scholarly journals A Hierarchical Control System for Autonomous Driving towards Urban Challenges

2020 ◽  
Vol 10 (10) ◽  
pp. 3543 ◽  
Author(s):  
Nam Dinh Van ◽  
Muhammad Sualeh ◽  
Dohyeong Kim ◽  
Gon-Woo Kim

In recent years, the self-driving car technologies have been developed with many successful stories in both academia and industry. The challenge for autonomous vehicles is the requirement of operating accurately and robustly in the urban environment. This paper focuses on how to efficiently solve the hierarchical control system of a self-driving car into practice. This technique is composed of decision making, local path planning and control. An ego vehicle is navigated by global path planning with the aid of a High Definition map. Firstly, we propose the decision making for motion planning by applying a two-stage Finite State Machine to manipulate mission planning and control states. Furthermore, we implement a real-time hybrid A* algorithm with an occupancy grid map to find an efficient route for obstacle avoidance. Secondly, the local path planning is conducted to generate a safe and comfortable trajectory in unstructured scenarios. Herein, we solve an optimization problem with nonlinear constraints to optimize the sum of jerks for a smooth drive. In addition, controllers are designed by using the pure pursuit algorithm and the scheduled feedforward PI controller for lateral and longitudinal direction, respectively. The experimental results show that the proposed framework can operate efficiently in the urban scenario.

2000 ◽  
Vol 12 (2) ◽  
pp. 103-109 ◽  
Author(s):  
Naoyuki Kubota ◽  
◽  
Yusuke Nojima ◽  
Fumio Kojima ◽  
Toshio Fukuda ◽  
...  

We studied intelligent control of self-organizing manufacturing system (SOMS) composed of modules that self-organize based on time-series information from other modules and environment. Modules create output through interaction with other modules. We discuss intelligent control and path planning in a manufacturing line of conveyer units and machining centers. Genetic algorithm are applied to conveyor pallet path planning in global decision making and learning automaton is applied to local conveyer decision making. We use simplified fuzzy inference to control pallets providing interval, verifying its feasibility by simulation.


2016 ◽  
Vol 26 (1) ◽  
pp. 101
Author(s):  
Mario Borja Borja ◽  
Javier Rojas Tintaya ◽  
Rodney Rodas Regalado ◽  
Carlos Díaz Ramirez ◽  
Cesar Paz Chavez Cesar Paz Chavez

RESUMEN El principal problema en el desarrollo de carreras de especialización en robótica en nuestro país es que no existen laboratorios con brazos robóticos que permitan hacer pruebas de control de posicionamiento, planificación de trayectoria y control con visión artificial y generalmente en entornos académicos se hace experimentos utilizando software de simulación.En el presente trabajo se propone una alternativa para mejorar el aprendizaje en el estudio de control de brazos robóticos utilizando brazos robóticos reales con una plataforma de tecnología abierta de software y hardware que permita a los estudiantes modificar los programas para implementar algoritmos de control de posición de articulaciones, planificación de trayectoria y control con visión artificial.La propuesta es desarrollar la tecnología total del sistema de control del brazos robóticos en la base al análisis de los requerimientos de electrónica y sistema de computo realizar la selección de electrónica de potencia, computadoras industriales basadas en Controlador Digital de señales (DSC), una computadora personal para interface de usuario.Desarrollar el software base para la computadora industrial y el software base para la computadora personal que permita cargar programas en línea a través del puerto serial desde una computadora personal y además una interface de usuario en la computadora que puede ser modificada de acuerdo a la necesidad y utilizar como sistema de control de nivel superior que realiza los cálculos de planificación de trayectoria, problema inverso y otros sistemas de alto nivel de control con visión artificial.Como resultado se obtuvo la plataforma de tecnología abierta que incluye hardware y software para brazos robóticos de hasta seis grados de libertad con motores de corriente continua en las articulaciones de hasta 100 vatios, encoders y sensores de fin de carrera.La plataforma se probó con la mecánica del brazo robótico serial Mitsubishi RV-M1 que cumple con los parámetros electrónicos y constructivos requeridos por el prototipo.Palabras claves: brazos robóticos; control de posición; plataforma abierta.ABSTRACT The main problem in the development of specialization courses in robotics in our country is that there are no laboratories with robotic arms that allow testing positioning control, path planning and control with artificial vision and generally in academic settings is done experiments using software simulation.In this paper an alternative to enhance learning in the study control robotic arms using real robotic arms with an open technology platform software and hardware that allows students to modify programs to implement control algorithms position it is proposed joints, path planning and control with artificial vision.The proposal is to develop the full technology control system of the robotic arms on the basis of the analysis of the requirements of electronic and computer system the selection of power electronics, industrial computers based on digital signal controller (DSC), a computer personnel to user interface.Develop the core software for industrial computer and basic software for the PC that allows load programs online through the serial port from a personal computer and also a user interface on the computer that can be modified according to the need and used as control system upper level that performs calculations path planning, inverse problem and other high-level systems with artificial vision control.As a result the open technology platform that includes hardware and software for robotic arms up to six degrees of freedom with DC motors in the joints of up to 100 watts, encoders and sensors to run was obtained. The platform was tested with the mechanics of serial robotic arm Mitsubishi RV-M1 compliant electronic and construction parameters required by the prototype.Keywords: robotic arms; position control; open platform.


