scholarly journals Multi-agent Approach to Predict the Trajectory of Road Infrastructure Agents Using a Convolutional Neural Network

2021 ◽  
Author(s):  
Andrey Azarchenkov ◽  
Maksim Lyubimov
Keyword(s):  
Neural Network ◽  
Autonomous Vehicle ◽  
Autonomous Driving ◽  
Planning System ◽  
Object A ◽  
Additional Information ◽  
Road Map ◽  
Road Users ◽  
The Neural Network ◽  
Multi Agent

The problem of creating a fully autonomous vehicle is one of the most urgent in the field of artificial intelligence. Many companies claim to sell such cars in certain working conditions. The task of interacting with other road users is to detect them, determine their physical properties, and predict their future states. The result of this prediction is the trajectory of road users’ movement for a given period of time in the near future. Based on such trajectories, the planning system determines the behavior of an autonomous-driving vehicle. This paper demonstrates a multi-agent method for determining the trajectories of road users, by means of a road map of the surrounding area, working with the use of convolutional neural networks. In addition, the input of the neural network gets an agent state vector containing additional information about the object. A number of experiments are conducted for the selected neural architecture in order to attract its modifications to the prediction result. The results are estimated using metrics showing the spatial deviation of the predicted trajectory. The method is trained using the nuscenes test dataset obtained from lgsvl-simulator.

scholarly journals End-to-End Autonomous Driving Through Dueling Double Deep Q-Network

2021 ◽  
Author(s):  
Baiyu Peng ◽  
Qi Sun ◽  
Shengbo Eben Li ◽  
Dongsuk Kum ◽  
Yuming Yin ◽  
...  
Keyword(s):  
Neural Network ◽  
State Space ◽  
Learning Algorithm ◽  
Rapid Development ◽  
Autonomous Driving ◽  
Saliency Map ◽  
Hierarchical Architecture ◽  
Link Type ◽  
The Neural Network ◽  
End To End

AbstractRecent years have seen the rapid development of autonomous driving systems, which are typically designed in a hierarchical architecture or an end-to-end architecture. The hierarchical architecture is always complicated and hard to design, while the end-to-end architecture is more promising due to its simple structure. This paper puts forward an end-to-end autonomous driving method through a deep reinforcement learning algorithm Dueling Double Deep Q-Network, making it possible for the vehicle to learn end-to-end driving by itself. This paper firstly proposes an architecture for the end-to-end lane-keeping task. Unlike the traditional image-only state space, the presented state space is composed of both camera images and vehicle motion information. Then corresponding dueling neural network structure is introduced, which reduces the variance and improves sampling efficiency. Thirdly, the proposed method is applied to The Open Racing Car Simulator (TORCS) to demonstrate its great performance, where it surpasses human drivers. Finally, the saliency map of the neural network is visualized, which indicates the trained network drives by observing the lane lines. A video for the presented work is available online, https://youtu.be/76ciJmIHMD8 or https://v.youku.com/v_show/id_XNDM4ODc0MTM4NA==.html.

Design and Realization of Experimental Autonomous Driving System Based on Neural Network Control

2012 ◽  
Vol 241-244 ◽  
pp. 1953-1958
Author(s):  
Qing Fu Kong ◽  
Fan Ming Zeng ◽  
Jie Chang Wu ◽  
Jia Ming Wu
Keyword(s):  
Neural Network ◽  
Autonomous Driving ◽  
Network Control ◽  
Neural Network Control ◽  
Test Results ◽  
Driving System ◽  
Neural Network Controller ◽  
The Neural Network ◽  
Network Controller ◽  
Autonomous Driving System

Intelligent vehicle is an attractive solution to the traffic problems caused by automobiles. An experimental autonomous driving system based on a slot car set is designed and realized in the paper. With the application of a wireless camera equipped on the slot car, the track information is acquired and sent to the controlling computer. A backpropogation (BP) neural network controller is built to imitate the way of player’s thinking. After being trained, the neural network controller can give the proper voltage instructions to the direct current (DC) motor of the slot car according to different track conditions. Test results prove that the development of the autonomous driving system is successful.

Neural-network-based containment control of nonlinear multi-agent systems under communication constraints

2016 ◽  
Vol 36 (2) ◽  
pp. 179-185 ◽  
Author(s):  
Chao Ma
Keyword(s):  
Neural Network ◽  
Continuous Time ◽  
Sampled Data ◽  
Multi Agent Systems ◽  
Communication Constraints ◽  
Containment Control ◽  
Content Type ◽  
Agent Systems ◽  
The Neural Network ◽  
Multi Agent

Purpose The purpose of this paper is to investigate the neural-network-based containment control of multi-agent systems with unknown nonlinear dynamics. Moreover, communication constraints are taken into account to reflect more realistic communication networks. Design/methodology/approach Based on the approximation property of the radial basis function neural networks, the control protocol for each agent is designed, where all the information is exchanged in the form of sampled data instead of ideal continuous-time communications. Findings By utilizing the Lyapunov stability theory and the Lyapunov–Krasovskii functional approach, sufficient conditions are developed to guarantee that all the followers can converge to the convex hull spanned by the stationary leaders. Originality/value As ideal continuous-time communications of the multi-agent systems are very difficult or even unavailable to achieve, the neural-network-based containment control of nonlinear multi-agent systems is solved under communication constraints. More precisely, sampled-data information is exchanged, which is more applicable and practical in the real-world applications.

