Search

Your search keyword '"Dai, Kunpeng"' showing total 21 results
Start Over Author "Dai, Kunpeng"
21 results on '"Dai, Kunpeng"'

1. A Real-time Critical-scenario-generation Framework for Testing Autonomous Driving System

Author

Xie, Yizhou, Dai, Kunpeng, and Zhang, Yong

Subjects
Computer Science - Robotics, Electrical Engineering and Systems Science - Systems and Control
Abstract

In order to find the most likely failure scenarios which may occur under certain given operation domain, critical-scenario-based test is supposed as an effective and widely used method, which gives suggestions for designers to improve the developing algorithm. However, for the state of art, critical-scenario generation approaches commonly utilize random-search or reinforcement learning methods to generate series of scenarios for a specific algorithm, which takes amounts of computing resource for testing a developing target that is always changing, and inapplicable for testing a real-time system. In this paper, we proposed a real-time critical-scenario-generation (RTCSG) framework to address the above challenges. In our framework, an aggressive-driving algorithm is proposed in controlling the virtual agent vehicles, a specially designed cost function is presented to guide scenarios to evolve towards critical conditions, and a self-adaptive coefficient iteration is designed that enable the approach to operate successfully in different conditions. With our proposed method, the critical-scenarios can be directly generated for the target under test which is a black-box system, and the real-time critical-scenario test can be brought into reality. The simulation results show that our approach is able to obtain more critical scenarios in most conditions than current methods, with a higher stability of success. For a real-time testing, our approach improves the efficiency around 16 times., Comment: 7pages,9 figures, 21 references

Published
2022

2. Inter-target Occlusion Handling in Multi-vehicle Corner Tracking Based on Labeled Multi-Bernoulli Filter with Detection Probability Optimization Model

Author

Dai, Kunpeng, Wang, Yafei, Wang, Shuai, Yin, Chengliang, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Zhang, Junjie James, Series Editor, and Zhang, Zhenyuan, editor

Published
2022
Full Text
View/download PDF

7. A real‐time critical‐scenario‐generation framework for defect detection of autonomous driving system.

Author

Xie, Yizhou, Zhang, Yong, Dai, Kunpeng, and Yin, Chengliang

Subjects
AUTONOMOUS vehicles, COST functions, DRIVERLESS cars, ADAPTIVE control systems, PREDICTION models, AGGRESSIVE driving
Abstract

To find the most‐likely‐failure scenarios given a certain operation domain, a critical‐scenario‐based test is supposed as an effective method. However, for the state of the art, critical‐scenario‐generation approaches commonly based on random‐search and take amounts of computing resource, some of them are also inapplicable in real time. Moreover, the approaches sometimes fail to obtain critical results, which are strongly relevant to the choice of initial condition. In order to address the above challenges, the authors proposed a Real‐time Critical‐scenario‐generation framework in this paper. The authors proposed an aggressive‐driving algorithm based on the model predictive control method to lead the agent vehicle. The agent vehicle will be controlled to directly create critical scenarios for a black‐box target under test, and the real‐time critical‐scenario test can be brought into reality. A specially designed cost function is presented that guides scenarios to evolve towards the interested conditions, and a self‐adaptive coefficient iteration is designed that enables the approach to be applied within a wider range of initial conditions. The authors carried out both simulation and Vehicle‐in‐the‐Loop (VIL) test; in the VIL test, the authors' approach improves 15.45% criticality of scenarios with around 9.7 times of efficiency, or improves 38.67% criticality with still around 1.7 times of efficiency with further iterations. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

12. 11THz GaAs Terahertz Schottky Barrier Diode with Sub 0.5 fF $C_{\mathrm{j}0}$

Author

Daoyu Fan, Tangsheng Chen, Bin Niu, Gang Lin, Hai-Yan Lu, and Dai Kunpeng

Subjects
chemistry.chemical_compound, Materials science, Equivalent series resistance, Condensed matter physics, chemistry, Terahertz radiation, Schottky diode, Wafer, Omega, Cutoff frequency, Gallium arsenide, Anode
Abstract

