Control Of Autonomous Vehicles Research Articles

Safety-Critical Trajectory Tracking Control with Safety-Enhanced Reinforcement Learning for Autonomous Underwater Vehicle

This paper investigates a novel reinforcement learning (RL)-based quadratic programming (QP) method for the safety-critical trajectory tracking control of autonomous underwater vehicles (AUVs). The proposed approach addresses the substantial challenge posed by model uncertainty, which may hinder the safety and performance of AUVs operating in complex underwater environments. The RL framework can learn the inherent model uncertainties that affect the constraints in Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs). These learned uncertainties are subsequently integrated for formulating a novel RL-CBF-CLF Quadratic Programming (RL-CBF-CLF-QP) controller. Corresponding simulations are demonstrated under diverse trajectory tracking scenarios with high levels of model uncertainties. The simulation results show that the proposed RL-CBF-CLF-QP controller can significantly improve the safety and accuracy of the AUV’s tracking performance.

Static Output-Feedback Path-Tracking Controller Tolerant to Steering Actuator Faults for Distributed Driven Electric Vehicles

The steering system plays a critical role in the vehicle’s handling and directly influences its lateral dynamics. Faults or abnormal behavior in this system can affect performance, cause vehicle instability, and even lead to accidents. Therefore, considering these potential events is essential for designing robust controllers for autonomous vehicles. For this reason, in this work, a fault-tolerant path-tracking Static Output-Feedback controller is designed to handle steering actuator faults in autonomous vehicle steering systems. The controller adopts a Linear Parameter Varying approach to effectively handle nonlinearities associated with varying vehicle speeds and tire behavior. Furthermore, it only uses information from sensors, avoiding estimation stages. This controller can operate in two modes: a no-fault mode where only the steering is controlled to follow the reference path and a fault mode where the controller manages both the steering and torque vectoring. In fault mode, torque vectoring compensates for faults in the steering actuator. The design of the controller is completed considering gain faults in the steering system. The simulation results show that the proposed controller successfully maintains vehicle stability and significantly reduces tracking errors during high-risk maneuvers, achieving reductions of up to 50.65% in lateral error and 47.26% in heading error under worst-case fault scenarios.

Composite neural learning-based adaptive actuator failure compensation control for full-state constrained autonomous surface vehicle

Composite neural learning-based adaptive actuator failure compensation control for full-state constrained autonomous surface vehicle

ANÁLISE MATEMÁTICA E SIMULAÇÃO DO SISTEMA DE AMORTECIMENTO VEICULAR COM MATLAB

Abstract: In modern control theory, the concept of state variables plays a crucial role in the modeling and analysis of dynamic systems. These variables provide a comprehensive description of the system’s future behavior over time. The organization into a state vector enables a compact and complete representation of the system’s internal state. The state-space function describes the temporal evolution of these variables in response to system inputs, offering an efficient mathematical approach for the design and analysis of control systems. Applications range from industrial process control to autonomous vehicle control and robotics. By understanding and applying these concepts, control engineers develop effective solutions for challenges in complex systems, ensuring performance, stability, and efficiency in dynamic environments. Keywords: state variables; dynamic systems; state-space; control; stability.

Resilient event-triggered [formula omitted] control for autonomous vehicle under novel important-data-based DoS attack

This paper presents the method of a resilient event-triggered H∞ controller for autonomous vehicles (AVs) to address the emerging threat of important-data-based (IDB) Denial-of-Service (DoS) attack. Specifically, a unique IDB DoS attack strategy from an adversarial perspective is proposed to enhance the attack’s destructiveness. Unlike many mature DoS attack methods, the proposed IDB DoS attack could discern the importance level for the data and selectively launch attacks on crucial information, resulting in more significant damage. Furthermore, a novel resilient event-triggered H∞ control technique is employed to mitigate the impact of the attack and counteract the negative effects produced by the IDB DoS attack. Utilizing the Lyapunov functional method, sufficient conditions are successfully derived to ensure the asymptotical stability of the resulted closed-loop system and H∞ interference suppression performance. Subsequently, simulation results demonstrate that: (1) the addressed IDB DoS attack method leads to a more severe system degradation, highlighting the potential risks associated with this novel attack approach; and (2) the proposed event-triggered H∞ controller effectively mitigates the potential impact of the IDB DoS attack, showcasing its efficiency in preserving system performance under adversarial conditions.

