Journal articles: 'Autonomous Train'

1

Guo, Yichen. "Design and research of train-centric autonomous control CBTC system." Applied and Computational Engineering 12, no. 1 (September 25, 2023): 260–67. http://dx.doi.org/10.54254/2755-2721/12/20230364.

Full text

Abstract:

Existing CBTC systems suffer from a number of limitations, some of which include convoluted communication between the ground and trains, costly construction, and high costs associated with the installation of ground equipment. The purpose of this study is to further improve the operational efficiency of a train-centric autonomous CBTC system by analyzing the system design, control principles, and module functioning. The planning of ground and onboard equipment will be the main research objects of the novel system. When compared to conventional CBTC systems, the TACS architecture, most notably in the OC and train-train communication modules, changes the control mode from ground-centric to train-centric. This results in an increase in the overall efficiency of the system, and a new train operation scenario of the virtual coupling is introduced to increase the flexibility. The TACS architecture that was designed paves the way for the engineering advancement of the system and establishes the groundwork for it.

APA, Harvard, Vancouver, ISO, and other styles

2

AFANASOV, A., D. LINIK, S. ARPUL, D. BELUKHIN, and V. VASYLYEV. "PROSPECTS OF USING AUTONOMOUS ELECTRIC TRAINS WITH ONBOARD STORAGE STORES." Transport systems and transportation technologies, no. 23 (July 28, 2022): 46. http://dx.doi.org/10.15802/tstt2022/261652.

Full text

Abstract:

Purpose. Improving the efficiency of passenger traffic on non-electrified sections of the railway of Ukraine by optimizing the structure and creating principles for building a traction electric drive of a promising autonomous electric train powered by traction engines from the system of onboard storage of electricity. Methods. The methodological basis of the study are the general theoretical provisions and principles of the system approach of theoretical electrical engineering, theoretical mechanics, theory of electrical machines and converters. The basic principles of management theory and the basics of decision theory are used. Results. The general principles of construction of the traction electric drive of the perspective autonomous electric train with power supply of traction engines from onboard energy storage devices are formulated. The functional scheme of the traction electric drive of the perspective autonomous electric train is offered, the analysis of work of the electric drive in the modes of traction and regenerative braking is carried out. The mass parameters of two types of energy storage devices, namely electrochemical batteries and supercapacitors, have been determined. The basic requirements to the system of automatic control of the traction drive of the electric train are formulated. It is shown that in the future the use of autonomous battery electric trains will be technically possible and economically justified on non-electrified sections of Ukrzaliznytsia.

APA, Harvard, Vancouver, ISO, and other styles

3

Oh, Sehchan, Kyunghee Kim, and Hyeonyeong Choi. "Train interval control and train-centric distributed interlocking algorithm for autonomous train driving control system." Journal of the Korea Academia-Industrial cooperation Society 17, no. 11 (November 30, 2016): 1–9. http://dx.doi.org/10.5762/kais.2016.17.11.1.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Atherton, Mark, Stuart Hill, David Harrison, and Marco Ajovalasit. "Economic and technical feasibility of a robotic autonomous system for train fluid servicing." Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit 234, no. 3 (February 20, 2019): 338–50. http://dx.doi.org/10.1177/0954409719830520.

Full text

Abstract:

Rail traffic in passenger miles [in the UK] is projected to increase by 100% over the next 30 years, which presents a considerable challenge for the current infrastructure to perform the regular fluid servicing tasks. Developing robotic autonomous systems for train fluid servicing is a prospect for which no solutions currently exist. Therefore, the economic and technical feasibility of a robotic autonomous system to perform several key fluid servicing tasks on passenger train vehicles is investigated. The fluid servicing tasks chosen include those that to a significant degree are repetitive or hazardous for humans to perform, and therefore if performed by a robotic autonomous system will release service personnel to focus on more suitable tasks. The economic and technical cases presented strongly support the use of a robotic autonomous system for fluid servicing of trains. Generally available robotic autonomous system technology has reached a state of development capable of delivering what is required once reliable couplings and fluid hose technologies have been developed for this application. Overall, the findings are that fluid servicing capacity will at least double for around 15% of the cost of an equivalent manual servicing facility, which represents a substantially attractive business case. There will be modest technical challenges to be overcome that will add unknown cost elements such as modifications to vehicle fluid ports for robotic autonomous system compatibility and development of long power hoses.

APA, Harvard, Vancouver, ISO, and other styles

5

Hadas, Zdenek, Jan Smilek, and Ondrej Rubes. "Energy harvesting from passing train as source of energy for autonomous trackside objects." MATEC Web of Conferences 211 (2018): 05003. http://dx.doi.org/10.1051/matecconf/201821105003.

Full text

Abstract:

This paper deals with an energy harvesting review and analysis of an ambient mechanical energy on a trackside during a passing of a train. Trains provide very high level of vibration and deformation which could be converted into useful electricity. Due to maintenance and safety reasons a rail trackside includes sensing systems and number of sensor nodes is increased for modern transportation. Recent development of modern communication and ultra-low power electronics allows to use energy harvesting systems as autonomous source of electrical energy for these trackside objects. Main aim of this paper is model-based design of proposed vibration energy harvesting systems inside sleeper and predict harvested power during the train passing. Measurements of passing train is used as input for simulation models and harvested power is calculated. This simulation of proposed energy harvesting device is very useful for future design.

APA, Harvard, Vancouver, ISO, and other styles

6

Hwang, Jong-Gyu, Sung-Yoon Chae, Byung-Hun Lee, and Rag-Gyo Jeong. "Design of Train Driving Control System for SITL-based Autonomous Train Control Simulator." Journal of Korean Institute of Information Technology 21, no. 11 (November 30, 2023): 71–79. http://dx.doi.org/10.14801/jkiit.2023.21.11.71.

Full text

APA, Harvard, Vancouver, ISO, and other styles

7

Kim, Kyung Min, and Suk-Joon Ko. "Path Search for Autonomous Train via Dial Algorithm." Journal of Korean Institute of Communications and Information Sciences 43, no. 4 (April 30, 2018): 775–83. http://dx.doi.org/10.7840/kics.2018.43.4.775.

Full text

APA, Harvard, Vancouver, ISO, and other styles

8

Lee, Dong-Jin, Ilmu Byun, and Rag-Gyo Jeong. "Integrated Antenna Design for Autonomous Train Control System." Journal of the Korean Society for Railway 27, no. 6 (June 30, 2024): 492–502. http://dx.doi.org/10.7782/jksr.2024.27.6.492.

