Local and Global Path Generation for Autonomous Vehicles Using Splines

Generación Local y Global de trayectorias para Vehículos Autónomos Usando Splines

  • Randerson Lemos Universidad Estatal de Campinas
  • Olmer Garcia Faculty of Mechanical Engineer - UNICAMP
  • Janito Vaqueiro Ferreira universidad esttal de campinas
Palabras clave: path planning, spline, curve space (en_US)
Palabras clave: Planeamento de Trayectorias, splines, arco de la distancia, espacio curvilineo. (es_ES)

Resumen (en_US)

Context: Before autonomous vehicles being a reality in daily situations, outstanding issues regarding the techniques of autonomous mobility must be solved. Hence, relevant aspects of a path planning for terrestrial vehicles are shown.

Method: The approached path planning technique uses splines to generate the global route. For this goal, waypoints obtained from online map services are used. With the global route parametrized in the arc-length, candidate local paths are computed and the optimal one is selected by cost functions.

Results: Different routes are used to show that the number and distribution of waypoints are highly correlated to a satisfactory arc-length parameterization of the global route, which is essential to the proper behavior of the path planning technique.

Conclusions: The cubic splines approach to the path planning problem successfully generates the global and local paths. Nevertheless, the use of raw data from the online map services showed to be unfeasible due the consistency of the data. Hence, a preprocessing stage of the raw data is proposed to guarantee the well behavior and robustness of the technique.

Resumen (es_ES)

Contexto: Antes que los vehículos autónomos sean una realidad en situaciones cotidianas temas pendientes de las técnicas de movilidad autónoma deben ser resueltos. Por eso, en este artículo es presentado una técnica de planeamiento de trayectorias para vehículos terrestres.

Método: La técnica de planeamiento de trayectorias utiliza splines para generar la ruta global. Para eso, se utilizan puntos obtenidos por servicios en línea de mapas digitales. Sobre esta ruta global, parametrizada por el arco de la distancia, son generadas rutas locales y seleccionada una trayectoria optima por diferentes funciones de costo.

Resultados: Diferentes rutas de pruebas se utilizan para mostrar que el número y la distribución de los puntos de la ruta global están altamente correlacionados con una parametrización  exitosa en el arco de la distancia de las splines, lo cual es esencial para un correcto funcionamiento de la técnica de planeamiento de trayectorias.

Conclusiones: El enfoque splines cúbicas al problema de planificación de trayectoria generó correctamente las trayectorias globales y locales. Sin embargo, el uso de los datos en bruto de los servicios de mapas en línea demostró ser inviable debido a inconsistencia de algunos datos. Por lo tanto, se propone  una etapa de preprocesamiento de los datos en bruto para garantizar la robustez de la técnica.


La descarga de datos todavía no está disponible.

Biografía del autor/a

Randerson Lemos, Universidad Estatal de Campinas

Master student of mechanical engineering at the Mechanical Engineering Faculty of the Campinas State University - Brazil. His main interests are: path planning, motion planning and autonomous vehicles.

Olmer Garcia, Faculty of Mechanical Engineer - UNICAMP

He is associate professor at the school of Engineering of the Jorge Tadeo Lozano University in Colombia. He obtained his degree on Mechatronics Engineering in 2005 at Universidad Militar Nueva Granada - Colombia, a Master degree on Electronics Engineering in 2010 at the Universidad de los Andes - Bogota, Colombia, and he obtain his doctor degree on mechanical engineering at the Campinas State University - Brazil in 2016.

Janito Vaqueiro Ferreira, universidad esttal de campinas

He is assistant professor at the Mechanical Engineering Faculty of the Campinas State University - Brazil. He obtained his bachelor degree on Mechanical Engineering in 1983 and his Master degree on Mechanical Engineering in 1989 at the same university. He obtained his doctor degree in Dynamics in 1998 at Imperial College Of Science Tecnology Medicine, IC, England. His main interests are: autonomous vehicles, combustion engine motors, dynamics control and vibrations.


