Investigating safety and liability of autonomous vehicles:Bayesian random parameter ordered probit model analysis

Purpose–This study aims to investigate the safety and liability of autonomous vehicles(AVs),and identify the contributing factors quantitatively so as to provide potential insights on safety and liability of AVs.Design/methodology/approach–The actual crash data were obtained from California DMV and Sohu websites involved in collisions of AVs from 2015 to 2021 with 210 observations.The Bayesian random parameter ordered probit model was proposed to reflect the safety and liability of AVs,respectively,as well as accommodating the heterogeneity issue simultaneously.Findings–The findings show that day,location and crash type were significant factors of injury severity while location and crash reason were significant influencing the liability.Originality/value–The results provide meaningful countermeasures to support the policymakers or practitioners making strategies or regulations about AV safety and liability.

Speech recognition algorithm based on neural network and hidden Markov model

This study proposes a hybrid model of speech recognition parallel algorithm based on hidden Markov model( HMM) and artificial neural network( ANN). First,the algorithm uses HMM for time-series modeling of speech signals and calculates the voice to the HMM of the output probability score. Second,with the probability score as input to the neural network,the algorithm gets information for classification and recognition and makes a decision based on the hybrid model. Finally,Matlab software is used to train and test sample data. Simulation results show that using the strong time-series modeling ability of HMM and the classification features of the neural network,the proposed algorithm possesses stronger noise immunity than the traditional HMM. Moreover,the hybrid model corrects the individual flaws of the HMM and the neural network,and greatly improves the speed and performance of speech recognition.

PTMOT: A Probabilistic Multiple Object Tracker Enhanced by Tracklet Confidence for Autonomous Driving

Real driving scenarios,due to occlusions and disturbances,provide disordered and noisy measurements,which makes the task of multi-object tracking quite challenging.Conventional approach is to find deterministic data association;however,it has unstable performance in high clutter density.This paper proposes a novel probabilistic tracklet-enhanced multiple object tracker(PTMOT),which integrates Poisson multi-Bernoulli mixture(PMBM)filter with confidence of tracklets.The proposed method is able to realize efficient and robust probabilistic association for 3D multi-object tracking(MOT)and improve the PMBM filter’s continuity by smoothing single target hypothesis with global hypothesis.It consists of two key parts.First,the PMBM tracker based on sets of tracklets is implemented to realize probabilistic fusion of disordered measure-ments.Second,the confidence of tracklets is smoothed through a smoothing-while-filtering approach.Extensive MOT tests on nuScenes tracking dataset demonstrate that the proposed method achieves superior performance in different modalities.

Cutting-Edge Technologies on Automotive and Mobility Applied in Beijing 2022 Winter Olympics

Electric vehicles(EVs)and intelligent and connected vehicles(ICVs)are promising solutions for a more sustainable environment and safer transportation.For better performance,EVs and ICVs need to address issues in special conditions,such as extremely cold weather,complex routes,and mixed traffic scenarios,where hazards associated with batteries,propulsion systems,and other automotive technologies could pose risks to vehicles.

Crowdsourced Road Semantics Mapping Based on Pixel-Wise Confidence Level

High-definition map has become a vital cornerstone in the navigation of autonomous vehicles in complex traffic scenarios.Thus,the construction of high-definition maps has become crucial.Traditional methods relying on expensive mapping vehicles equipped with high-end sensor equipment are not suitable for mass map construction because of the limitation imposed by its high cost.Hence,this paper proposes a new method to create a high-definition road semantics map using multi-vehicle sensor data.The proposed method implements crowdsourced point-based visual SLAM to align and combine the local maps derived by multiple vehicles.This allows users to modify the extraction process by using a more sophisticated neural network,thus achieving a more accurate detection result when compared with traditional binarization method.The resulting map consists of road marking points suitable for autonomous vehicle navigation and path-planning tasks.Finally,the method is evaluated on the real-world KAIST urban dataset and Shougang dataset to demonstrate the level of detail and accuracy of the proposed map with 0.369 m in mapping errors in ideal condition.