Full text

APA, Harvard, Vancouver, ISO, and other styles

9

Kim, Hyunkun, Hyeongoo Pyeon, Jong Sool Park, Jin Young Hwang, and Sejoon Lim. "Autonomous Vehicle Fuel Economy Optimization with Deep Reinforcement Learning." Electronics 9, no. 11 (November 13, 2020): 1911. http://dx.doi.org/10.3390/electronics9111911.

Full text

Abstract:

The ever-increasing number of vehicles on the road puts pressure on car manufacturers to make their car fuel-efficient. With autonomous vehicles, we can find new strategies to optimize fuels. We propose a reinforcement learning algorithm that trains deep neural networks to generate a fuel-efficient velocity profile for autonomous vehicles given road altitude information for the planned trip. Using a highly accurate industry-accepted fuel economy simulation program, we train our deep neural network model. We developed a technique for adapting the heterogeneous simulation program on top of an open-source deep learning framework, and reduced dimension of the problem output with suitable parameterization to train the neural network much faster. The learned model combined with reinforcement learning-based strategy generation effectively generated the velocity profile so that autonomous vehicles can follow to control itself in a fuel efficient way. We evaluate our algorithm’s performance using the fuel economy simulation program for various altitude profiles. We also demonstrate that our method can teach neural networks to generate useful strategies to increase fuel economy even on unseen roads. Our method improved fuel economy by 8% compared to a simple grid search approach.

APA, Harvard, Vancouver, ISO, and other styles

10

Jing, Chunhui, Haohong Dai, Xing Yao, Dandan Du, Kaidi Yu, Dongyu Yu, and Jinyi Zhi. "Influence of Multi-Modal Warning Interface on Takeover Efficiency of Autonomous High-Speed Train." International Journal of Environmental Research and Public Health 20, no. 1 (December 25, 2022): 322. http://dx.doi.org/10.3390/ijerph20010322.

Full text

Abstract:

As a large-scale public transport mode, the driving safety of high-speed rail has a profound impact on public health. In this study, we determined the most efficient multi-modal warning interface for automatic driving of a high-speed train and put forward suggestions for optimization and improvement. Forty-eight participants were selected, and a simulated 350 km/h high-speed train driving experiment equipped with a multi-modal warning interface was carried out. Then, the parameters of eye movement and behavior were analyzed by independent sample Kruskal–Wallis test and one-way analysis of variance. The results showed that the current level 3 warning visual interface of a high-speed train had the most abundant warning graphic information, but it failed to increase the takeover efficiency of the driver. The visual interface of the level 2 warning was more likely to attract the attention of drivers than the visual interface of the level 1 warning, but it still needs to be optimized in terms of the relevance of and guidance between graphic–text elements. The multi-modal warning interface had a faster response efficiency than the single-modal warning interface. The auditory–visual multi-modal interface had the highest takeover efficiency and was suitable for the most urgent (level 3) high-speed train warning. The introduction of an auditory interface could increase the efficiency of a purely visual interface, but the introduction of a tactile interface did not improve the efficiency. These findings can be used as a basis for the interface design of automatic driving high-speed trains and help improve the active safety of automatic driving high-speed trains, which is of great significance to protect the health and safety of the public.

APA, Harvard, Vancouver, ISO, and other styles

11

Chai, Ming, Haoxiang Su, and Hongjie Liu. "Long Short-Term Memory-Based Model Predictive Control for Virtual Coupling in Railways." Wireless Communications and Mobile Computing 2022 (February 3, 2022): 1–17. http://dx.doi.org/10.1155/2022/1859709.

Full text

Abstract:

The increasing need for capacity has led the railway industry to explore new train control systems based on a concept called virtual coupling. Inspired by the platooning of autonomous vehicles, the safe operation of virtual coupling is guaranteed by a relative brake distance-based train separation method. This paper proposes a novel long short-term memory (LSTM)-based model predictive control (MPC) method for train operations. An MPC-based control design for virtual coupled train operations is presented. The LSTM is introduced to model the dynamics of the preceding train to approximate the actual train operations. With the train dynamics models, the operation trajectories of the preceding train are predicted based on planned control inputs. A study of a metro line in Chengdu was chosen to analyze the proposed control approach. The simulation results of different scenarios show that compared with the conventional MPC methods, the proposed LSTM-based MPC can reduce the speed differences and position differences of tracking trains by up to 35 % and 25 % , respectively.

APA, Harvard, Vancouver, ISO, and other styles

12

Zhou, Yonghua, Zhenlin Zhang, and Deng Liu. "Analysis of train movement dynamics under various temporal–spatial constraints in fixed-block railway network using extended cellular automaton model." Modern Physics Letters B 28, no. 08 (March 26, 2014): 1450060. http://dx.doi.org/10.1142/s0217984914500602.

Full text

Abstract:

In the fixed-block railway traffic, the trains adjust their speeds in view of their preceding allowable spaces caused by their respective front adjacent trains or specified by scheduling commands. The railway lines have the line-type speed limits within some block sections and the point-type ones at the terminals of block sections. Those speed limits originate from line conditions, scheduling commands and indications of signal equipment. This paper attempts to in detail reveal the train movement mechanism synthetically considering those temporal–spatial constraints. The proposed train movement model defines four kinds of target points and utilizes them to successively engender the instantaneous target points with their corresponding target speeds. It adopts the rule-based description mechanism in cellular automata (CA) but with continuous spaces to replicate restrictive, autonomous and synergistic behaviors of and among trains. The selections of accelerations and decelerations are based upon the data models of practical acceleration and deceleration processes; thereupon, the model is data-driven. The analysis of train movement dynamics through case studies demonstrates that the extended CA model can reproduce the train movement mechanism of grading speed control to satisfy the aforementioned temporal–spatial constraints. The model is applicable to represent the as-is or should-be states of train movements when adjustable parameters are properly configured.

APA, Harvard, Vancouver, ISO, and other styles

13

Hao, Yang, Tao Tang, and Chunhai Gao. "Train Distance Estimation in Turnout Area Based on Monocular Vision." Sensors 23, no. 21 (October 27, 2023): 8778. http://dx.doi.org/10.3390/s23218778.

