公开(公告)号：US20230182725A1

公开(公告)日：2023-06-15

申请号：US17766870

申请日：2021-04-12

Applicant: SOUTHEAST UNIVERSITY

Inventor： Xu LI ,  Weiming HU ,  Jinchao HU ,  Xuefen ZHU

IPC: B60W30/095 ,  G06N3/045 ,  G06N3/0464

CPC classification number: B60W30/0956 ,  G06N3/045 ,  G06N3/0464 ,  B60W2554/4041 ,  B60W2420/52 ,  B60W2554/80 ,  B60W2300/125

Abstract: The present invention discloses a backward anti-collision driving decision-making method for a heavy commercial vehicle. Firstly, a traffic environment model is established, and movement state information of a heavy commercial vehicle and a vehicle behind the heavy commercial vehicle is collected. Secondly, a backward collision risk assessment model based on backward distance collision time is established, and a backward collision risk is accurately quantified. Finally, a backward anti-collision driving decision-making problem is described as a Markov decision-making process under a certain reward function, a backward anti-collision driving decision-making model based on deep reinforcement learning is established, and an effective, reliable and adaptive backward anti-collision driving decision-making policy is obtained. The method provided by the present invention can overcome the defect of lack for research on the backward anti-collision driving decision-making policy for the heavy commercial vehicle in the existing method, can quantitatively output proper steering wheel angle and throttle opening control quantities, can provide effective and reliable backward anti-collision driving suggestions for a driver, and can reduce backward collision accidents.

公开(公告)号：US20170276795A1

公开(公告)日：2017-09-28

申请号：US15511046

申请日：2016-06-27

Applicant: Southeast University

Inventor： Xiyuan CHEN ,  Yang YANG ,  Xiying WANG ,  Bingbo CUI ,  Xinhua TANG ,  Xuefen ZHU

IPC: G01S19/25 ,  G01S19/24 ,  G01S19/23 ,  G01S5/02

CPC classification number: G01S19/256 ,  G01S5/0294 ,  G01S19/235 ,  G01S19/246 ,  G01S19/30

Abstract: The present invention discloses a joint non-coherent integral vector tracking method based on a spatial domain, which is used for further improving the performance of a vector tracking GPS (Global Positioning System) receiver. In a new vector tracking strategy design, a phase discriminator/a frequency discriminator in a traditional vector tracking loop is discarded, and baseband signals of visible satellites in each channel are taken as an observation value after performing non-coherent integration, and EKE (abbreviation of Extended Kalman Filter) is used to estimate directly and to solve the position, the velocity, a clock error, etc. of the GPS receiver. Because of the existence of non-coherent integral calculation, when GPS satellite signals are relatively weak, a carrier to noise ratio of an observation value may be effectively improved, and the tracking sensitivity is improved.