A novel adaptive control approach for path tracking control of autonomous vehicles subject to uncertain dynamics

Mohammadzadeh, Ardashir; Taghavifar, Hamid

doi:10.1177/0954407019901083

Cited by 24 publications

(14 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a composite controller, the CDRC combines an MPPC and a DRC, as shown in Figure 4. The DRC, a cascaded feedback control structure, [36][37][38] is designed to minimize the lateral error by manipulating the steering motor. Nonetheless, as a feedback controller with a real-time observer, the DRC usually needs a high feedback frequency, which is limited by the low sampling rate and noisy output of the GPS.…”

Section: Controller Synthesismentioning

confidence: 99%

Layered disturbance rejection path-following control with geometry-based feedforward for unmanned rollers

Xie

Quanzhi

Song

2022

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

As a widely used engineering vehicle, drum rollers have a higher degree of freedom in motion than conventional passenger vehicles. The uncertainties, caused by road and vehicle condition variations, introduce severe disturbances in the path-following control of unmanned rollers. In this work, a single-drum roller is considered, for which a composite disturbance rejection controller (CDRC) is proposed for path following. The CDRC comprises a disturbance rejection controller (DRC) and a modified pure pursuit controller (MPPC). The DRC lumps all the discrepancies of the models from the roller as total disturbance, which is estimated by the extended state observer (ESO) and rejected in the feedback control loop. For enhanced performance, MPPC is added as a feedforward controller, which calculates the target articulation angle based on the roller geometry model. Compared with the DRC, the settling time of the CDRC is reduced by 12.3%, and the lateral errors are reduced by 43.1% and 39.9% in the presence of uncertainties in the positioning system and steering motor, respectively, while it still maintains a low computational cost. The proposed controller have been used in 15 unmanned rollers for 2 years, using which over 5 million square meters area has been compacted.

show abstract

Section: Controller Synthesismentioning

confidence: 99%

Layered disturbance rejection path-following control with geometry-based feedforward for unmanned rollers

Xie

Quanzhi

Song

2022

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

show abstract

“…At present, the mainstream intelligent methods include fuzzy control, genetic algorithms, neural networks, reinforcement learning, etc. The author in [ 10 ] proposed a new control approach based on the immersion and invariance control theorem to ensure that the vehicle completes the vehicle path-tracking task under various operating conditions, parameter uncertainties, and external disturbances. Because intelligent algorithms are mainly model-free, many scholars have combined intelligent algorithms with traditional algorithms to solve the shortcomings of traditional methods.…”

Section: Introductionmentioning

confidence: 99%

Path-Tracking Control Strategy of Unmanned Vehicle Based on DDPG Algorithm

Yao

2022

Sensors

View full text Add to dashboard Cite

This paper proposes a deep reinforcement learning (DRL)-based algorithm in the path-tracking controller of an unmanned vehicle to autonomously learn the path-tracking capability of the vehicle by interacting with the CARLA environment. To solve the problem of the high estimation of the Q-value of the DDPG algorithm and slow training speed, the controller adopts the deep deterministic policy gradient algorithm of the double critic network (DCN-DDPG), obtains the trained model through offline learning, and sends control commands to the unmanned vehicle to make the vehicle drive according to the determined route. This method aimed to address the problem of unmanned-vehicle path tracking. This paper proposes a Markov decision process model, including the design of state, action-and-reward value functions, and trained the control strategy in the CARLA simulator Town04 urban scene. The tracking task was completed under various working conditions, and its tracking effect was compared with the original DDPG algorithm, model predictive control (MPC), and pure pursuit. It was verified that the designed control strategy has good environmental adaptability, speed adaptability, and tracking performance.

show abstract

“…The path planning and path-tracking control strategies have attracted focused attention in recent years. The design of path-tracking control usually considers the detailed vehicle model to improve the control performance [ 1 , 2 , 3 ]. Particularly, a adaptive path-tracking control approach is proposed based on the lateral dynamics model with uncertain vehicle parameters [ 1 ].…”

Section: Introductionmentioning

confidence: 99%

“…The design of path-tracking control usually considers the detailed vehicle model to improve the control performance [ 1 , 2 , 3 ]. Particularly, a adaptive path-tracking control approach is proposed based on the lateral dynamics model with uncertain vehicle parameters [ 1 ]. Furthermore, a nonlinear sliding mode controller is proposed for the path-tracking control of an unmanned agricultural tractor by considering the kinematic model with wheel slip [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

A Study on Dynamic Motion Planning for Autonomous Vehicles Based on Nonlinear Vehicle Model

Tang

2022

Sensors

View full text Add to dashboard Cite

Autonomous driving technology, especially motion planning and the trajectory tracking method, is the foundation of an intelligent interconnected vehicle, which needs to be improved urgently. Currently, research on path planning methods has improved, but few of the current studies consider the vehicle’s nonlinear characteristics in the reference model, due to the heavy computational effort. At present, most of the algorithms are designed by a linear vehicle model in order to achieve the real-time performance at the cost of lost accuracy. To achieve a better performance, the dynamics and kinematics characteristics of the vehicle must be simulated, and real-time computing ensured at the same time. In this article, a Takagi–Sugeno fuzzy-model-based closed-loop rapidly exploring random tree algorithm with on-line re-planning process is applied to build the motion planner, which effectively improves the vehicle performance of dynamic obstacle avoidance, and plans the local obstacle avoidance path in line with the dynamic characteristics of the vehicle. A nonlinear vehicle model is integrated into the motion planner design directly. For fast local path planning mission, the Takagi–Sugeno fuzzy modelling method is applied to the modeling process in the planner design, so that the vehicle state can be directly utilized into the path planner to create a feasible path in real-time. The performance of the planner was evaluated by numerical simulation. The results demonstrate that the proposed motion planner can effectively generate a reference trajectory that guarantees driving efficiency with a lower re-planning rate.

show abstract

A novel adaptive control approach for path tracking control of autonomous vehicles subject to uncertain dynamics

Cited by 24 publications

References 43 publications

Layered disturbance rejection path-following control with geometry-based feedforward for unmanned rollers

Layered disturbance rejection path-following control with geometry-based feedforward for unmanned rollers

Path-Tracking Control Strategy of Unmanned Vehicle Based on DDPG Algorithm

A Study on Dynamic Motion Planning for Autonomous Vehicles Based on Nonlinear Vehicle Model

Contact Info

Product

Resources

About