Tim D Barfoot and Christopher M Clark. Motion planning for formations of mobile robots. Robotics and Autonomous Systems, 46(2):65–78, 2004.

Ilía Nikolaevich Bronshtein, Konstantin A Semendyayev, Gerhard Musiol, and Heiner Muehlig. Handbook of mathematics. Springer Science & Business Media, 2007.

Keonyup Chu, Minchae Lee, and Myoungho Sunwoo. Local path planning for off-road autonomous driving with avoidance of static obstacles. Intelligent Transportation Systems, IEEE Transactions on, 13(4):1599–1616, 2012.

Randerson Araujo de Lemos, Olmer Garcia, and Janito Vaqueiro Ferreira. Local and global path generation for autonomous vehicles using splines. In Engineering Applications-International Congress on Engineering (WEA), 2015 Workshop on, pages 1–6. IEEE, 2015.

GoogleMaps. Google Company. https://www.google.com.br/maps/@-22.8195851,-47.0631774,15z, 2015.

Thomas M Howard and Alonzo Kelly. Optimal rough terrain trajectory generation for wheeled mobile robots.The International Journal of Robotics Research, 26(2):141–166, 2007.

Unghui Lee, Sangyol Yoon, HyunChul Shim, P. Vasseur, and C. Demonceaux. Local path planning in a complex environment for self-driving car. In Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), 2014 IEEE 4th Annual International Conference on, pages 445–450, June 2014.

Xiaohui Li, Zhenping Sun, Qi Zhu, and Daxue Liu. A unified approach to local trajectory planning and control for autonomous driving along a reference path. In Mechatronics and Automation (ICMA), 2014 IEEE International Conference on, pages 1716–1721, Aug 2014.

OpenStreetMap. The free wiki world map. http://www. openstreetmap. org, 2015.

John W Peterson. Arc length parameterization of spline curves. Journal of Compu ter Aided Design, 2006.

Richard J Sharpe and Richard W Thorne. Numerical method for extracting an arc length parameterization from parametric curves. Computer-aided design, 14(2):79–81, 1982.

Bruno Siciliano, Lorenzo Sciavicco, Luigi Villani, and Giuseppe Oriolo. Robotics: modelling, planning and control. Springer Science & Business Media, 2009.

Roland Siegwart, Illah R Nourbakhsh, and Davide Scaramuzza. Introduction to autonomous mobile robots. The MIT Press, second edition, Febraury 2011.

Jarrod M Snider. Automatic steering methods for autonomous automobile path tracking. Robotics Institute, Pittsburgh, PA, Tech. Rep. CMU-RITR-09-08, 2009.

MarkWSpong, Seth Hutchinson, and Mathukumalli Vidyasagar. Robot modeling and control, volume 3. Wiley New York, 2006.

Hongling Wang, Joseph Kearney, and Kendall Atkinson. Arc-length parameterized spline curves for real-time simulation. In Proceedings of the 5th international conference on Curves and Surfaces, 2002.

Hongling Wang, Joseph Kearney, and Kendall Atkinson. Robust and efficient computation of the closest point on a spline curve. In Proceedings of the 5th International Conference on Curves and Surfaces, pages 397–406, 2002.

Werling, J. Ziegler, S. Kammel, and S. Thrun. Optimal trajectory generation for dynamic street scenarios in a frenét frame. In Robotics and Automation (ICRA), 2010 IEEE International Conference on, pages 987–993, 2010.

Cómo citar
Lemos, R., Garcia, O., & Ferreira, J. V. (2016). Generación Local y Global de trayectorias para Vehículos Autónomos Usando Splines. Ingeniería, 21(2), 188-200. https://doi.org/10.14483/udistrital.jour.reving.2016.2.a05
Publicado: 2016-05-26
Sección Especial: Mejores Artículos Extendidos - WEA 2015