Full text

Abstract:

Train distance estimation in a turnout area is an important task for the autonomous driving of urban railway transit, since this function can assist trains in sensing the positions of other trains within the turnout area and prevent potential collision accidents. However, because of large incident angles on object surfaces and far distances, Lidar or stereo vision cannot provide satisfactory precision for such scenarios. In this paper, we propose a method for train distance estimation in a turnout area based on monocular vision: firstly, the side windows of trains in turnout areas are detected by instance segmentation based on YOLOv8; secondly, the vertical directions, the upper edges and lower edges of side windows of the train are extracted by feature extraction; finally, the distance to the target train is calculated with an appropriated pinhole camera model. The proposed method is validated by practical data captured from Hong Kong Metro Tsuen Wan Line. A dataset of 2477 images is built to train the instance segmentation neural network, and the network is able to attain an MIoU of 92.43% and a MPA of 97.47% for segmentation. The accuracy of train distance estimation is then evaluated in four typical turnout area scenarios with ground truth data from on-board Lidar. The experiment results indicate that the proposed method achieves a mean RMSE of 0.9523 m for train distance estimation in four typical turnout area scenarios, which is sufficient for determining the occupancy of crossover in turnout areas.

APA, Harvard, Vancouver, ISO, and other styles

14

Al-Khafaji, Israa M. Abdalameer, and A. V. Panov. "FEDERATED LEARNING FOR VISION-BASED OBSTACLE AVOIDANCE IN MOBILE ROBOTS." Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics 23, no. 3 (2023): 35–47. http://dx.doi.org/10.14529/ctcr230304.

Full text

Abstract:

Federated learning (FL) is a machine learning approach that allows multiple devices or systems to train a model collaboratively, without exchanging their data. This is particularly useful for autonomous mobile robots, as it allows them to train models customized to their specific environment and tasks, while keeping the data they collect private. Research Objective to train a model to recognize and classify different types of objects, or to navigate around obstacles in its environment. Materials and me¬thods we used FL to train models for a variety of tasks, such as object recognition, obstacle avoidance, localization, and path planning by an autonomous mobile robot operating in a warehouse FL. We equipped the robot with sensors and a processor to collect data and perform machine learning tasks. The robot must communicate with a central server or cloud platform that coordinates the training process and collects model updates from different devices. We trained a neural network (CNN) and used a PID algorithm to generate a control signal that adjusts the position or other variable of the system based on the difference between the desired and actual values, using the relative, integrative and derivative terms to achieve the desired performance. Results through careful design and execution, there are several challenges to implementing FL in autonomous mobile robots, including the need to ensure data privacy and security, and the need to manage communications and the computational resources needed to train the model. Conclusion. We conclude that FL enables autonomous mobile robots to continuously improve their performance and adapt to changing environments and potentially improve the performance of vision-based obstacle avoidance strategies and enable them to learn and adapt more quickly and effectively, leading to more robust and autonomous systems.

APA, Harvard, Vancouver, ISO, and other styles

15

Bouibed, Kamel, Abdel Aitouche, and Mireille Bayart. "Control and Reconguration of Train of Autonomous Electric Vehicles." Journal of Asian Electric Vehicles 10, no. 1 (2012): 1543–51. http://dx.doi.org/10.4130/jaev.10.1543.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Mahtani, Ankur, Eddy Doba, and Nadia Ammad. "The Autonomous Train vision: Embedded AI for pedestrians monitoring." Transportation Research Procedia 72 (2023): 949–56. http://dx.doi.org/10.1016/j.trpro.2023.11.522.

Full text

APA, Harvard, Vancouver, ISO, and other styles

17

Gao, Yupeng. "Research on the autonomous train control system based on vehicle-to-vehicle communication." Applied and Computational Engineering 6, no. 1 (June 14, 2023): 1495–502. http://dx.doi.org/10.54254/2755-2721/6/20230971.

Full text

Abstract:

In recent years, there has been a significant increase in the importance of rail transit, which is largely due to the development of cities. It is anticipated that a new generation of train control systems will be required as the number of passengers increases and track resources become more limited. Seven driving modes of the autonomous train control system based on vehicle-to-vehicle communication are studied in four aspects: system architecture, control method, driving mode conversion, and system safety analysis. By analyzing the correlation between each operating mode in the normal and abnormal operations scenarios, and taking safety into consideration, this paper proposes a train driving mode conversion scheme that covers the whole scenario of train operation by taking safety into consideration in both normal and abnormal operations. This virtual coupling technology further reduces the overall system headway, thereby allowing for more efficient train control systems to be developed, and is intended to provide a useful reference for the engineering of new train control systems.

APA, Harvard, Vancouver, ISO, and other styles

18

Wang, Shen, Thomas Weber, and Dieter Schramm. "Simulative Study of an Innovative On-Demand Transport System Using a Realistic German Urban Scenario." Future Transportation 3, no. 1 (December 30, 2022): 38–56. http://dx.doi.org/10.3390/futuretransp3010003.

Full text

Abstract:

Trams are a meaningful means of public transport in urban traffic. However, trams have some well-known disadvantages. These include, for example, possibly long distances to the stop, long waiting times, and lack of privacy, among others. The innovative mobility concept “FLAIT-Train” offers solutions to the problems mentioned. The FLAIT-train operates on ordinary roads and is intended to offer DOOR-2-DOOR transport. In the first application phase, the FLAIT-train runs on exclusive lanes but in the future can mix with other traffic. They are designed as vehicles with 2 seats and 1 m width. The vehicle technology of FLAIT-trains is similar/identical to battery-electric autonomous vehicles. This paper uses traffic simulations to investigate whether FLAIT trains are a suitable alternative to conventional trams, taking simulated/theoretical transport capacities in passenger-kilometers per day into account. Using the software SUMO (“Simulation of Urban Mobility”), a realistic traffic scenario is generated. In this scenario, the operation of the FLAIT-Trains and the trams are simulated under the same conditions and based on statistical data. Based on the simulation results, the performances of the FLAIT-Trains and the trams are compared.

APA, Harvard, Vancouver, ISO, and other styles

19

García Cuenca, Laura, Enrique Puertas, Javier Fernandez Andrés, and Nourdine Aliane. "Autonomous Driving in Roundabout Maneuvers Using Reinforcement Learning with Q-Learning." Electronics 8, no. 12 (December 13, 2019): 1536. http://dx.doi.org/10.3390/electronics8121536.

Full text

Abstract:

Navigating roundabouts is a complex driving scenario for both manual and autonomous vehicles. This paper proposes an approach based on the use of the Q-learning algorithm to train an autonomous vehicle agent to learn how to appropriately navigate roundabouts. The proposed learning algorithm is implemented using the CARLA simulation environment. Several simulations are performed to train the algorithm in two scenarios: navigating a roundabout with and without surrounding traffic. The results illustrate that the Q-learning-algorithm-based vehicle agent is able to learn smooth and efficient driving to perform maneuvers within roundabouts.

