Model-reference adaptive sliding mode control of longitudinal speed tracking for autonomous vehicles

Abstract

This paper presents a longitudinal speed control algorithm using a model-reference adaptive sliding mode control (ASMC) scheme for an autonomous vehicle in various driving environments using only wheel speed sensors. The proposed algorithm could control the vehicle’s speed not using parameter estimators but using an adaptation technique. The parameter adaptation laws were designed to compensate for the changes in the environmental disturbances and model uncertainties. Moreover, the upper bound of unknown disturbances, that were not compensated by the adaptation algorithm, was estimated using radial basis function neural network (RBFNN). The sliding mode controller updated the upper bound from the RBFNN and obtained robustness without knowing the bound in advance. Adaptive equivalent control input was also defined to compensate for zero-throttle acceleration varying with speed. This input could enhance the mode switch smoothly between throttle and brake control. We conducted computer simulations and vehicle tests under various driving environments to evaluate the performance of the proposed algorithm. In the simulation result, the average tracking error of the proposed algorithm was 0.718 kph, and the maximum change rate of the error due to the disturbances was 11%. The improvements were 55% and 68%, respectively, compared to the PID control. The average error in the vehicle test result was 0.414 kph, which was improved by 48% compared to the PID control in the test track. The results demonstrate that the proposed algorithm ensures desirable tracking performance under environmental disturbances and model uncertainties.

Trajectory Planning and Control of Autonomous Vehicles for Static Vehicle Avoidance in Dynamic Traffic Environments

“…The control input is defined as the desired longitudinal acceleration. The longitudinal prediction model is based on a kinematic model with a first order acceleration input delay in order to consider the desired acceleration tracking characteristics of the actual vehicle [31]. The continuous time state space representation of the proposed longitudinal vehicle model is as follows:…”

Distributed Drive Autonomous Vehicle Trajectory Tracking Control Based on Multi-Agent Deep Reinforcement Learning

“…Some scholars have proposed improvements to these methods; for instance, reference [10] combines PID methods with radial basis function neural networks to enhance robustness. Reference [11] presents an adaptive sliding mode control method, introducing parameter adaptation laws to compensate for variations in environmental disturbances and model uncertainties. Reference [12] employs MPC algorithms to design hierarchical controllers for distributeddriven vehicles, achieving autonomous driving longitudinal speed tracking and verifying control performance.…”

A Tube-Based Model Predictive Control for Path Tracking of Autonomous Articulated Vehicle

“…For example, autonomous buses experience notable variations in vehicle mass depending on passenger load, a factor not as pronounced in autonomous cars. Consequently, real-time estimation of mass and center of gravity becomes crucial, with these factors needing incorporation into the controller [4]. Similarly, self-driving trucks exhibit mass and center of gravity variations based on cargo load, necessitating the use of estimators akin to those used for autonomous buses [5].…”