scholarly journals Learning Latent Representation of Freeway Traffic Situations from Occupancy Grid Pictures Using Variational Autoencoder

Energies ◽  
2021 ◽  
Vol 14 (17) ◽  
pp. 5232
Author(s):  
Olivér Rákos ◽  
Tamás Bécsi ◽  
Szilárd Aradi ◽  
Péter Gáspár
Keyword(s):  
Autonomous Vehicles ◽  
Dynamic Environment ◽  
Structured Data ◽  
Intelligent Vehicles ◽  
Freeway Traffic ◽  
Occupancy Grid ◽  
Variational Autoencoder ◽  
Long Term Forecasting ◽  
Lower Dimensional

Several problems can be encountered in the design of autonomous vehicles. Their software is organized into three main layers: perception, planning, and actuation. The planning layer deals with the sort and long-term situation prediction, which are crucial for intelligent vehicles. Whatever method is used to make forecasts, vehicles’ dynamic environment must be processed for accurate long-term forecasting. In the present article, a method is proposed to preprocess the dynamic environment in a freeway traffic situation. The method uses the structured data of surrounding vehicles and transforms it to an occupancy grid which a Convolutional Variational Autoencoder (CVAE) processes. The grids (2048 pixels) are compressed to a 64-dimensional latent vector by the encoder and reconstructed by the decoder. The output pixel intensities are interpreted as probabilities of the corresponding field is occupied by a vehicle. This method’s benefit is to preprocess the structured data of the dynamic environment and represent it in a lower-dimensional vector that can be used in any further tasks built on it. This representation is not handmade or heuristic but extracted from the database patterns in an unsupervised way.

A new occupancy grid of the dynamic environment for autonomous vehicles

2014 ◽  
Author(s):  
Yu Xin ◽  
Huawei Liang ◽  
Tao Mei ◽  
Rulin Huang ◽  
Mingbo Du ◽  
...  
Keyword(s):  
Autonomous Vehicles ◽  
Dynamic Environment ◽  
Occupancy Grid

Development of Social and Economic Forecasting and Ideas of A. Anchishkin

2013 ◽  
pp. 143-155
Author(s):  
A. Klepach ◽  
G. Kuranov
Keyword(s):  
Economic Planning ◽  
Special Role ◽  
Economic Management ◽  
Economic Forecasting ◽  
Russian Economy ◽  
World Economic ◽  
Long Term Forecasting ◽  
Working Out

The role of the prominent Soviet economist, academician A. Anchishkin (1933—1987), whose 80th birth anniversary we celebrate this year, in the development of ideas and formation of economic forecasting in the country at the time when the directive planning acted as a leading tool of economic management is explored in the article. Besides, Anchishkin’s special role is noted in developing a comprehensive program of scientific and technical progress, an information basis for working out long-term forecasts of the country’s development, moreover, his contribution to the creation of long-term forecasting methodology and improvement of the statistical basis for economic analysis and economic planning. The authors show that social and economic forecasting in the period after 1991, which has undertaken a number of functions of economic planning, has largely relied on further development of Anchishkin’s ideas, at the same time responding to new challenges for the Russian economy development during its entry into the world economic system.

Pension Reform in Russia: Assessing the Susceptibility of GDP Production to a Shift in the Number of the Working-Age Population

2019 ◽  
pp. 80-86
Author(s):  
T. P. Skufina ◽  
S. V. Baranov
Keyword(s):  
Pension Reform ◽  
Fixed Capital ◽  
Economic Effects ◽  
Pension Scheme ◽  
Retirement Age ◽  
Working Age ◽  
Working Age Population ◽  
Long Term Forecasting ◽  
The Impact

The presented study considers the susceptibility of gross domestic product (GDP) production to a shift in the number of the working-age population due to an increase in retirement age starting with 2019.Aim. The study aims to examine the quantitative assessments of GDP production in Russia with allowance for the changes in the number of the working-age population due to an increase in the actual retirement age.Tasks. The authors forecast the number of the working-age population with allowance for an increase in the retirement age; develop a model to establish a correlation between the number of the workingage population, investment in fixed capital, and GDP production; quantify the impact of the shift in the number of the working-age population on GDP production in Russia. Methods. This study is based on the results of modeling and long-term forecasting.Results. An economic-mathematical model to establish a correlation between the number of the working-age population, investment in fixed capital, and GDP production is presented. To specify the economic effects of a shift in the number of the working-age population due to an increase in the retirement age, Russia’s GDP production is forecasted for the “old” and “new” (increased retirement age) pension scheme. The forecast is provided for three variants of the number of the working-age population.Conclusions. It is found that with the “old” pension scheme with a lower retirement age GDP production across all three variants will decrease by 2036 compared to 2017. With regard to the “new” scheme that increases the retirement age, it is concluded that an increase in the retirement age is a factor that facilitates GDP production. However, its effect on economic growth will be insignificant.

Short to Long-Term Forecasting of River Flows by Heuristic Optimization Algorithms Hybridized with ANFIS

2021 ◽  
Vol 35 (4) ◽  
pp. 1149-1166
Author(s):  
Hossien Riahi-Madvar ◽  
Majid Dehghani ◽  
Rasoul Memarzadeh ◽  
Bahram Gharabaghi
Keyword(s):  
Optimization Algorithms ◽  
Heuristic Optimization ◽  
River Flows ◽  
Long Term Forecasting

scholarly journals Gaussian processes with skewed Laplace spectral mixture kernels for long-term forecasting

2021 ◽  
Author(s):  
Kai Chen ◽  
Twan van Laarhoven ◽  
Elena Marchiori
Keyword(s):  
Gaussian Processes ◽  
Multivariate Time Series ◽  
Heavy Tail ◽  
Lottery Ticket ◽  
Spectral Densities ◽  
Heavy Tailed ◽  
Long Term Forecasting ◽  
The Time Domain ◽  
Spectral Mixture

AbstractLong-term forecasting involves predicting a horizon that is far ahead of the last observation. It is a problem of high practical relevance, for instance for companies in order to decide upon expensive long-term investments. Despite the recent progress and success of Gaussian processes (GPs) based on spectral mixture kernels, long-term forecasting remains a challenging problem for these kernels because they decay exponentially at large horizons. This is mainly due to their use of a mixture of Gaussians to model spectral densities. Characteristics of the signal important for long-term forecasting can be unravelled by investigating the distribution of the Fourier coefficients of (the training part of) the signal, which is non-smooth, heavy-tailed, sparse, and skewed. The heavy tail and skewness characteristics of such distributions in the spectral domain allow to capture long-range covariance of the signal in the time domain. Motivated by these observations, we propose to model spectral densities using a skewed Laplace spectral mixture (SLSM) due to the skewness of its peaks, sparsity, non-smoothness, and heavy tail characteristics. By applying the inverse Fourier Transform to this spectral density we obtain a new GP kernel for long-term forecasting. In addition, we adapt the lottery ticket method, originally developed to prune weights of a neural network, to GPs in order to automatically select the number of kernel components. Results of extensive experiments, including a multivariate time series, show the beneficial effect of the proposed SLSM kernel for long-term extrapolation and robustness to the choice of the number of mixture components.

Sign in / Sign up

Export Citation Format

Share Document