Control Of Autonomous Vehicles Research Articles

Observer-based prescribed performance path-following control for autonomous ground vehicles via error shifting method

Observer-based prescribed performance path-following control for autonomous ground vehicles via error shifting method

Neural network-based practical fixed-time nonsingular sliding mode tracking control of autonomous surface vehicles under actuator saturation

The article considers the fixed-time tracking control of autonomous surface vehicles (ASVs) subject to actuator saturation. A novel sliding variable with state-dependent exponents is first constructed to alleviate chattering and overcome the singularity. By using the proposed fixed-time sliding variable and the neural network (NN), an NN-based fixed-time sliding mode control (SMC) scheme is developed. Besides, an auxiliary system is utilized to solve the input saturation constraint. Unlike some existing results for ASVs with input saturation, the designed fixed-time SMC law does not require assumptions on a priori upper bound of the lumped disturbances. Through Lyapunov analysis, it is proven that the tracking error can converge to a bounded region in a fixed time. Simulation examples are given to show the validity of the proposed control scheme.

Performance-optimisation-based repetitive trajectory tracking control for autonomous farming vehicle

The high precision trajectory tracking for the autonomous farming vehicle (AFV) is closely related to work quality and crop yield. Farmland operations are usually repetitive tillages, and the farmland soil is relatively soft, slippery, and uneven, which can easily lead to uncertain problems such as slippage, parameter perturbation, and external disturbance. This paper proposes a finite-time repetitive trajectory tracking control strategy integrated with particle swarm optimisation (PSO) and equivalent input disturbance (EID) for the AFV to achieve performance optimisation. The repetitive control framework with finite-time convergence technique can effectively realise the iterative convergence performance of the repetitive trajectory tracking. The PSO algorithm is integrated into determining the control gains to optimise the dynamic and steady-state performances of the trajectory tracking control system. The EID method enhances the tracking precision and robustness to internal and external disturbances. Under MATLAB/Simulink and CarSim co-simulation environment, the effectiveness and advantages of the designed control strategy are illustrated by comparing it with the traditional repetitive control, the EID-based PI control, the active-disturbance-rejection-control-based nonsingular terminal sliding mode control, as well as the sliding-mode-observer-based integral sliding mode control strategies for a farming vehicle.

UAV control in autonomous object-goal navigation: a systematic literature review

Research interest in autonomous control of unmanned aerial vehicles (UAVs) has increased rapidly over the past decade. They are now widely used in civilian, military, and private areas. Applications include surveillance, search and rescue, and delivery tasks. More broadly, they excel at solving problems where a significant amount of space must be covered and traveled. However, using UAVs to solve navigation problems with full autonomy necessitates the mastering of complex subtasks. A solution that includes control, planning, localization, and mapping remains an open challenge. Object-goal navigation contains the same navigation problems where the main objective is to reach a target object. The search and identification of this target are central to the vehicle’s navigation. This requires an understanding of what it is and where it can be located to move around the scene. This paper presents a systematic literature review on object-goal navigation and its subtasks, using autonomous UAVs. Survey taxonomies were found for the tasks and methods behind navigation and target localization problems using UAVs. The review analyzed 67 articles found between 2011 and 2022. They were found in the ACM, IEEE Xplore, WebOfScience, Science Direct, and Scopus databases. This review revealed essential issues related to autonomous navigation task dependencies. Moreover, it highlighted gaps in UAV development and framework standardization. Open challenges for autonomous UAV control for object-goal navigation must address the research on finding methods for problems. For example, autonomy level and comparison metrics, considering safety, ethics, and legal implications.

Adaptive event-triggered based path following output feedback control for networked autonomous vehicles

This paper studies the adaptive event-triggered (AET)-based path following controller design problem for a networked autonomous vehicle, where the limited networked bandwidth, system nonlinearities and uncertainties are considered. The polytopic model is proposed to construct a linear parameter varying (LPV) system for the nonlinear vehicle system. Taking into account the effects of event trigger on the path following performance, an improved AET mechanism is designed to achieve a balance between efficient communication and accurate path following requirements. Sufficient conditions are developed to guarantee that the closed-loop system is exponentially stable with an H∞ performance index being satisfied. In addition, a co-design method with less conservatism is derived to obtain the event-triggered weight matrix and output feedback controller gain matrix simultaneously. Finally, simulation results verify the effectiveness of the proposed control strategy.

