Robust Control Strategy for Dynamic Lane Change of Intelligent Articulated Heavy...
Robust Control Strategy for Dynamic Lane Change of Intelligent Articulated Heavy Vehicle in Complex Traffic Environment
The complex traffic environment with dynamic changes of speed and acceleration of multi-surrounding vehicles, and adhesion coefficient and curve radius of the road, results in that the optimal and precise control of lane change fo...
ver más
¿Tienes un proyecto y buscas un partner? Gracias a nuestro motor inteligente podemos recomendarte los mejores socios y ponerte en contacto con ellos. Te lo explicamos en este video
Proyectos interesantes
DPI2016-81002-R
CONTROL AVANZADO Y APRENDIZAJE DE ROBOTS EN OPERACIONES DE T...
59K€
Cerrado
PID2019-105572RB-I00
METODO DE IDENTIFICACION DEL TIPO DE CARRETERA BASADO EN RED...
145K€
Cerrado
TrustVehicle
Improved trustworthiness and weather independence of conditi...
5M€
Cerrado
DESERVE
DEvelopment platform for Safe and Efficient dRiVE
24M€
Cerrado
DPI2014-59276-R
METODOS PREDICTIVOS INTELIGENTES PARA LA PROTECCION DE USUAR...
117K€
Cerrado
DPI2017-86915-C3-3-R
TECNICAS DE INTELIGENCIA ARTIFICIAL Y AYUDA A LA NAVEGACION...
109K€
Cerrado
Información proyecto RACE
Duración del proyecto: 29 meses
Fecha Inicio: 2024-04-05
Fecha Fin: 2026-09-08
Descripción del proyecto
The complex traffic environment with dynamic changes of speed and acceleration of multi-surrounding vehicles, and adhesion coefficient and curve radius of the road, results in that the optimal and precise control of lane change for intelligent articulated heavy vehicle (IAHV) is difficult to be achieved. According to the real-time states of multi-surrounding vehicles and road parameters, the real-time safe optimal trajectory of lane change is obtained by setting the multi-objective function considering efficiency, jack-knife, yaw and roll stability. The dynamic thresholds of each control mode, which are modified by real-time trajectory and road parameters, are obtained, and then the multi-mode switching mechanism is established by deep neural network. The vehicle parameters and states are accurately estimated by using an estimator with multi-estimation algorithms combining steady state with dynamic state. Considering the parameter uncertainty, a robust control strategy based on a linear parameter-varying model is designed to real-time achieve precise and optimal tracking control of dynamic trajectory and maintain vehicle stability by optimizing weight coefficients and multi-mode switching. Thus, the safe and optimal lane change of IAHV under normal and extreme conditions with different velocities and loads is realized. The proposed control strategy is verified on HIL bench. The research results will provide theoretical basis for IAHV control in complex traffic environment.
This project provides a unique knowledge exchange from leading experts in different fields (vehicle, control, mechanical, transportation, optimization, motor, pneumatic) to solve the challenges in IAHV. The fellow will benefit from not only the scientific impact of the work but also exposure to new techniques and collaborative networks in different disciplines. The dedicated training and high scientific value will help the fellow to become an independent researcher in a world-leading institution.