State Estimation of Drive-by-Wire Chassis Vehicle Based on Dual Unscented Particle Filter Algorithm

Accurate vehicle dynamic information plays an important role in vehicle driving safety.However,due to the characteristics of high mobility and multiple controllable degrees of freedom of drive-by-wire chassis vehicles,the current mature application of traditional vehicle state estimation algorithms can not meet the requirements of drive-by-wire chassis vehicle state estimation.This paper proposes a state estimation method for drive-by-wire chassis vehicle based on the dual unscented particle filter algorithm,which make full use of the known advantages of the four-wheel drive torque and steer angle parameters of the drive-by-wire chassis vehicle.In the dual unscented particle filter algorithm,two unscented particle filter transfer information to each other,observe the vehicle state information and the tire force parameter information of the four wheels respectively,which reduce the influence of parameter uncertainty and model parameter changes on the estimation accuracy during driving.The performance with the dual unscented particle filter algorithm,which is analyzed in terms of the time-average square error,is superior of the unscented Kalman filter algorithm.The effectiveness of the algorithm is further verified by driving simulator test.In this paper,a vehicle state estimator based on dual unscented particle filter algorithm was proposed for the first time to improve the estimation accuracy of vehicle parameters and states.

Human-like lane-changing trajectory planning algorithm for human-machine conflict mitigation

The purpose of this paper is to alleviate the potential safety problems associated with the human driver and the automatic system competing for the right of way due to different objectives by mitigating the human-machine conflict phenomenon in human-machine shared driving(HMSD)technology from the automation system.Firstly,a basic lane-changing trajectory algorithm based on the quintic polynomial in the Frenet coordinate system is developed.Then,in order to make the planned trajectory close to human behavior,naturalistic driving data is collected,based on which some lane-changing performance features are selected and analyzed.There are three aspects have been taken into consideration for the human-like lane-changing trajectory:vehicle dynamic stability performance,driving cost optimization,and collision avoidance.Finally,the HMSD experiments are conducted with the driving simulator to test the potential of the human-like lane-changing trajectory planning algorithm.The results demonstrate that the lane-changing trajectory planning algorithm with the highest degree of personalization is highly consistent with human driver behavior and consequently would potentially mitigate the human-machine conflict with the HMSD application.Furthermore,it could be further employed as an empirical trajectory prediction result.The algorithm employs the distribution state of the historical trajectory for human-like processing,simplifying the operational process and ensuring the credibility,integrity,and interpretability of the results.Moreover,in terms of optimization processing,the form of optimization search followed by collision avoidance detection is adopted to in principle reduce the calculation difficulty.Additionally,a new convex polygon collision detection method,namely the vertex embedding method,is proposed for collision avoidance detection.

Scale variant vehicle object recognition by CNN module of multipooling- PCA process

The moving vehicles present different scales in the image due to the perspective effect of different viewpoint distances.The premise of advanced driver assistance system(ADAS)system for safety surveillance and safe driving is early identification of vehicle targets in front of the ego vehicle.The recognition of the same vehicle at different scales requires feature learning with scale invariance.Unlike existing feature vector methods,the normalized PCA eigenvalues calculated from feature maps are used to extract scale-invariant features.This study proposed a convolutional neural network(CNN)structure embedded with the module of multi-pooling-PCA for scale variant object recognition.The validation of the proposed network structure is verified by scale variant vehicle image dataset.Compared with scale invariant network algorithms of Scale-invariant feature transform(SIFT)and FSAF as well as miscellaneous networks,the proposed network can achieve the best recognition accuracy tested by the vehicle scale variant dataset.To testify the practicality of this modified network,the testing of public dataset ImageNet is done and the comparable results proved its effectiveness in general purpose of applications.