A Gaussian-Process-Based Model Predictive Control Approach for Trajectory Tracking and Obstacle Avoidance in Autonomous Underwater Vehicles

To achieve the efficient and precise control of autonomous underwater vehicles (AUVs) in dynamic ocean environments, this paper proposes an innovative Gaussian-Process-based Model Predictive Control (GP-MPC) method. This method combines the advantages of Gaussian process regression in modeling uncertainties in nonlinear systems, and MPC’s constraint optimization and real-time control abilities. To validate the effectiveness of the proposed GP-MPC method, its performance is first evaluated for trajectory tracking control tasks through numerical simulations based on a 6-degrees-of-freedom, fully actuated, AUV dynamics model. Subsequently, for 3D scenarios involving static and dynamic obstacles, an AUV horizontal plane decoupled motion model is constructed to verify the method’s obstacle avoidance capability. Extensive simulation studies demonstrate that the proposed GP-MPC method can effectively manage the nonlinear motion constraints faced by AUVs, significantly enhancing their intelligent obstacle avoidance performance in complex dynamic environments. By effectively handling model uncertainties and satisfying motion constraints, the GP-MPC method provides an innovative and efficient solution for the design of AUV control systems, substantially improving the control performance of AUVs.

Hybrid nonlinear ripple‐free sampled‐data robust regulation with application to UAVs

AbstractThis paper proposes a novel solution to the problem of robust ripple‐free hybrid robust regulator ensuring the elimination of intersample ripples. The paper considers a structurally stable regulation approach in the hybrid framework. A regulator is designed using this technique under periodic sampling and is applied to the nonlinear model of a quadrotor. The control of unmanned autonomous vehicles has become a research topic that is important by itself, particularly in the case of multi‐rotor systems due to their versatility in various applications. Tracking a reference signal for such vehicles can be challenging, particularly when the frequency of communication is limited, or the control station is located far away. The proposed controller is hence tested for this challenging application.

Research on model predictive control of autonomous underwater vehicle based on physics informed neural network modeling

In the rapidly evolving field of Autonomous Underwater Vehicles (AUVs), achieving precise control remains a critical endeavor. This study presents a pioneering integration of Model Predictive Control (MPC) with a Physics-Informed Neural Network (PINN), aiming to enhance control system precision and operational efficiency in AUVs. The efficacy of MPC lies in its adept handling of the intricate constraints and inherent nonlinear dynamics intrinsic to AUV systems. Concurrently, the PINN architecture incorporates the fundamental physical laws represented by Partial Differential Equations (PDEs), augmenting the predictive fidelity of the system. Firstly, this research implements the novel PINN-enhanced MPC framework for trajectory tracking and conducts a comparative evaluation against adaptive proportional-integral-derivative (PID) and Gaussian-process-based MPC controllers. This comparative analysis elucidates the advancements in control mechanisms attributable to the PINN integration. Furthermore, this study meticulously assesses the PINN-MPC's proficiency in navigating through static and dynamic obstacles within three-dimensional marine environments, a critical capability for AUV operations. Through extensive and meticulous simulations, the proposed approach demonstrates notable progress in overcoming environmental challenges and executing intricate operational tasks, such as obstacle avoidance, with heightened efficiency and dexterity. This research constitutes a substantial contribution to the theoretical advancement and elucidation of control systems in the AUV domain, bearing profound practical implications. It lays the foundation for the development of increasingly sophisticated, advanced, and reliable AUV missions, signifying a crucial advancement in the realms of underwater exploration and operational technology.