Low complexity fault-tolerant formation control for autonomous underwater vehicles with global prescribed-time performance

This paper investigates a novel control scheme for multiple autonomous underwater vehicle (AUV) systems in the presence of measurement errors, unknown external disturbances, and actuator faults. The proposed strategy achieves robust formation control while ensuring global prescribed-time performance. By employing passive strategies and event-triggering mechanism, the communication burden between controller and actuator and computational complexity are significantly reduced. All closed-loop signals are proven to be bounded, and Zeno behavior is avoided. The effectiveness of this control scheme is validated through a simulation.

Dynamic Event-Triggered and Fast Natural Logarithmic Sliding Mode Path Tracking Control for Autonomous Ground Vehicles With the Experiment Validation

Dynamic Event-Triggered and Fast Natural Logarithmic Sliding Mode Path Tracking Control for Autonomous Ground Vehicles With the Experiment Validation

K-SMPC: Koopman Operator-Based Stochastic Model Predictive Control for Enhanced Lateral Control of Autonomous Vehicles

K-SMPC: Koopman Operator-Based Stochastic Model Predictive Control for Enhanced Lateral Control of Autonomous Vehicles

Improved Deep Reinforcement Learning for Efficient Motion Control of Autonomous Vehicle with Domain-Centralized Electronic and Electrical Architecture

Improved Deep Reinforcement Learning for Efficient Motion Control of Autonomous Vehicle with Domain-Centralized Electronic and Electrical Architecture

ARTIFICIAL INTELLIGENCE, ETHICAL CONSIDERATIONS, FUTURE TRENDS AND CHALLENGES

Artificial intelligence has somehow become the force that has transformed various sectors, including the military. Moreover, AI technology has revolutionized the military with its ability to rapidly process large amounts of data, make decisions, and analyze complex patterns. Analyzing the question of how it is used and what ethical norms exist in military structures is not an easy task, because artificial intelligence components are supported by the defense sector in many directions - autonomous weapons and vehicle systems, intelligent command and control systems, predictive maintenance performance, logistics and maintenance services. , cyber security, intelligence and surveillance, decision support systems, simulations and training, artificial intelligence applications and more. We have already discussed these issues in detail in the main part of the book, analyzed and discussed all the relevant issues related to the introduction, use and development of artificial intelligence technologies. The development of artificial intelligence has raised hopes of bringing great benefits, which can be reflected on the one hand in the Internet of Things (IoT), a huge set of capabilities, such as unmanned surveillance and targeting, health monitoring of soldiers, situational awareness and other critical applications. The trend is that decisions in future wars will require seconds, minutes, or even hours rather than days and weeks. This implies that the operational environment should be analyzed. By using artificial intelligence and machine learning, rapid information can be delivered to the frontline, which also means rapid decision-making. The Internet of Military Things is known to encompass many different tools, from battlefield sensors and weapon systems, to surveillance, intelligence, communications, wearables, and sensors on ships, aircraft, tanks, and the body. These tools collectively share an unprecedented amount of information in real-time during the war. The success of this issue depends on the ability to collect and store huge amounts of data from thousands of devices. However, a much more problematic issue is to quickly understand this information and deliver results to the fighters so that said information is useful and can be used. Ethical norms for the use of artificial intelligence differ from general ethical standards, artificial intelligence is more automated and scalable than most other processes, roles also include ethical risks - risk mitigation, legal risks reduction, human discrimination reduction, etc.