2016 ◽  
Vol 26 (1) ◽  
pp. 101
Author(s):  
Mario Borja Borja

RESUMEN El principal problema en el desarrollo de carreras de especialización en robótica en nuestro país es que no existen laboratorios con brazos robóticos que permitan hacer pruebas de control de posicionamiento, planificación de trayectoria y control con visión artificial y generalmente en entornos académicos se hace experimentos utilizando software de simulación.En el presente trabajo se propone una alternativa para mejorar el aprendizaje en el estudio de control de brazos robóticos utilizando brazos robóticos reales con una plataforma de tecnología abierta de software y hardware que permita a los estudiantes modificar los programas para implementar algoritmos de control de posición de articulaciones, planificación de trayectoria y control con visión artificial.La propuesta es desarrollar la tecnología total del sistema de control del brazos robóticos en la base al análisis de los requerimientos de electrónica y sistema de computo realizar la selección de electrónica de potencia, computadoras industriales basadas en Controlador Digital de señales (DSC), una computadora personal para interface de usuario.Desarrollar el software base para la computadora industrial y el software base para la computadora personal que permita cargar programas en línea a través del puerto serial desde una computadora personal y además una interface de usuario en la computadora que puede ser modificada de acuerdo a la necesidad y utilizar como sistema de control de nivel superior que realiza los cálculos de planificación de trayectoria, problema inverso y otros sistemas de alto nivel de control con visión artificial.Como resultado se obtuvo la plataforma de tecnología abierta que incluye hardware y software para brazos robóticos de hasta seis grados de libertad con motores de corriente continua en las articulaciones de hasta 100 vatios, encoders y sensores de fin de carrera.La plataforma se probó con la mecánica del brazo robótico serial Mitsubishi RV-M1 que cumple con los parámetros electrónicos y constructivos requeridos por el prototipo.Palabras claves: brazos robóticos; control de posición; plataforma abiertaABSTRACT The main problem in the development of specialization courses in robotics in our country is that there are no laboratories with robotic arms that allow testing positioning control, path planning and control with artificial vision and generally in academic settings is done experiments using software simulation.In this paper an alternative to enhance learning in the study control robotic arms using real robotic arms with an open technology platform software and hardware that allows students to modify programs to implement control algorithms position it is proposed joints, path planning and control with artificial vision.The proposal is to develop the full technology control system of the robotic arms on the basis of the analysis of the requirements of electronic and computer system the selection of power electronics, industrial computers based on digital signal controller (DSC), a computer personnel to user interface.Develop the core software for industrial computer and basic software for the PC that allows load programs online through the serial port from a personal computer and also a user interface on the computer that can be modified according to the need and used as control system upper level that performs calculations path planning, inverse problem and other high-level systems with artificial vision control.As a result the open technology platform that includes hardware and software for robotic arms up to six degrees of freedom with DC motors in the joints of up to 100 watts, encoders and sensors to run was obtained. The platform was tested with the mechanics of serial robotic arm Mitsubishi RV-M1 compliant electronic and construction parameters required by the prototype.Keywords: robotic arms; position control; open platform


Sensors ◽  
2020 ◽  
Vol 20 (5) ◽  
pp. 1488
Author(s):  
Federico Peralta ◽  
Mario Arzamendia ◽  
Derlis Gregor ◽  
Daniel G. Reina ◽  
Sergio Toral

Local path planning is important in the development of autonomous vehicles since it allows a vehicle to adapt their movements to dynamic environments, for instance, when obstacles are detected. This work presents an evaluation of the performance of different local path planning techniques for an Autonomous Surface Vehicle, using a custom-made simulator based on the open-source Robotarium framework. The conducted simulations allow to verify, compare and visualize the solutions of the different techniques. The selected techniques for evaluation include A*, Potential Fields (PF), Rapidly-Exploring Random Trees* (RRT*) and variations of the Fast Marching Method (FMM), along with a proposed new method called Updating the Fast Marching Square method (uFMS). The evaluation proposed in this work includes ways to summarize time and safety measures for local path planning techniques. The results in a Lake environment present the advantages and disadvantages of using each technique. The proposed uFMS and A* have been shown to achieve interesting performance in terms of processing time, distance travelled and security levels. Furthermore, the proposed uFMS algorithm is capable of generating smoother routes.


2021 ◽  
Vol 193 ◽  
pp. 107913
Author(s):  
Yuan Tang ◽  
Yiming Miao ◽  
Ahmed Barnawi ◽  
Bander Alzahrani ◽  
Reem Alotaibi ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document