Fault Prediction Method of the Marine Gas Turbine Based on Neural Network-Markov

2014 ◽  
Vol 538 ◽  
pp. 171-174 ◽  
Author(s):  
Jian Guo Cui ◽  
Long Zhang ◽  
Gui Hua Wang ◽  
Bo Cui ◽  
Li Ying Jiang
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Gas Turbine ◽  
Prediction Method ◽  
Rolling Bearing ◽  
Fault Prediction ◽  
Health State ◽  
Object A ◽  
The Neural Network ◽  
Specific Object

Since the fault of marine gas turbine is difficult to predict accurately, making the rolling bearing as the specific object, a fault prediction model of the marine gas turbine based on Neural Network and Markov method is built through the data analysis, preprocessing and feature extraction for the rolling bearing history test data. First, it uses the neural network method to realize the health state recognition of the marine gas turbine. Then, the fault of the marine gas turbine is predicted by taking advantage of the fault prediction which is based on the Markov model. The results show that the efficiency of fault prediction for the marine gas turbine can be realized better through the fault prediction model constructed in view of the Neural Network and Markov. And it also has a significant practical value in project item.

scholarly journals Optimization of combined production of electricity and hydrogen at nuclear power plants using a neural network

2020 ◽  
Vol 221 ◽  
pp. 01003
Author(s):  
Ilia Lopyrev ◽  
Vadim Golubev ◽  
Daria Voznesenskaya ◽  
Victoria Verbnikova ◽  
Olga Novikova
Keyword(s):  
Neural Network ◽  
Nuclear Power ◽  
Power Plants ◽  
Planning System ◽  
Energy Industry ◽  
Fourth Generation ◽  
Technological Advancement ◽  
Investment Projects ◽  
The Neural Network ◽  
Production Of Hydrogen

This article discusses a project with a basis on implementation of combined production of electricity and hydrogen based on a HTGR reactor in the Primorsky Krai of Russia. One of the major advantages of the fourth-generation reactors of the HTGR type is, that water vapor reaches 800 degrees Celsius, which allows not only to efficiently transfer thermal energy to external circuits, but also to use it in the production of hydrogen using the steam reforming of methane [1]. The results of the research were composed mainly of two fully-calculated investment projects, which showed an significant increase in the economic efficiency of combined production of electricity and hydrogen when included in the neural network planning system. Moreover, further technological advancement in developing this method of forecasting could prove highly beneficial in implementing a higher percentage of renewable energy sourced power plants into energy industry[2].

scholarly journals Randomized Adversarial Imitation Learning for Autonomous Driving

2019 ◽  
Author(s):  
MyungJae Shin ◽  
Joongheon Kim
Keyword(s):  
Autonomous Vehicle ◽  
Autonomous Driving ◽  
Imitation Learning ◽  
Cruise Control ◽  
Driving System ◽  
Derivative Free Optimization ◽  
Derivative Free ◽  
Multi Agent ◽  
Lane Keeping ◽  
Autonomous Driving System

With the evolution of various advanced driver assistance system (ADAS) platforms, the design of autonomous driving system is becoming more complex and safety-critical. The autonomous driving system simultaneously activates multiple ADAS functions; and thus it is essential to coordinate various ADAS functions. This paper proposes a randomized adversarial imitation learning (RAIL) method that imitates the coordination of autonomous vehicle equipped with advanced sensors. The RAIL policies are trained through derivative-free optimization for the decision maker that coordinates the proper ADAS functions, e.g., smart cruise control and lane keeping system. Especially, the proposed method is also able to deal with the LIDAR data and makes decisions in complex multi-lane highways and multi-agent environments.

scholarly journals Explore User Behaviour in Semi-autonomous Driving

2019 ◽  
Vol 1 (1) ◽  
pp. 3871-3880
Author(s):  
Yuan Shi ◽  
Jeyhoon Maskani ◽  
Giandomenico Caruso ◽  
Monica Bordegoni
Keyword(s):  
Autonomous Vehicle ◽  
Autonomous Driving ◽  
Lateral Position ◽  
Steering Wheel ◽  
Physiological Indicators ◽  
The Road ◽  
Road Map ◽  
Human Driver ◽  
And Performance ◽  
Physiological Sensors