APA, Harvard, Vancouver, ISO, and other styles

20

Gantumur, B., V. A. Prechissky, M. A. Sleptsov, and A. A. Barat. "ON THE EFFICIENCY OF USING AUTONOMOUS LOCOMOTIVES ON THE RAILWAYS OF MONGOLIA." World of Transport and Transportation 15, no. 1 (February 28, 2017): 100–110. http://dx.doi.org/10.30932/1992-3252-2017-15-1-9.

Full text

Abstract:

[For the English abstract and full text of the article please see the attached PDF-File (English version follows Russian version)].ABSTRACT The requirements of speed, reliability, safety and cost-effectiveness of cargo transportation pose a number of complex logistics tasks for Ulaanbaatar Railroad (UBZhD), including the choice of optimal train mass, series and number of locomotive sections for driving a freight train of a given weight. The mass of the train selected in the course of the study was checked by the condition of starting from the place on the calculated ascent. Based on the analysis of the longitudinal track profile, a computational profile scheme was compiled. Calculation of the minimum traction force of the locomotive was given by the mass of the train, the series and the number of sections. Using the diagrams of the specific slowing and accelerating forces, the train speed curve was constructed by the method of A. I. Lipets, after which by the method of G. V. Lebedev the total train travel time and the operating time of TED in various modes was found, which allows finding the specific fuel consumption. After considering three possible variants, it is established that the combination of locomotives 2TE116UM-23AGAL allows for faster and more economical cargo transportation. Given the equipment of the UBZhD with these locomotives, the idea proposed in the article can be realized on the most heavily stressed sections. Keywords: railway, locomotive, Mongolia, cargo transportation optimization, calculations, efficiency.

APA, Harvard, Vancouver, ISO, and other styles

21

Neto, João Batista Pinto, Lucas de Carvalho Gomes, Miguel Elias Mitre Campista, and Luís Henrique Maciel Kosmalski Costa. "An Accurate GNSS-Based Redundant Safe Braking System for Urban Elevated Rail Maglev Trains." Information 11, no. 11 (November 15, 2020): 531. http://dx.doi.org/10.3390/info11110531.

Full text

Abstract:

The association of elevated rail structures and Maglev (magnetic levitation) trains is a promising alternative for urban transportation. Besides being cost-effective in comparison with underground solutions, the Maglev technology is a clean and low-noise mass transportation. In this paper, we propose a low-cost automatic braking system for Maglev trains. There is a myriad of sensors and positioning techniques used to improve the accuracy, precision and stability of train navigation systems, but most of them result in high implementation costs. In this paper, we develop an affordable solution, called Redundant Autonomous Safe Braking System (RASBS), for the MagLev-Cobra train, a magnetic levitation vehicle developed at the Federal University of Rio de Janeiro (UFRJ), Brazil. The proposed braking system employs GNSS (Global Navigation Satellite System) receivers at the stations and trains, which are connected via an ad-hoc wireless network. The proposed system uses a cooperative error correction algorithm to achieve sub-meter distance precision. We experimentally evaluate the performance of RASBS in the MagLev prototype located at the campus of UFRJ, Brazil. Results show that, using RASBS, the train is able to dynamically set the precise location to start the braking procedure.

APA, Harvard, Vancouver, ISO, and other styles

22

Kwak, Ho-Chan, Ji Young Song, Kyung-Min Kim, and Suk Mun Oh. "Dynamic Route Control Algorithm based on Autonomous Train Control System." Journal of the Korean Society for Railway 24, no. 9 (September 30, 2021): 793–801. http://dx.doi.org/10.7782/jksr.2021.24.9.793.

Full text

APA, Harvard, Vancouver, ISO, and other styles

23

Weichselbaum, Johann, Christian Zinner, Oliver Gebauer, and Wolfgang Pree. "Accurate 3D-vision-based obstacle detection for an autonomous train." Computers in Industry 64, no. 9 (December 2013): 1209–20. http://dx.doi.org/10.1016/j.compind.2013.03.015.

Full text

APA, Harvard, Vancouver, ISO, and other styles

24

Wang, Shen, Thomas Weber, Dieter Schramm, and Thorben Berns. "Simulation-Based Investigation of On-Demand Vehicle Deployment for Night Bus Routes Using the Monte Carlo Method." Future Transportation 4, no. 2 (April 9, 2024): 380–408. http://dx.doi.org/10.3390/futuretransp4020019.

Full text

Abstract:

Public transportation systems, including trams and buses, play a crucial role in urban traffic. However, these traditional modes of transport have some well-known drawbacks, such as long distances between stops, lengthy waiting times, and a lack of privacy. In response to these challenges, an innovative mobility concept called “FLAIT-train” offers potential solutions. The FLAIT-train operates on regular roads and aims to provide DOOR-2-DOOR transport, addressing the issues associated with fixed stops and offering increased accessibility and convenience. In its initial phase, the FLAIT-train operates on exclusive lanes, but it is designed to integrate with other traffic eventually. The vehicle technology of FLAIT-trains closely resembles that of battery electric autonomous vehicles. To assess whether FLAIT-trains can be used as a suitable alternative to conventional public transportation systems, this paper employs traffic simulations that consider key performance indicators, including the average waiting time per passenger, maximum waiting time of a single passenger, average in-vehicle time per passenger, and average occupancy rate of the vehicles. Using SUMO software (“Simulation of Urban Mobility”, version 1.12.0), a night bus service scenario is meticulously designed and generated. Within this scenario, both FLAIT-trains and conventional buses are simulated under identical conditions and based on statistical data.

APA, Harvard, Vancouver, ISO, and other styles

25

Hou, Kaiwen, and George Giannopoulos. "Modeling the Deployment and Management of Large-Scale Autonomous Vehicle Circulation in Mixed Road Traffic Conditions Considering Virtual Track Theory." Future Transportation 4, no. 1 (February 23, 2024): 215–35. http://dx.doi.org/10.3390/futuretransp4010011.