Autonomous Vehicle Decision and Control through Reinforcement Learning with Traffic Flow Randomization

Most of the current studies on autonomous vehicle decision-making and control based on reinforcement learning are conducted in simulated environments. The training and testing of these studies are carried out under the condition of rule-based microscopic traffic flow, with little consideration regarding migrating them to real or near-real environments. This may lead to performance degradation when the trained model is tested in more realistic traffic scenes. In this study, we propose a method to randomize the driving behavior of surrounding vehicles by randomizing certain parameters of the car-following and lane-changing models of rule-based microscopic traffic flow. We trained policies with deep reinforcement learning algorithms under the domain-randomized rule-based microscopic traffic flow in freeway and merging scenes and then tested them separately in rule-based and high-fidelity microscopic traffic flows. The results indicate that the policies trained under domain-randomized traffic flow have significantly better success rates and episodic rewards compared to those trained under non-randomized traffic flow.

Data‐driven iterative learning cooperative trajectory tracking control for multiple autonomous underwater vehicles with input saturation constraints

AbstractThis paper investigates the cooperative trajectory tracking (CTT) control problem of multiple autonomous underwater vehicles (AUVs). The multi‐AUV system is characterized by uncertain dynamics, being subjected to the impact about input saturation constraints and unmeasurable disturbances. First, a neural network‐based data‐driven control algorithm is proposed for the multi‐AUV system with unmeasurable disturbances and model parameters uncertain. The radial basis function neural network is employed to estimate the primary pseudo parameters of an equivalent data model, established through dynamic linearization methods. Subsequently, an iterative learning control approach based on adaptive gain is designed to act as a feedforward scheme along the iteration axis to enhance the tracking accuracy within a time constraint. Third, to prove that the resulting CTT control system fulfills the bounded stability under the proposed control approach, a formal stability analysis is provided. Finally, a simulation case study is conducted to illustrate the effectiveness of the proposed CTT control approach.

Learning-Based Control of Autonomous Vehicles Using an Adaptive Neuro-Fuzzy Inference System and the Linear Matrix Inequality Approach.

This paper proposes a learning-based control approach for autonomous vehicles. An explicit Takagi-Sugeno (TS) controller is learned using input and output data from a preexisting controller, employing the Adaptive Neuro-Fuzzy Inference System (ANFIS) algorithm. At the same time, the vehicle model is identified in the TS model form for closed-loop stability assessment using Lyapunov theory and LMIs. The proposed approach is applied to learn the control law from an MPC controller, thus avoiding the use of online optimization. This reduces the computational burden of the control loop and facilitates real-time implementation. Finally, the proposed approach is assessed through simulation using a small-scale autonomous racing car.

Finite-time fuzzy cooperative control for multi-AUV systems under cyber-attacks with hybrid unknown nonlinearities

In this paper, we investigate the fuzzy cooperative control and collision-free problems of discrete-time multiple autonomous underwater vehicles (AUVs) systems subject to unknown nonlinearities and constrained communication under cyber-attacks. A cooperative controller composed of three components is proposed for each AUV follower. The first component maneuvers the position and velocity for tracking desired signals by the feedback information. The repulsion part protects the AUV from collision with environmental obstacles or other vehicles. The remaining nonlinearities compensation term is employed to compensate for the system’s nonlinearities. Notably, the fuzzy logic systems (FLSs) approximate the hybrid unknown term constituted by external disturbances, unmodeled dynamics and deceptive signals. Then, the unknown terms identification and cooperative control problems are transformed into an error system stability problem. Inequality conditions for finite-time bounded error signals are presented through stability analysis. Also, it is theoretically proven that the cooperative control objective with collision avoidance can be accomplished by using suitable controller parameters. Lastly, the simulation results demonstrate the effectiveness of the complete control framework. Comparisons of various scenarios also affirm the significance of the FLSs and repulsion control for the multi-AUV cooperative control system.

Model Predictive Control for Trajectory Planning Considering Constraints on Vertical Load Variation