Consensus-Based Formation Control and Gyroscopic Obstacle Avoidance for Multiple Autonomous Underwater Vehicles on SE(3)

To address the control challenges posed by increasingly complex mission scenarios, this paper aims to develop an advanced formation control and obstacle avoidance strategy for autonomous underwater vehicles (AUVs) in SE(3). This study establishes a dynamic model for fully actuated AUVs and designs a consensus-based formation control strategy to achieve coordinated movement. Motivated by limitations of existing obstacle avoidance strategies such as local minima issues and mutual interference between formation members in high-density environments, this paper introduces a novel gyroscopic force-based obstacle avoidance method. The proposed approach leverages the principles of rotation and angular momentum conservation to enable effective obstacle avoidance while maintaining formation integrity. Simulation results demonstrate the effectiveness of the proposed methodology in achieving robust formation control and collision avoidance under challenging conditions.

Path tracking control of autonomous vehicles via prescribed performance approach

Path tracking control of autonomous vehicles via prescribed performance approach

Advanced Trajectory Planning and Control for Autonomous Vehicles with Quintic Polynomials.

This paper focuses on the design of vehicle trajectories and their control systems. A method based on quintic polynomials is utilized to develop trajectories for intelligent vehicles, ensuring the smooth continuity of the trajectory and related state curves under varying conditions. The construction of lateral and longitudinal controllers is discussed, which includes a tracking error model derived from the two-degree-of-freedom dynamic model of a two-wheeled vehicle and the application of the Frenet coordinate system transformation. The vehicle tracking performance is regulated by these controllers. Experimental verification on a small intelligent vehicle platform operating on the Ackermann steering principle was conducted. The results confirm the tracking performance of the controllers under different conditions and validate the effectiveness and feasibility of the overall framework of the study.

Meso Hybridized Silk Fibroin Watchband for Wearable Biopotential Sensing and AI Gesture Signaling.

Human biopotential signals, such as electrocardiography, are closely linked to health and chronic conditions. Electromyography, corresponds to muscle actions and is pertinent to human-machine interactions. Here, we present a type of smart and flexible watchband that includes a mini flexible electrode array based on Mo-Au filament mesh, combined with mesoscopic hybridized silk fibroin films. As the layer in contact with the skin, waterborne polyurethane and SF create a highly flexible and permeable meso-hybridized SF/WPU layer, ensuring skin-friendliness and comfortable wearing. The flexible FM electrodes are created by integrating Mo-Au FM into 2D-interconnected networks. Molybdenum filaments provide high rigidity and are coated with Aurum to enhance conductivity. The use of Mo-Au FMs in warp-knitted patterns results in high SNR (43.22 dB), high sensitivity (44.43 mV/kg), and significant motion noise reduction due to the pattern's elastic deformability and skin-gripping properties. Leveraging these unique technologies, these smart watchbands excel in prolonged sensing operation, grasping force detection, and gesture recognition. Through smart raining via deep learning, we achieved an unparalleled recognition rate (96% across 20 volunteers of different genders) among other EMG sensing devices. These results have significant implications for human-machine interaction, including applications in underwater robot control, drone operation, and autonomous vehicle control.

Safety-Critical Receding-Horizon Planning and Formation Control of Autonomous Surface Vehicles via Collaborative Neurodynamic Optimization.

This article addresses the safety-critical receding-horizon planning and formation control of autonomous surface vehicles (ASVs) in the presence of model uncertainties, environmental disturbances, as well as stationary and moving obstacles. A three-level formation control architecture is proposed with a safety-critical formation trajectory generation module at its high level, a collision-free guidance module at its middle level, and an anti-disturbance control module at its low level. Specifically, a safety-critical formation trajectory generator is designed by leveraging collaborative neurodynamic optimization to plan safe formation trajectories to track a given trajectory and avoid stationary obstacles in a receding-horizon manner. Based on control barrier functions, a collision-free line-of-sight guidance law is developed to generate safe guidance commands to avoid collision with moving obstacles and other vehicles. An anti-disturbance control law is customized with a finite-time convergent observer for a vehicle to follow the guidance command signals. Simulation and hardware-in-the-loop experimental results are elaborated to validate the efficacy of the proposed method for the receding-horizon planning and formation control of ASVs.

