Hybrid strategy for traffic light detection by combining classical and self‐learning detectors

Driving Capability-Based Transition Strategy for Cooperative Driving: From Manual to Automatic

Contact Info

Product

Resources

About