To address the issue of centrifugal force affecting the vertical load during the stability and trajectory planning of autonomous vehicles during high-speed cornering and obstacle avoidance, a model predictive control of trajectory planning and tracking is proposed that considers the roll factor using only a two-degrees-of-freedom vehicle dynamics model. Firstly, a trajectory planning controller is designed. As a predictive model, a dual-track two-degrees-of-freedom vehicle dynamics model is established. This model describes the relationship between tire lateral forces and vertical loads using a quadratic nonlinear tire model. To reflect the actual dynamic state of the vehicle, the controller incorporates a nonlinear constraint that considers vertical load variations. The nonlinear optimization problem is transformed into a simplified quadratic programming problem by using the Jacobian matrix method to linearize the constraints. By fitting a fourth-degree polynomial curve to the discrete points calculated by the replanning algorithm, an optimal collision-free trajectory is obtained. Secondly, an MPC trajectory tracking controller is designed to control the vehicle in real time along the optimal trajectory from the planning, incorporating control quantity constraints, control increment constraints, and lateral angle constraints to maintain the vehicle’s motion state. We transform the trajectory tracking control problem into a quadratic programming problem, solving for the optimal control sequence for the autonomous vehicle to track the trajectory, achieving an optimized solution and rolling time domain control. Finally, the effectiveness of the vehicle’s obstacle avoidance planning and tracking under high-speed double-lane-change maneuver conditions is validated using the Simulink simulation platform. The results indicate that the designed planning and tracking controllers effectively improve the obstacle avoidance planning and tracking control for high-speed autonomous vehicles.

Segmented hybrid event‐triggered control for underactuated autonomous underwater vehicles with an asymmetrical prescribed performance constraint

AbstractIn this technical article, the trajectory‐tracking problem of event‐based adaptive prescribed performance control for underactuated autonomous underwater vehicles (AUVs) is considered. The primary innovation of this article is the proposal of a segmented event‐triggered mechanism (SETM) that incorporates preselected convergence time. This mechanism allows for the regulation of communication frequency in the control channel (controller‐to‐actuator) according to the dynamic characteristics of the AUV system at different stages. In addition to presenting new design scheme based on SETM, an enhanced vision known as segmented hybrid event‐triggered mechanism (SHETM) is introduced. Notably, the minimum and maximum triggering intervals (MITI and MATI) for these two ETMs can be calculated from the corresponding resettable dynamic variables presented in the trigger conditions. Subsequently, by utilizing the proposed asymmetrical prescribed performance control (APPC) strategy, the system's output tracking error behaviors in both transient and steady‐state stages can be qualitatively predetermined through design parameters within the boundary function. Moreover, the minimum learning parameter (MLP) based RBFNN adaptive control law is developed to counteract the effects of model uncertainties and ocean current perturbations. Finally, rigorous theoretical analysis and simulation results confirm the viability of the proposed scheme.

Prediction Horizon-Varying Model Predictive Control (MPC) for Autonomous Vehicle Control

The prediction horizon is a key parameter in model predictive control (MPC), which is related to the effectiveness and stability of model predictive control. In vehicle control, the selection of a prediction horizon is influenced by factors such as speed, path curvature, and target point density. To accommodate varying conditions such as road curvature and vehicle speed, we proposed a control strategy using the proximal policy optimization (PPO) algorithm to adjust the prediction horizon, enabling MPC to achieve optimal performance, and called it PPO-MPC. We established a state space related to the path information and vehicle state, regarded the prediction horizon as actions, and designed a reward function to optimize the policy and value function. We conducted simulation verifications at various speeds and compared them with an MPC with fixed prediction horizons. The simulation demonstrates that the PPO-MPC proposed in this article exhibits strong adaptability and trajectory tracking capability.

MPC-based Lateral Motion Control for Autonomous Vehicles Through Serially Cascaded Discretization Method Considering Path Preview

MPC-based Lateral Motion Control for Autonomous Vehicles Through Serially Cascaded Discretization Method Considering Path Preview

Adaptive Terminal Sliding Mode Trajectory Tracking Control for Autonomous Vehicles Considering Completely Unknown Parameters and Unknown Perturbation Conditions

In the actual implementation of autonomous vehicle controller and related applications, it is difficult to obtain all the actual parameters of the vehicle. Considering factors such as uneven pavement and different pavement conditions, it is difficult to accurately establish the vehicle dynamic system model. Based on the non-singular terminal sliding mode and adaptive control theory, this paper establishes a trajectory tracking control strategy for an autonomous vehicle with unknown parameters and unknown disturbances. Firstly, the complex trajectory tracking problem is decoupled from the position and heading angle tracking problem, and the preview error equation is established. Secondly, a non-singular terminal sliding mode (NTSM) controller is established to stabilize the trajectory tracking error to the origin in a finite time, and adaptive laws are proposed to estimate the unknown vehicle parameters to adapt to environmental changes. Through the CarSim–Matlab platform, typical working conditions are implemented to verify the proposed controller. Our experimental outcomes affirm that the NTSM controller effectively guarantees the autonomous vehicle’s accurate following of the reference path, ensuring smooth control inputs throughout the entire process.