Full text

Abstract:

This paper offers a novel view for managing and controlling the movement of driverless, i.e., autonomous, vehicles by converting this movement to a simulated train movement moving on a rail track. It expands on the “virtual track” theory and creates a model for virtual track autonomous vehicle management and control based on the ideas and methods of railway train operation. The developed model and adopted algorithm allow for large-scale autonomous driving vehicle control on the highway while considering the temporal-spatial distribution of vehicles, temporal-spatial trajectory diagram optimization, and the management and control model and algorithm for autonomous vehicles, as design goals. The ultimate objective is to increase the safety of the road traffic environment when autonomous vehicles are operating in it together with human-driven vehicles and achieve more integrated and precise organization and scheduling of these vehicles in such mixed traffic conditions. The developed model adopted a “particle swarm” optimization algorithm that is tested in a hypothetical network pending a full-scale test on a real highway. The paper concludes that the proposed management and control model and algorithm based on the “virtual track” theory is promising and demonstrates feasibility and effectiveness for further development and future application.

APA, Harvard, Vancouver, ISO, and other styles

26

Arshintsev, Dmitriy, Sergey Tolmachev, and Alexander Brzhezovskiy. "The development of service conditions for special-purpose cars based on the results of full-scale tests." Proceedings of Petersburg Transport University, no. 3 (September 20, 2018): 455–62. http://dx.doi.org/10.20295/1815-588x-2018-3-455-462.

Full text

Abstract:

Objective: To develop the conditions of special cargo railway cars, multi-axis container cars and railway non-autonomous multiple unit trains circulation for transportation of special-purpose goods on public railways of OAO “RZhD”. The speeds of such trains can be higher in comparison with the speeds established by the existing normative documents of JSC “Russian Railways” for cargo trains. Special-purpose cars in nominal loading mode circulate in a train set with a unit locomotive. Methods: The assessment of conditions of the special-purpose rolling stock circulation was carried out by the results of tests on the line as well as the impact on the track and pointwork in the accredited centers, based on the regulations of GOST R 55050–2012. Results: The conditions for the ﬂeet circulation consisting of 8–32-axle special-purpose railway cars, multiaxial container cars and non-autonomous multiple unit trains were established. Practical importance: A set of regulatory documents of JSC “Russian Railways” was developed in the form of regulations on technical conditions of special-purpose railway cars, conveyors and multiple unit trains designed for transportation of special purpose freight.

APA, Harvard, Vancouver, ISO, and other styles

27

Oppelt, Maximilian P., Andreas Foltyn, Jessica Deuschel, Nadine R. Lang, Nina Holzer, Bjoern M. Eskofier, and Seung Hee Yang. "ADABase: A Multimodal Dataset for Cognitive Load Estimation." Sensors 23, no. 1 (December 28, 2022): 340. http://dx.doi.org/10.3390/s23010340.

Full text

Abstract:

Driver monitoring systems play an important role in lower to mid-level autonomous vehicles. Our work focuses on the detection of cognitive load as a component of driver-state estimation to improve traffic safety. By inducing single and dual-task workloads of increasing intensity on 51 subjects, while continuously measuring signals from multiple modalities, based on physiological measurements such as ECG, EDA, EMG, PPG, respiration rate, skin temperature and eye tracker data, as well as behavioral measurements such as action units extracted from facial videos, performance metrics like reaction time and subjective feedback using questionnaires, we create ADABase (Autonomous Driving Cognitive Load Assessment Database) As a reference method to induce cognitive load onto subjects, we use the well-established n-back test, in addition to our novel simulator-based k-drive test, motivated by real-world semi-autonomously vehicles. We extract expert features of all measurements and find significant changes in multiple modalities. Ultimately we train and evaluate machine learning algorithms using single and multimodal inputs to distinguish cognitive load levels. We carefully evaluate model behavior and study feature importance. In summary, we introduce a novel cognitive load test, create a cognitive load database, validate changes using statistical tests, introduce novel classification and regression tasks for machine learning and train and evaluate machine learning models.

APA, Harvard, Vancouver, ISO, and other styles

28

Singhal, Vivek, Divya Anand, Hani Moaiteq Aljahdali, Nitin Goyal, Aman Singh, and Seifedine Kadry. "An Intelligent and Autonomous Sight Distance Evaluation Framework for Sustainable Transportation." Sustainability 13, no. 16 (August 9, 2021): 8885. http://dx.doi.org/10.3390/su13168885.

Full text

Abstract:

Railways are facing a serious problem of road vehicle–train collisions at unmanned railway level crossings. The purpose of the study is the development of a safe stopping sight distance and sight distance from road to rail track model with appropriate computation and analysis. The scope of the study lies in avoiding road vehicle–train collisions at unmanned railway level crossings. An intelligent and autonomous framework is being developed using supervised machine learning regression algorithms. Further, a sight distance from road to rail track model is being developed for road vehicles of 0.5 to 10 m length using the observed geometric characteristics of the route. The model prediction accuracy obtained better results in the development of a stopping sight distance model in comparison to other intelligent algorithms. The developed model suggested an increment of approximately 23% in the current safe stopping sight distance on all unmanned railway level crossings. Further, the feature analysis indicates the ‘approach road gradient’ to be the major contributing parameter for safe stopping sight distance determination. The accident prediction study finally indicates that, as the safe stopping sight distance is increased by following the developed model, it is predicted to decrease road vehicle–train collisions.

APA, Harvard, Vancouver, ISO, and other styles

29

Heirich, Oliver, Benjamin Siebler, and Erik Hedberg. "Study of Train-Side Passive Magnetic Measurements with Applications to Train Localization." Journal of Sensors 2017 (2017): 1–10. http://dx.doi.org/10.1155/2017/8073982.

Full text

Abstract:

Passive magnetic sensors measure the magnetic field density in three axes and are often integrated on a single chip. These low-cost sensors are widely used in car navigation as well as in battery powered navigation equipment such as smartphones as part of an electronic compass. We focus on a train localization application with multiple, exclusively onboard sensors and a track map. This approach is considered as a base technology for future railway applications such as collision avoidance systems or autonomous train driving. In this paper, we address the following question: how beneficial are passive magnetic measurements for train localization? We present and analyze measurements of two different magnetometers recorded on a regional train at regular passenger service. We show promising correlations of the measurements with the track positions and the traveled switch way. The processed data reveals that the railway environment has repeatable, location-dependent magnetic signatures. This is considered as a novel approach to train localization, as the use of these magnetic signals at first view is not obvious. The proposed methods based on passive magnetic measurements show a high potential to be integrated in new and existing train localization approaches.

APA, Harvard, Vancouver, ISO, and other styles

30

Zanelli, Federico, Marco Mauri, Francesco Castelli-Dezza, Edoardo Sabbioni, Davide Tarsitano, and Nicola Debattisti. "Energy Autonomous Wireless Sensor Nodes for Freight Train Braking Systems Monitoring." Sensors 22, no. 5 (February 27, 2022): 1876. http://dx.doi.org/10.3390/s22051876.