GaAs terahertz schottky barrier diode SBD has been a major technology in terahertz wave multiplexing, mixing and direct detection for decades, due to its high mobility and low capacity. In this paper, T-anode GaAs terahertz SBD was presented with its $C_{\mathrm{j}0}$ scaled into sub-fF range. Scalling C-V measurement showed $C_{\mathrm{j}0}$ without parasitic capacity reached 0.476fF for the $0.5\mu\mathrm{m}$ anode diameter device. With the relative low series resistance R s of $28.8\mathrm{\Omega}$ , cutoff frequency $f_{\mathrm{t}}$ reached 11.6THz. The whole process was based on 4 inch GaAs wafer, guarantee stability and conformity in terahertz GaAs SBD integrated circuits working over 1THz.

Published
2020

16. Relationship Analysis of Central Venous-to-arterial Carbon Dioxide Difference and Cardiac Index for Septic Shock

Author

Ming Yin, Dai Kunpeng, Kong Jichang, Guo Zhiqiang, Tian Zuo, Bao Yong, Wang Bin, and Guangyan Yu

Subjects
0301 basic medicine, Male, medicine.medical_specialty, Resuscitation, Mean arterial pressure, Time Factors, Disease-free survival, Cardiac index, lcsh:Medicine, Article, Veins, 03 medical and health sciences, 0302 clinical medicine, Internal medicine, Heart rate, medicine, Humans, lcsh:Science, Multidisciplinary, business.industry, Septic shock, Myocardium, lcsh:R, Central venous pressure, Hemodynamics, Health care, Arteries, Carbon Dioxide, Middle Aged, medicine.disease, Shock, Septic, Confidence interval, 030104 developmental biology, ROC Curve, Shock (circulatory), Cardiology, lcsh:Q, Female, medicine.symptom, business, 030217 neurology & neurosurgery
Abstract

To analyze the relationship of the central venous-to-arterial carbon dioxide difference (p(cv-a)CO2) and cardiac index (CI) in patients with septic shock, an observational study was conducted in intensive care unit (ICU). 66 consecutive patients with septic shock and central venous oxygen saturation (ScvO2) ≥ 70% were included after early fluid resuscitation. Measurements were taken at a 6 h interval (T0, T6, T12, T18, T24) during first 24 h after their admission into ICU, including heart rate (HR), mean arterial pressure (MAP), central venous pressure (CVP), p(cv-a)CO2, cardiac index(CI, L/(min•m2)) and ScvO2. Patients were divided into low p(cv-a)CO2 group (n = 35) and high p(cv-a)CO2 group (n = 31) according to a threshold of 6 mmHg for p(cv-a)CO2 at T0. As a result, at T0, T6, T12, T18 and T24, there were respectively significant differences between low and high p(cv-a)CO2 groups for CI (4.1 ± 1.4 vs 2.4 ± 0.6, 4.4 ± 0.9 vs 2.8 ± 0.7, 4.1 ± 1.3 vs 2.9 ± 0.6, 4.0 ± 1.3 vs 2.7 ± 0.8, 4.2 ± 1.4 vs 2.9 ± 0.8, p p(cv-a)CO2 group and 22.8% (8/35) for low p(cv-a)CO2 group (p > 0.05), there were significant differences for p(cv-a)CO2 (p p(cv-a)CO2 groups, no differences for HR, MAP, CVP, ScvO2 (p > 0.05). CI was inversely correlated with p(cv-a)CO2 value (r = −0.804, p 2(r = 0.08, p > 0.05). Receiver operating characteristic curve analysis confirmed the correlation of p(cv-a)CO2 with CI (AUC: 0.782;p 2) was p(cv-a)CO2 of 5.55 mmHg or lower with a sensitivity of 85.7% and specificity of 66.8%. Hence CI measured with USCOM is inversely correlated with p(cv-a)CO2 values in guiding the resuscitation of patients with septic shock.

Published
2018

Catalog

Books, media, physical & digital resources
See catalog results