AbstractThe control shifting between a human driver and a semi-autonomous vehicle is one of the most critical scenarios in the road-map of autonomous vehicle development. This paper proposes a methodology to study driver's behaviour in semi-autonomous driving with physiological-sensors-integrated driving simulators. A virtual scenario simulating take-over tasks has been implemented. The behavioural profile of the driver has been defined analysing key metrics collected by the simulator namely lateral position, steering wheel angle, throttle time, brake time, speed, and the take-over time. In addition, heart rate and skin conductance changes have been considered as physiological indicators to assess cognitive workload and reactivity. The methodology has been applied in an experimental study which results are crucial for taking insights on users’ behaviour. Results show that individual different driving styles and performance are able to be distinguished by calculating and elaborating the data collected by the system. This research provides potential directions for establishing a method to characterize a driver's behaviour in a semi-autonomous vehicle.

scholarly journals A Review on Autonomous Driving Systems

2018 ◽  
Vol 5 (1) ◽  
pp. 1-16
Author(s):  
Salma Yaakub ◽  
Mohammed Hayyan Alsibai
Keyword(s):  
Autonomous Vehicles ◽  
Power Efficiency ◽  
Autonomous Vehicle ◽  
Autonomous Driving ◽  
Planning System ◽  
Ground Vehicles ◽  
Traffic Crashes ◽  
Traffic System ◽  
Surrounding Environment ◽  
Analysis System

Autonomous vehicles are one of the promising solutions to reduce traffic crashes and improve mobility and traffic system. An autonomous vehicle is preferable because it helps in reducing the need for redesigning the infrastructure and because it improves the vehicle power efficiency in terms of cost and time taken to reach the destination. Autonomous vehicles can be divided into 3 types: Aerial vehicles, ground vehicles and underwater vehicles. General, four basic subsystems are integrated to enable a vehicle to move by itself which are: Position identifying and navigation system, surrounding environment situation analysis system, motion planning system and trajectory control system. In this paper, a review on autonomous vehicles and their related technological applications is presented to highlight the aspects of this industry as a part of industry 4.0 concept. Moreover, the paper discusses the best autonomous driving systems to be applied on our wheelchair project which aims at converting a manual wheelchair to a smart electric wheelchair

scholarly journals USING NEURAL NETWORKS TO DETECT OBJECTS IN MLS POINT CLOUDS BASED ON LOCAL POINT NEIGHBORHOODS

2019 ◽  
Vol IV-2/W7 ◽  
pp. 17-24
Author(s):  
B. Borgmann ◽  
M. Hebel ◽  
M. Arens ◽  
U. Stilla
Keyword(s):  
Neural Network ◽  
Point Clouds ◽  
Training Data ◽  
Actual Object ◽  
Object A ◽  
The Neural Network ◽  
Local Point ◽  
Object Center ◽  
Training Examples ◽  
Multiple Neighborhoods

<p><strong>Abstract.</strong> This paper presents an approach which uses a <i>PointNet</i>-like neural network to detect objects of certain types in MLS point clouds. In our case, it is used for the detection of pedestrians, but the approach can easily be adapted to other object classes. In the first step, we process local point neighborhoods with the neural network to determine a descriptive feature. This is then further processed to generate two outputs of the network. The first output classifies the neighborhood and determines if it is part of an object of interest. If this is the case, the second output determines where it is located in relation to the object center. This regression output allows us to use a voting process for the actual object detection. This processing step is inspired by approaches based on implicit shape models (ISM). It is able to deal with a certain amount of incorrectly classified neighborhoods, since it combines the results of multiple neighborhoods for the detection of an object. A benefit of our approach as compared to other machine learning methods is its low demand for training data. In our experiments, we achieved a promising detection performance even with less than 1000 training examples.</p>

scholarly journals Behaviour Cloning for Autonomous Driving

Webology ◽  
2020 ◽  
Vol 17 (2) ◽  
pp. 694-705
Author(s):  
T. Kirthiga Devi ◽  
Akshat Srivatsava ◽  
Kritesh Kumar Mudgal ◽  
Ranjnish Raj Jayanti ◽  
T. Karthick
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Autonomous Vehicle ◽  
Autonomous Driving ◽  
Lane Detection ◽  
Human Intervention ◽  
Steering Angle ◽  
Steering Mechanism ◽  
Deep Learning Model

The objective of this project is to automate the process of driving a car. The result of this project will surely reduce the number of hazards happening everyday. Our world is in progress and self driving car is on its way to reach consumer‟s door-step but the big question still lies that will people accept such a car which is fully automated and driverless. The idea is to create an autonomous Vehicle that uses only some sensors (collision detectors, temperature detectors etc.) and camera module to travel between destinations with minimal/no human intervention. The car will be using a trained Convolutional Neural Network (CNN) which would control the parameters that are required for smoothly driving a car. They are directly connected to the main steering mechanism and the output of the deep learning model will control the steering angle of the vehicle. Many algorithms like Lane Detection, Object Detection are used in tandem to provide the necessary functionalities in the car.

Sign in / Sign up

Export Citation Format

Share Document