Full text

Abstract:

Nowadays, railway freight transportation is becoming more and more crucial since it represents the best alternative to road transport in terms of sustainability, pollution, and impact on the environment and on public health. Upgrading the potentiality of this kind of transportation, it would be possible to avoid delays in goods deliveries due to road accidents, traffic jams, and other situation occurring on roads. A key factor in this framework is therefore represented by monitoring and maintenance of the train components. Implementing a real time monitoring of the main components and a predictive maintenance approach, it would be possible to avoid unexpected breakdowns and consequently unavailability of wagons for unscheduled repair activities. As highlighted in recent statistical analysis, one of the elements more critical in case of failure is represented by the brake system. In this view, a real time monitoring of pressure values in some specific points of the system would provide significant information on its health status. In addition, since the braking actions are related to the load present on the convoy, thanks to this kind of monitoring, it would be possible to appreciate the different behavior of the system in case of loaded and unloaded trains. This paper presented an innovative wireless monitoring system to perform brake system diagnostics. A low-power system architecture, in terms of energy harvesting and wireless communication, was developed due to the difficulty in applying a wired monitoring system to a freight convoy. The developed system allows acquiring brake pressure data in critical points in order to verify the correct behavior of the brake system. Experimental results collected during a five-month field test were provided to validate the approach.

APA, Harvard, Vancouver, ISO, and other styles

31

Oh, Sehchan, and Young-Jong Cho. "Track Switching Algorithm for the T2T-Based Autonomous Train Control System." Journal of Korean Institute of Communications and Information Sciences 42, no. 11 (November 30, 2017): 2160–69. http://dx.doi.org/10.7840/kics.2017.42.11.2160.

Full text

APA, Harvard, Vancouver, ISO, and other styles

32

Piccioni, Cristiana, Stefano Ricci, Arbra Bardhi, and Polis Karatzas. "Rail Vehicle Accessibility: Towards an Autonomous Train Usage for All Passengers." Transportation Research Procedia 72 (2023): 3260–67. http://dx.doi.org/10.1016/j.trpro.2023.11.863.

Full text

APA, Harvard, Vancouver, ISO, and other styles

33

Xie, Chun Lin. "Research on Applied Technology in Training Autonomous Abilities of Learners." Applied Mechanics and Materials 540 (April 2014): 556–59. http://dx.doi.org/10.4028/www.scientific.net/amm.540.556.

Full text

Abstract:

This research aims at studying the effectiveness of applied technology in training learners’ autonomous learning abilities. Under the circumstance of networking, it is undoubted a new way to train autonomous abilities of learners with applied technology benefits the development of learners in future. Therefore, both instructors and learners have necessity to master and share some skills and strategies of autonomous learning by means of applied technology. It is also essential that learners enhance their abilities to manage their time and develop a positive attitude and a sense of responsibilities towards learning.

APA, Harvard, Vancouver, ISO, and other styles

34

Wang, Wencong, Gang Li, Shuwei Liu, and Qiang Yang. "Trajectory Planning of a Semi-Trailer Train Based on Constrained Iterative LQR." Applied Sciences 13, no. 19 (September 23, 2023): 10614. http://dx.doi.org/10.3390/app131910614.

Full text

Abstract:

With the development of science and technology, self-driving technology is gradually being applied to automobile semi-trailer trains. Aiming at the problem that it is challenging to plan the traveling trajectory of an autonomous semi-trailer train, a trajectory planning algorithm based on a constrained iterative linear quadratic regulator is proposed. The constrained iterative linear quadratic regulator solves the problem that the iterative constrained linear quadratic regulator cannot deal with inequality constraints by transforming inequality constraints into interior point penalty functions to deal with all kinds of inequality constraints in the trajectory planning problem. When dealing with the obstacle avoidance problem, the body contour is modeled approximately according to the actual shape of the vehicle, and the obstacle avoidance constraints are transformed into inequality constraints. Considering the unique body structure of a semi-trailer train, the articulation angle constraint function is designed according to different vehicle speeds. Simulation experimental results show that the algorithm can plan safe driving trajectories for semi-trailer trains in complex traffic scenarios.

APA, Harvard, Vancouver, ISO, and other styles

35

Zhou, Yefang, Yanyan Li, Mingyang Hao, and Toshiyuki Yamamoto. "A System of Shared Autonomous Vehicles Combined with Park-And-Ride in Residential Areas." Sustainability 11, no. 11 (June 2, 2019): 3113. http://dx.doi.org/10.3390/su11113113.

Full text

Abstract:

As suburbanization and unprecedented population aging are converging, enhanced personal mobility for suburban residents is required. In this study, a collaborative scheme involving park-and-ride services associated with public transport and a shared autonomous vehicle system are proposed. Two residential areas in the Nagoya metropolitan region, Japan, are considered: a residential area at the outer edge of a subway line and a commuter town with a nearby railway station. Three user groups are assumed: park-and-ride commuters who park shared autonomous vehicles at the station and take the train to their workplaces; inbound commuters who disembark from trains at the station and use the vehicles to reach their workplaces within the target area; and elderly and disabled residents, who use shared autonomous vehicles for trips within the target area. The system performance is investigated through agent-based simulation. The results suggest that, in the edge case, approximately 400 shared autonomous vehicles can facilitate more than 10,000 trips at an appropriate level of service. For the commuter town, fewer than 400 vehicles can provide rapid responses with a wait time of approximately 5 min for more than 5000 trips per day. Thus, the proposed system can feasibly provide a quick response service.

APA, Harvard, Vancouver, ISO, and other styles

36

Hadas, Zdenek, Ondrej Rubes, Filip Ksica, and Jan Chalupa. "Kinetic Electromagnetic Energy Harvester for Railway Applications—Development and Test with Wireless Sensor." Sensors 22, no. 3 (January 25, 2022): 905. http://dx.doi.org/10.3390/s22030905.