AUV way-point tracking at constant velocity: cross-track error (CTE) and line-of-sight (LOS) guidance

This paper addresses the integrated challenges of path-following and tracking control for an under-actuated Autonomous Underwater Vehicle (AUV) in the two-dimensional (2D) plane. Four distinct 2D trajectories: linear, linear with sharp turns, curved, and circular trajectories have been considered in this study. The proposed path-following control algorithm leverages AUV kinematic and dynamic models, incorporating the Cross-Track Error (CTE) method and Line-of-Sight (LOS) technique to determine the desired orientation. Stability analysis has been performed to evaluate the robustness of the controllers against sudden underwater disturbances. Additionally, perturbation has been introduced in simulations to mimic real-world conditions more accurately. The simulations confirm the controllers’ proficiency in accurately tracking these various trajectories from a given starting point.

Optimal design of adaptive model predictive control based on improved GWO for autonomous vehicle considering system vision uncertainty

The tuning issue of the parameters and the system uncertainty represent big challenges in most engineering applications. In this regard, a new tuning approach is developed for adaptive model predictive control (AMPC) of autonomous vehicles (AVs). The proposed control strategy tackles the uncertainty issue of the vision system due to the variation of the velocity, road curvature, time delay, and look ahead distance. The proposed AMPC is designed depending on a new improved grey wolf optimizer (IGWO) algorithm with different learning procedures and fitness-distance balance (FDB) approach to equilibrium the exploration and exploitation manners of the original GWO. This development of GWO based on FDB can increase the capability of the GWO for global search and avoid trapping in local states. Furthermore, the proposed IGWO does not require more adjustable parameters that can enhance the convergence to the best global solution rapidly. The new IGWO is compared with recent optimization algorithms such as the mayfly optimization algorithm (MA), chimp optimization algorithm (COA), dynamic arithmetic optimization algorithm (DAOA), whale optimization algorithm (WOA), jaya algorithm (JA), archimedes optimization algorithm (AOA), and equilibrium optimizer (EO) as well as the original GWO. Besides, the performance of the designed AMPC is compared with the fuzzy logic proportional integral (FLPI) controller and the traditional MPC. Various test scenarios are performed to assert the robustness and effectiveness of the designed AMPC against the variation of the velocity, road curvature, time delay, and look ahead distance. The results emphasize that the proposed AMPC can perform the best damping response with an overshoot of around 1.3 m and a settling time of around 1.12 s less than the FLPI controller and the traditional MPC.

An improved eco-driving strategy for mixed platoons of autonomous and human-driven vehicles

The emergence of autonomous vehicles (AVs) could transform traffic flow characteristics and affect energy consumption subsequently. The primary objective of this study is to propose an improved eco-driving strategy for the mixed platoons by exploring the impacts of AVs on energy consumption characteristics. Initially, leveraging precise AV control, this study utilizes a Model Predictive Control (MPC) system to optimize AV trajectories, aiming to minimize energy consumption within mixed platoons of AVs and human-driven vehicles (HDVs). Given the differing collaborative capabilities of HDVs and AVs in mixed platoons, exceptional situations may arise at intersections where not all platoon vehicles cross the stop line during the same green light cycle (GLC). To address these challenges, we then propose a splitting approach to optimize the platoon operation mode. This approach allows for flexible splitting decisions based on AVs market penetration and current traffic conditions. The simulation results indicate that the energy consumption reduction ranges from 15.35% to 35.39% and 2.75–3.64% compared to the traditional mode and the eco-driving mode, respectively. In addition, through an analysis of the energy consumption of various vehicle orders within a mixed platoon, we determined that positioning the second AV in the middle platoon maximizes stability, resulting in a more consistent energy consumption pattern. These findings highlight the advantages of the strategy in terms of energy consumption, providing theoretical support management of mixed platoons.