Combined-Slip Trajectory Tracking and Yaw Stability Control for 4WID Autonomous Vehicles Based on Effective Cornering Stiffness

Combined-Slip Trajectory Tracking and Yaw Stability Control for 4WID Autonomous Vehicles Based on Effective Cornering Stiffness

Centralized cooperative control for autonomous vehicles at unsignalized all-directional intersections: A multi-agent projection-based constrained policy optimization approach

Centralized cooperative control for autonomous vehicles at unsignalized all-directional intersections: A multi-agent projection-based constrained policy optimization approach

Trajectory tracking controller design for quadcopter under disturbances environment: using a hybrid approach

The development of a robust tracking controller for autonomous aerial vehicles to reach the desired point has become extremely important, especially when flying in the ground region. This paper proposes a hybrid controller (proportional fractional-order integral derivative sliding surface based on sliding mode control with backstepping (PFOIDSMCBS)) to control the quadcopter to flow the predefined trajectory. The proposed controller is designed to control the attitude, altitude, and angular motion with payload in the presence of external disturbances, wind, and ground effects. The performances of the proposed controller have been compared with the existing SMCBS controller. The simulation results show that the system satisfies the stability condition and is efficient in path tracking. As the vehicle approaches the ground, the simulation indicates a consistent linear increase in the total thrust generated by the rotors. In the landing, the proposed controller reduces settling time by 6.12% compared to SMCBS for the system without load. With a load, it reduces settling time by 5.17% compared to SMCBS. PFOIDSMCBS controller exhibits superior performance over SMCBS in terms of minimizing chattering effects and reducing control effort.

Adaptive event-triggered dynamic output feedback control for networked autonomous vehicles affected by signal quantization and actuator failures

In this paper, an event-triggered sliding-mode output feedback control (SMOFC) strategy with adaptive fault-tolerance is proposed to achieve path tracking for networked autonomous vehicles, considering the challenges posed by network communication and electric steering systems. Initially, signal quantization, external disturbances, and actuator faults are incorporated into the vehicle model. This incorporation enhances the designed controller’s robustness against a broader and more demanding range of driving scenarios. Subsequently, in situations where only output feedback is available, a dynamic output compensator is designed to reconstruct the unmeasurable vehicle state. Utilizing the reconstructed vehicle state, an event-triggered strategy is devised to alleviate the network burden and determine the minimum time between triggering events to prevent Zeno behavior. Furthermore, an adaptive mechanism is employed to estimate the actuator fault boundaries. The performance of the designed controller is evaluated through simulation instances.

Advanced heave control of a hydrofoil-based autonomous surface vehicle: CFD modeling with integrated variable propeller revolution control

An innovative control strategy employing the Proportional-Integral-Derivative (PID) algorithm is proposed to address the heave stability challenges in the in-house developed hydrofoil-based Autonomous Surface Vehicle (HASV). This method regulates the HASV's heave motion by adjusting the propeller's revolution speed. After confirming that the aerodynamic load on the superstructure contributes less than 2% compared to the hydrodynamic load, a detailed numerical simulation study and recirculating water tunnel test were conducted to validate the reliability of the established Unsteady Reynolds-Averaged Navier-Stokes (URANS) CFD model for the HASV substructure. The integration of the PD controller for propeller revolutions into the CFD free-running model, which incorporates fully nonlinear and viscous effects, was achieved using the ‘Region-Moving’ method for the background domain and the Body Force Method (BFM) for the propeller domain. By analyzing the impact of various PD coefficients on heave control, optimal settings for the HASV were determined. Subsequent studies examined the vehicle's capability in draft correction and draft maintenance under wave conditions. The results of direct CFD-PD simulations demonstrate that the proposed heave control method effectively stabilizes the HASV under complex nonlinear environmental conditions, offering valuable insights for addressing similar heave control challenges in hydrofoil-based vehicles.