Full text

Abstract:

This paper deals with a development and lab testing of energy harvesting technology for autonomous sensing in railway applications. Moving trains are subjected to high levels of vibrations and rail deformations that could be converted via energy harvesting into useful electricity. Modern maintenance solutions of a rail trackside typically consist of a large number of integrated sensing systems, which greatly benefit from autonomous source of energy. Although the amount of energy provided by conventional energy harvesting devices is usually only around several milliwatts, it is sufficient as a source of electrical power for low power sensing devices. The main aim of this paper is to design and test a kinetic electromagnetic energy harvesting system that could use energy from a passing train to deliver sufficient electrical power for sensing nodes. Measured mechanical vibrations of regional and express trains were used in laboratory testing of the developed energy harvesting device with an integrated resistive load and wireless transmission system, and based on these tests the proposed technology shows a high potential for railway applications.

APA, Harvard, Vancouver, ISO, and other styles

37

Wang, Yang, Yihao Chen, Hao Yuan, and Cheng Wu. "An automated learning method of semantic segmentation for train autonomous driving environment understanding." International Journal of Advances in Intelligent Informatics 10, no. 1 (February 29, 2024): 148. http://dx.doi.org/10.26555/ijain.v10i1.1521.

Full text

Abstract:

One of the major reasons for the explosion of autonomous driving in recent years is the great development of computer vision. As one of the most fundamental and challenging problems in autonomous driving, environment understanding has been widely studied. It directly determines whether the entire in-vehicle system can effectively identify surrounding objects of vehicles and make correct path planning. Semantic segmentation is the most important means of environment understanding among the many image recognition algorithms used in autonomous driving. However, the success of semantic segmentation models is highly dependent on human expertise in data preparation and hyperparameter optimization, and the tedious process of training is repeated over and over for each new scene. Automated machine learning (AutoML) is a research area for this problem that aims to automate the development of end-to-end ML models. In this paper, we propose an automatic learning method for semantic segmentation based on reinforcement learning (RL), which can realize automatic selection of training data and guide automatic training of semantic segmentation. The results show that our scheme converges faster and has higher accuracy than researchers manually training semantic segmentation models, while requiring no human involvement.

APA, Harvard, Vancouver, ISO, and other styles

38

Pfeiffer, Christian, Simon Wengeler, Antonio Loquercio, and Davide Scaramuzza. "Visual attention prediction improves performance of autonomous drone racing agents." PLOS ONE 17, no. 3 (March 1, 2022): e0264471. http://dx.doi.org/10.1371/journal.pone.0264471.

Full text

Abstract:

Humans race drones faster than neural networks trained for end-to-end autonomous flight. This may be related to the ability of human pilots to select task-relevant visual information effectively. This work investigates whether neural networks capable of imitating human eye gaze behavior and attention can improve neural networks’ performance for the challenging task of vision-based autonomous drone racing. We hypothesize that gaze-based attention prediction can be an efficient mechanism for visual information selection and decision making in a simulator-based drone racing task. We test this hypothesis using eye gaze and flight trajectory data from 18 human drone pilots to train a visual attention prediction model. We then use this visual attention prediction model to train an end-to-end controller for vision-based autonomous drone racing using imitation learning. We compare the drone racing performance of the attention-prediction controller to those using raw image inputs and image-based abstractions (i.e., feature tracks). Comparing success rates for completing a challenging race track by autonomous flight, our results show that the attention-prediction based controller (88% success rate) outperforms the RGB-image (61% success rate) and feature-tracks (55% success rate) controller baselines. Furthermore, visual attention-prediction and feature-track based models showed better generalization performance than image-based models when evaluated on hold-out reference trajectories. Our results demonstrate that human visual attention prediction improves the performance of autonomous vision-based drone racing agents and provides an essential step towards vision-based, fast, and agile autonomous flight that eventually can reach and even exceed human performances.

APA, Harvard, Vancouver, ISO, and other styles

39

Kolmogorov, Aleksey, and Nadezhda Zaytseva. "AUTOMATIC COMPUTER LEARNING SYSTEM THE SIMULATOR." Modern Technologies and Scientific and Technological Progress 2024, no. 1 (April 22, 2024): 140–41. http://dx.doi.org/10.36629/2686-9896-2024-1-140-141.

Full text

Abstract:

One of the effective tools of a computer simulator is considered – an automatic training system (AOS) designed to train operators of technological installations on a simulator in an autonomous mode without the participation of an instructor

APA, Harvard, Vancouver, ISO, and other styles

40

Pan, Yunpeng, Ching-An Cheng, Kamil Saigol, Keuntaek Lee, Xinyan Yan, Evangelos A. Theodorou, and Byron Boots. "Imitation learning for agile autonomous driving." International Journal of Robotics Research 39, no. 2-3 (October 14, 2019): 286–302. http://dx.doi.org/10.1177/0278364919880273.

Full text

Abstract:

We present an end-to-end imitation learning system for agile, off-road autonomous driving using only low-cost on-board sensors. By imitating a model predictive controller equipped with advanced sensors, we train a deep neural network control policy to map raw, high-dimensional observations to continuous steering and throttle commands. Compared with recent approaches to similar tasks, our method requires neither state estimation nor on-the-fly planning to navigate the vehicle. Our approach relies on, and experimentally validates, recent imitation learning theory. Empirically, we show that policies trained with online imitation learning overcome well-known challenges related to covariate shift and generalize better than policies trained with batch imitation learning. Built on these insights, our autonomous driving system demonstrates successful high-speed off-road driving, matching the state-of-the-art performance.

APA, Harvard, Vancouver, ISO, and other styles

41

V S, Amar. "Autonomous Driving using CNN." International Journal for Research in Applied Science and Engineering Technology 9, no. VI (June 30, 2021): 3633–36. http://dx.doi.org/10.22214/ijraset.2021.35771.

Full text

Abstract:

Human beings are currently addicted to automation and robotics technologies. The state-of-the-art in deep learning technologies and AI is the subject of this autonomous driving. Driving with automated driving systems promises to be safe, enjoyable, and efficient.. It is preferable to train in a virtual environment first and then move to a real-world one. Its goal is to enable a vehicle to recognise its surroundings and navigate without the need for human intervention. The raw pixels from a single front-facing camera were directly transferred to driving commands using a convolution neural network (CNN). This end-to-end strategy proved to be remarkably effective, The system automatically learns internal representations of the essential processing stages such as detecting useful road components using only the human steering angle as the training signal. We never expressly taught it to recognise the contour of roadways, for example. In comparison to explicit issue decomposition, such as lane marking detection, Our end-to-end solution optimises all processing processes at the same time, including path planning and control. We believe that this will lead to improved performance and smaller systems in the long run. Internal components will self-optimize to maximise overall system performance, resulting in improved performance.

APA, Harvard, Vancouver, ISO, and other styles

42

Pose, Sebastian, Stefan Reitmann, Gero Jörn Licht, Thomas Grab, and Tobias Fieback. "AI-Prepared Autonomous Freshwater Monitoring and Sea Ground Detection by an Autonomous Surface Vehicle." Remote Sensing 15, no. 3 (February 3, 2023): 860. http://dx.doi.org/10.3390/rs15030860.

Full text

Abstract:

Climate change poses special and new challenges to inland waters, requiring intensive monitoring. An application based on an autonomous operation swimming vehicle (ASV) is being developed that will provide simulations, spatially and depth-resolved water parameter monitoring, bathymetry detection, and respiration measurement. A clustered load system is integrated with a high-resolution sonar system and compared with underwater photogrammetry objects. Additionally, a holistic 3D survey of the water body above and below the water surface is generated. The collected data are used for a simulation environment to train artificial intelligence (AI) in virtual reality (VR). These algorithms are used to improve the autonomous control of the ASV. In addition, possibilities of augmented reality (AR) can be used to visualize the data of the measurements and to use them for future ASV assistance systems. The results of the investigation into a flooded quarry are explained and discussed. There is a comprehensive, high-potential, simple, and rapid monitoring method for inland waters that is suitable for a wide range of scientific investigations and commercial uses due to climate change, simulation, monitoring, analyses, and work preparation.

APA, Harvard, Vancouver, ISO, and other styles

43

Liu, Mingshuo, Shiyi Luo, Kevin Han, Ronald F. DeMara, and Yu Bai. "Autonomous Binarized Focal Loss Enhanced Model Compression Design Using Tensor Train Decomposition." Micromachines 13, no. 10 (October 14, 2022): 1738. http://dx.doi.org/10.3390/mi13101738.

Full text

Abstract:

Deep learning methods have exhibited the great capacity to process object detection tasks, offering a practical and viable approach in many applications. When researchers have advanced deep learning models to improve their performance, the model derived from the algorithmic improvement may itself require complementary increases in computational and power demands. Recently, model compression and pruning techniques have received more attention to promote the wide employment of the DNN model. Although these techniques have achieved a remarkable performance, the class imbalance issue during the mode compression process does not vanish. This paper exploits the Autonomous Binarized Focal Loss Enhanced Model Compression (ABFLMC) model to address the issue. Additionally, our proposed ABFLMC can automatically receive the dynamic difficulty term during the training process to improve performance and reduce complexity. A novel hardware architecture is proposed to accelerate inference. Our experimental results show that the ABFLMC can achieve higher accuracy, faster speed, and smaller model size.

APA, Harvard, Vancouver, ISO, and other styles

44

Lee, Dong-Jin, and In-June Hwang. "Self-powered Senor System using RF energy for Autonomous Train Control System." Journal of the Korean Society for Railway 25, no. 1 (January 31, 2022): 43–51. http://dx.doi.org/10.7782/jksr.2022.25.1.43.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Oh, Sehchan, and Hyeon-Yeong Choi. "Protection Algorithm for Virtual Coupler in T2T-Based Autonomous Train Control System." Journal of Korean Institute of Communications and Information Sciences 43, no. 11 (November 30, 2018): 1894–902. http://dx.doi.org/10.7840/kics.2018.43.11.1894.

Full text

APA, Harvard, Vancouver, ISO, and other styles

46

Theriault, James A., Craig Sheppard, Joey Hood, Hilary B. Moors-Murphy, and Matthew Coffin. "Counting odontocetes from click train detections using multiple independent autonomous acoustic sensors." Journal of the Acoustical Society of America 135, no. 4 (April 2014): 2241. http://dx.doi.org/10.1121/1.4877333.

Full text

APA, Harvard, Vancouver, ISO, and other styles

47

Suzuki, Tsuyoshi, Takashi Kawano, Yutaka Umehara, Yoshihide Nagatsugu, and Masayuki Matsumoto. "Assurance technology for the mode change of autonomous decentralised train control system." International Journal of Critical Computer-Based Systems 2, no. 2 (2011): 111. http://dx.doi.org/10.1504/ijccbs.2011.041255.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

Hwang, Jong-Gyu, Sung-Yoon Chae, Hyeon-Yeong Choi, and Rag-Gyo Jeong. "Design of SITL-based Simulator for Performance Analysis of Autonomous Train Control." TRANSACTION OF THE KOREAN INSTITUTE OF ELECTRICAL ENGINEERS P 71, no. 4 (December 31, 2022): 203–9. http://dx.doi.org/10.5370/kieep.2022.71.4.203.

Full text

APA, Harvard, Vancouver, ISO, and other styles

49

Plissonneau, Antoine, Luca Jourdan, Damien Trentesaux, Lotfi Abdi, Mohamed Sallak, Abdelghani Bekrar, Benjamin Quost, and Walter Schön. "Deep reinforcement learning with predictive auxiliary task for autonomous train collision avoidance." Journal of Rail Transport Planning & Management 31 (September 2024): 100453. http://dx.doi.org/10.1016/j.jrtpm.2024.100453.

Full text

APA, Harvard, Vancouver, ISO, and other styles

50

Sleaman, Walead Kaled, and Sırma Yavuz. "Indoor mobile robot navigation using deep convolutional neural network." Journal of Intelligent & Fuzzy Systems 39, no. 4 (October 21, 2020): 5475–86. http://dx.doi.org/10.3233/jifs-189030.

Full text

Abstract:

Robot can help human in their everyday life and routine. These are not an indoor robot which was designed to perform desired task, but they can adapt to our environment by themselves and to learn from their own experiences. In this research we focus on high degree of autonomy, which is a must for social robots. For training purpose autonomous exploration and unknown environments is used along with proper algorithm so that robot can adapt to unknown environments. For testing purpose, simulation is carried with sensor fusion method, so that real world noise can be reduced and accuracy can be increased. This dissertation focuses on the intelligent robot control in autonomous navigation tasks and investigates the robot learning in following aspects. This method is based on human instinct of imitation. In this standard real time data set is provided to the robot for training purpose, it gets train from these data and generalize over all unseen potential situations and environments. Convolutional Neural Network is used to determine the probability and based on that robot can act. After acceptable number of demonstrations, robot can predict output with high accuracy and hence can acquire the independent navigation skills. State-of-the-art reinforcement learning techniques is used to train the robot via interaction with the robots. Convolutional Neural Network is also incorporated for fast generalization. Robot is train based on all past state-action pairs collected during interaction. This training model can predict output which helps robot for autonomous navigation.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Autonomous Train'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles