Autopilot Research Articles

Composite Adaptive Attitude Control of Asteroid-Orbiting Spacecraft With Regressor Integral Excitation

This article (correspondence) develops a composite adaptive control system for the attitude trajectory tracking of a spacecraft in elliptic orbit around a uniformly rotating asteroid. It is assumed that the spacecraft’s moment of inertia and the asteroid’s gravitational parameters are unknown. The adaptation law designed here includes a positive semidefinite regressor-dependent matrix integral. For its synthesis, the tracking error as well as two model prediction errors are used. This enhances parameter excitation and causes faster decay of the parameter error. By the Lyapunov analysis, local convergence of the tracking error is established. In addition, it is shown that the trajectories of the system converge to two manifolds. Simulation results for a spacecraft on prograde elliptic orbit around asteroid 433 Eros are presented. These results show nadir-pointing attitude regulation. Interestingly, six out of nine unknown parameters are estimated accurately for certain proportional perturbations in the model parameters.

Action-State Joint Learning-Based Vehicle Taillight Recognition in Diverse Actual Traffic Scenes

As the vital factor of vehicle behavior understanding and prediction, vehicle taillight recognition is an important technology for autonomous driving, especially in diverse actual traffic scenes full of dynamic interactive traffic participants. However, in practical application, it always faces many challenges, such as ‘variable lighting conditions’, ‘non-uniform taillight standards’ and ‘random relative observation pose’, which lead to few mature solutions in current common autopilot systems. This work proposes an action-state joint learning-based vehicle taillight recognition method on the basis of vehicles detection and tracking, which takes both taillight state features and time series features into account, consequently getting practicable results even in complex actual scenes. In detail, vehicle tracking sequence is used as input and split into pieces through a sliding window. Then, a CNN-LSTM model is applied to simultaneously identify the action features of brake lights and turn signals, dividing taillight actions into five categories: None, Brake_on, Brake_off, Left_turn, Right_turn. Next, the brightness of high-position brake light is extracted through semantic segmentation and combined with taillight actions to form higher-level features for taillight state sequence analysis. Finally, an undirected graph model is used to establish the long-term dependence between successive pieces by analysing the higher-level features, thus inferring the continuous taillight state into: <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$off$ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$brake$ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$left$ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$right$ </tex-math></inline-formula> . Datasets including daytime, nighttime, congested road, highway, etc. were collected, tested and published in our work to demonstrate its effectiveness and practicability.

CNS Flight Stack for Reproducible, Customizable, and Fully Autonomous Applications

While low-level auto pilot stacks for aerial vehicles focus on robust control, sensing, and estimation, the continuous advancement of higher-level autonomy for aerial vehicles requires much more complex higher-level flight stacks in order to enable safe, fully autonomous long-duration missions. Rather than focusing on the low-level control, high-level flight stacks are required to monitor the system's integrity continuously, initiate contingency plans, execute mission plans and adapt them in non-nominal situations, allow for proper data logging, and provide standardized interfaces and integrity verification for external mission planners and localization modules. To that end, we present our freely available, high-level flight stack dubbed CNS Flight Stack that meets the above requirements and at the same time a) is platform-agnostic through a generalized (embedded) hardware abstraction layer, b) uses low compute complexity for online use on embedded hardware, and c) can be extended with other sensor modalities, integrity checks, and mission modules. These additional properties make it reproducible on a variety of different platforms for safe and fully autonomous applications. We tested the proposed flight stack in over 450 real-world flights and report the failure modes our framework detected and also mitigated to avoid crashes of the aerial system.

Predictive Control of the Mobile Robot under the Deep Long-Short Term Memory Neural Network Model.

At present, there is a phenomenon of network data packet loss in the trajectory tracking control system, which will degrade or even destabilize the system's performance. Therefore, this work first explains the theory of the deep long-short term memory (LSTM) neural network model, the kinematic model of mobile robots, and the trajectory tracking error model. The reasons for data packet loss in the control system are analyzed. Second, a prediction model based on the LSTM network is designed according to the theory mentioned above. Finally, the training effect of the LSTM model and the robot trajectory tracking effect based on the model are tested by setting up simulation experiments. The research results are as follows: (1) The pose test error of the mobile robot will eventually tend to zero through the simulation curve generated by the pose parameters (x, y, θ) of the mobile robot. (2) The trajectory tracking error of the deep LSTM neural network prediction and compensation method with the packet loss rate of 5% is less than that with the packet loss rate of 10%. (3) The linear velocity υ of the mobile robot based on the prediction model of the LSTM network varies greatly but is always in the interval (−2, 2). Its angular velocity ω initially fluctuates greatly but gradually tends to zero after about 13 s. (4) When the prediction model tracks the trajectory of the robot, the horizontal position x, the vertical position y, and the angle θ coincide with the reference trajectory. The exploration is conducted to provide a reference for the research on data packet loss in the networked mobile robot trajectory tracking system.

Membership-Function-Dependent Control Design of Interval Type-2 Sampled-Data Fuzzy-Model-Based Output-Feedback Tracking Control System

This article focuses on the stability analysis and control design of an interval type-2 sampled-data fuzzy-model-based output-feedback (IT2SDFMBOF) tracking control system, which is formed by the interval type-2 (IT2) Takagi–Sugeno (T–S) fuzzy model, the stable reference model, and the interval type-2 sampled-data output-feedback (IT2SDOF) fuzzy controller. The design goal is to establish a proper IT2SDOF fuzzy controller that is able to drive the states of the nonlinear plant subject to uncertainties to track those of the stable reference model, and the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$H_\infty$</tex-math></inline-formula> performance index is adopted to optimize the tracking control performance. To improve the robustness of the IT2SDOF fuzzy controller against uncertainties of the nonlinear plant, IT2 fuzzy sets are utilized. Considering that the tracking control system is sampled-data (SD) type, a two-sided looped-functional-based approach exploiting the information on the interval from time <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$t_k$</tex-math></inline-formula> to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$t$</tex-math></inline-formula> and the interval from time <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$t$</tex-math></inline-formula> to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$t_{k+1}$</tex-math></inline-formula> is applied to enhance the stability analysis. The imperfect premise matching (IPM) concept permits the number of rules and the premise membership functions of the IT2 T-S fuzzy model and the IT2SDOF fuzzy controller to be different, which can be employed to promote the design flexibility. The tracking control system with the SD type and IPM design will cause the membership grades between the IT2 T-S fuzzy model and the IT2SDOF fuzzy controller to be mismatched. In addition, the membership-function-dependent stability analysis approach that can introduce the boundary information of membership functions into the stability analysis is used to relax the stability conditions. The relaxed stability conditions subject to the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$H_\infty$</tex-math></inline-formula> performance building on the Lyapunov stability theory are developed in terms of linear matrix inequalities. Simulation results demonstrate the effectiveness of the proposed IT2SDFMBOF tracking control system.

Performance evaluation of MDKF based on state estimations for path tracking applications

One of the most difficult tasks for tracking in control systems in the presence of uncertainty is estimating the accuracy and efficiency of hidden variables. For tracking applications, the Kalman filter is the most extensively used estimation algorithm. However, tracking several objects remains a difficult effort in order to improve prediction and corrective results. For tracking several objects, a multi-dimensional Kalman filter (MDKF) based on state estimations is offered as a solution. This research also includes a performance analysis of the MDKF for tracking paths by modifying co-efficients of the steady-state and covariance equations. For linear dynamic systems, MDKF is evaluated. Path tracking using the Kalman filter and MDKF is also investigated. The true and filtered responses of MDKF filtering algorithm for path tracking are observed. After four trials, the output covariance yields steady state values. The simulation results reveal that our proposed filtering algorithm performs 2x better than a typical Kalman filter for objects moving in linear motion, indicating that it is suitable for real-time implementation.

Characterizing the use of Tesla’s Auto Lane Change Feature in Driver-Initiated Maneuvers

Tesla auto lane change is a feature within Autopilot (AP) – a collection of automated driving features designed to assist the driver with automatic steering and adaptive cruise control. In order to determine how drivers engage in maneuvers performed automatically by AP, 5,154 manual and automated lane change events along with video, system data, and vehicle kinematics were extracted from over 691 hours of naturalistic driving from 19 different drivers. Findings indicate that drivers performed manual lane changes more frequently than auto lane changes despite the use of Autopilot being more prevalent than manual driving on motorways. Auto lane changes occurred at higher speed and were associated with fewer acceleration and braking events and narrower distributions of kinematic characteristics. The lower frequency and kinematic variability in auto lane changes may suggest that drivers use this feature in a limited set of circumstances.

Tracking and Regulation Performance Limitations of Networked Control Systems Over Erasure Channel With Input Quantization

Limitations in communication networks, such as delays, packet dropouts, and insufficient bandwidth, create great challenges in the output tracking control and regulation performance of networked control systems. In this article, we propose some novel performance indexes for achieving the optimal tracking and regulation performance. By considering the influences of noise, packet dropouts, and logarithmic quantization on the channel input, the performance limitations of the networked systems are investigated by applying a two-degree-of-freedom (TDOF) control technique. The results obtained prove that the tracking and regulation performance is dependent not only on the position of the plant’s nonminimum phase zeros and unstable poles, but also on the directions. Furthermore, it is demonstrated that noise and quantization error have a negative influence on the control performance, and the design of the TDOF controller can eliminate the effect of packet dropouts on control performance. To validate the innovation results, several simulations are conducted.

Trajectory Tracking Control for Small Electric Sweeper Based on the Hybrid Control Method

Background: Trajectory tracking, one of the critical automatic driving technologies, is significant for the operation of small electric sweepers working in complex road environments, such as campuses and closed parks. Methods: This paper investigates a trajectory tracking control system for small self-driving electric sweepers on roads with different operating speed requirements. A hybrid control method combining sliding mode control and model predictive control is proposed, with sliding mode control operating under low-speed (&lt;2 m/s) conditions, and model predictive control operating under high-speed (&gt;2 m/s) conditions. An improved sliding mode controller based on the kinematic model is designed to reduce chattering, and a model predictive controller based on the dynamics model is constructed. Result: Finally, the performance of the hybrid control method is verified using the MATLAB/ Simulink platform. Conclusion: The simulation results prove the effectiveness of the hybrid control method and the good tracking performance of the electric sweeper at different driving speeds.

A Gain-Scheduled Robust Controller for Autonomous Vehicles Path Tracking Based on LPV System With MPC and H ∞

Due to the uncertainty of vehicle model parameters, modeling errors and external disturbances, the performance of path tracking control system is poor, especially under high velocity and large curvature extreme conditions. To address this issue, this paper presents a novel gain-scheduled robust control strategy based on linear parameter varying system with model predictive control (MPC) and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">H</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">∞</sub> . Firstly, fully considering the influence of the time-varying characteristics of vehicle velocity and tire cornering stiffness on the path tracking system model, a novel linear parameter varying system model is built for path tracking control of autonomous vehicle. Then, a path tracking robust controller is designed based on gain-scheduled approach, and the linear matrix inequality (LMI) is applied to solve optimization problem, in which MPC and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">H</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">∞</sub> robust control theory are applied to the controller design process. Finally, the simulation experiments have verified that the proposed novel robust control strategy can improve the path tracking accuracy and ensure the vehicle lateral and roll stability, especially under high velocity and large curvature extreme conditions. Meanwhile, the proposed robust controller shows superiority to suppress the parameters uncertainty, modeling error and external disturbance.

Pathfinder Networks for Measuring Operator Mental Model Structure with a Simple Autopilot System

Pathfinder networks are a method to represent mental models from empirically generated pairwise relatedness ratings. This study examined the effects of training exposure on mental model structures based on relatedness ratings collected using the Target Rating method. Forty-eight participants read instruction slides with or without explicit information on the functionality of an autopilot system (Advanced Mental Model or Basic Mental Model groups, respectively). Participants provided relatedness ratings and completed a comprehension test. The Advanced Mental Model group had more common links with the expected model, higher within-group network similarity scores, and higher mental model assessment questionnaire scores than the Basic Mental Model group. Both groups had coherence scores above the minimum threshold for internal consistency. Pathfinder network analysis was sensitive to changes produced by a simple exposure training intervention. In practice, a simple training program may effectively influence operator mental models in novel technological environments such as Advanced Air Mobility.

Coordinated Attitude Control of Spacecraft Formation Flying via Fixed-Time Estimators under a Directed Graph

This paper mainly studies the distributed fixed-time coordinated attitude tracking control problem of spacecraft formation with a dynamic leader spacecraft under directed communication topology. Follower spacecraft cannot communicate directly with the leader spacecraft; therefore, in order to enable them to obtain the target attitude information, a fixed-time state estimator that can be applied to directed graphs is designed. Based on the estimators, a distributed fixed-time attitude tracking control law is proposed. The settling time of the fixed-time algorithm is only related to the parameters of the control law and independent of the initial state; thus, the proposed control law can reduce the influence of the dynamic leader attitude on the spacecraft formation-coordinated attitude tracking control system. Moreover, external disturbances and spacecraft inertia uncertainty were also considered in the design of the control law. The stability of the system was verified by Lyapunov stability theory, and the effectiveness of the control law was verified by numerical simulation.

Evaluation of Auto Pilot Situational Awareness System Using Gunshot Detection Algorithm in a Localized Environment: Case Study Federal Polytechnic Offa, Mini Campus

Gunshot detection technologies are more applicable in many industries for the security enhancement of public places like the Federal Republic Territory FCT Abuja in Nigeria. Many factors affect the accuracy of the gun detection algorithm. This paper describes an audio-based video surveillance system in an auto pilot situational awareness to detect gunshots in Federal Polytechnic Offa. The Time Difference of Arrival (TDOA) of Shock Wave and Muzzle Blast is integrated to estimate the shooter location in the study are. The proposed design and algorithm was validated and shooter origin was resolute that was very close to theoretical values. The video camera is steering regarding the initial position to localize the acoustic source's position. Implementing an auto pilot situational awareness system is an experimental procedure with a gunshot detection algorithm in a localized environment. In the direction of the weapon, the distance between firearms, types of ammunition, types of study environment, and diffraction of audio, the standard feature for gunshot recognition are Mel frequency cepstral coefficients in terms of uniform gamma-tone filters linearly spaced over the whole frequency range from 0KHZ to 16KHZ. Experiments show that our system can detect gunshots with a precision of 93% at a false rejection rate of 5% when the SNR is 10db while proving the estimate of the source direction of the gunshot with an accuracy of one degree. The outcomes reveal that the data generated by the system can be leveraged by the firefighting department to quickly locate the whereabouts of the indoor fires, and the VR gamification scenarios can expedite the development of situational awareness for the trainees. The research recommends a real-time system implementation for protecting the Federal Polytechnic Offa against any form of treats.

Tethered Architectures in Cyber-Physical System Development: The Case of Tesla’s Autopilot System

Cyber-physical systems developed to operate under environmental uncertainty, such as self-driving cars, represent challenges within the new product development process. The amount of data and need for iteration of software in addressing the variety and complexity of use environments can conflict with the realities of hardware development lead-time and manufacture. Furthermore, developing new capabilities requires the ability to learn from product use. Current theories regarding product architecture do not provide an adequate architectural blueprint for the development of cyber-physical systems. In this research, through a longitudinal analysis of Tesla's Autopilot system, we propose the concept of a “tethered architecture”. A tethered architecture simultaneously allows the slower, incremental iteration of hardware to be linked with faster, exploratory development of software and continual data-rich feedback loops between product development and use. This paper demonstrates how a tethered product architecture and related development process can enable continuous cycles of learning and adaptation to the variety and complexity of physical environments and situations. This architectural reconfiguration decouples hardware and software while introducing a tight integration between the consumer-facing product and backend software infrastructure and operations. The iterative nature of product development may prove identity-challenging for firms that have traditionally focused on developing complete products, as a tethered architecture gives rise to new product strategies, lifecycle models, knowledge regimes, and organizational arrangements.

Fractional-Order Terminal Sliding-Mode Control Using Self-Evolving Recurrent Chebyshev Fuzzy Neural Network for MEMS Gyroscope

To maintain the vibrations of the gyroscope proof mass, a trajectory tracking control system using a neural network estimator is proposed. The proposed control system incorporates a fractional controller based on the terminal sliding-mode and a recurrent Chebyshev fuzzy neural network using a self-evolving mechanism. The fractional-order terminal sliding-mode control can guarantee the tracking error exponential stable, and a self-evolving recurrent Chebyshev fuzzy neural network (SERCFNN) is introduced to relax the requirement of nonlinear functional certainty. In addition, the SERCFNN develops the advantages of the self-evolving fuzzy neural network (SEFNN), recurrent fuzzy neural network (RFNN), and Chebyshev function network (CFN). The SEFNN can adaptively update the dynamic structure through generating and adjusting fuzzy logic rules. The RFNN improves the performance for coping with a temporal problem with the capability to store prior information. The CFN is capable to enlarge the dimensionality of the input variables. Moreover, the asymptotic stability of the proposed control system can be proved by the Lyapunov stability theory. The effectiveness and superiority of the performance are exhibited with simulation studies and comprehensive comparisons.

Unstructured Road Detection Method Based on RGB Maximum Two-Dimensional Entropy and Fuzzy Entropy

To solve the problem that lane keeping function for automatic driving and vehicle assisted driving will not work reliably on unstructured road without lane lines or other guide markings, this article uses the characteristics of information entropy to generate the RGB entropy image to pre-segment the road region on unstructured road image. At the same time, the maximum two-dimensional entropy algorithm is introduced to achieve the joint segmentation using gray and neighborhood gray to effectively reduce the impact of interference on segmentation. After that, the fuzzy entropy algorithm is used to judge and determine the actual road boundary by combining the results of RGB and maximum two-dimensional entropy image. Finally, using the improved least square fitting quadratic curve model to build the road boundary. Our method could well and rapidly extract the lane from unstructured road image and fit out the lane line, which helps to achieve visual based lane keeping on unstructured road for autopilot and driver assistance system.

Unmanned systems and experience of their application in agriculture

The use of unmanned aerial vehicles (UAVs) is booming in almost every sector of the economy, especially in the agricultural industry. According to some reports, the agricultural UAV market is expected to increase from USD 2.6 billion in 2020 to USD 9.5 billion in 2030. In this paper a brief overview devoted to the use of UAVs in the Russian State Agrarian University – Moscow Timiryazev Agricultural Academy (RSAU-MTAA), including the results of studying the equipment use effectiveness for automatic driving of tractor equipment when sowing grain crops and planting potatoes. In the course of studying the equipment use effectiveness for automatic driving of tractor equipment, the deviations of the guess row spacing from the standard row spacing provided for by the seeder design were established; in the case of sowing barley using a marker, it was up to 4.3 cm, and in the case of winter wheat it was up to 5 cm. When using the autopilot system, these values were no more than 1.5 and 2.3 cm, respectively, which indicates the high accuracy and efficiency of the automatic driving systems. The autopilot system use provided a deviation of adjacent rows from the straightness when planting potatoes from 2.8 to 3.0 cm. The paper concludes that the use of unmanned robotic systems in agriculture, in conjunction with modern means of receiving and processing information, opens up new opportunities for increasing agriculture efficiency.

A new control strategy of stopped-rotor aircraft based on manipulation model

PurposeThe purpose of this paper is to study the control strategy of transition mode of the stopped-rotor (SR) aircraft under the condition of redundant control and complex aerodynamic characteristics.Design/methodology/approachThis paper first proposes a transition strategy for the conversion between helicopter mode and fixed-wing mode. Then, aiming at the redundancy of the two control systems in the transition process, a control model is proposed, which greatly simplifies the control in conversion mode. Then, to facilitate the design of the control system, the Takagi-Sugeno model of the SR aircraft in transition mode is established. Finally, an explicit model tracking and tuning parameter stability augmentation control system is designed, so that the SR aircraft has a good stability during the transition process. Then, the outer loop control system of transition flight is designed.FindingsThe simulation results show that the control strategy proposed in this paper can realize the mode conversion well. It lays a solid foundation for the subsequent engineering flight test for the SR aircraft.Originality/valueThe work done in this paper provides ideas and methods for the flight control system design of SR aircraft in transition mode. The method of designing control model to solve the coordination of redundant control system is also applicable for other multimode aircraft, which provides a simple and convenient method for the multimode aircraft control.

A New combined MPPT-Pitch Angle control of a Large Variable Speed Wind Turbine in Different Operating Areas based on Synergetic control

The aim of this paper is to create a novel combination between two controls, maximum power point tracking (MPPT) and Pitch angle control system of a variable-speed wind turbine. The main objective sought is to achieve the maximization of the power produced by the fixed pitch angle turbine through the MPPT control in the zone 02 of operation. Then, limit the power to its nominal value by using the Pitch control with variable pitch angle in zone 03 of operation. Our contribution will be to propose strategies based on two types of controllers. The first is the control by the MPPT control, it is applied in light winds to extract the maximum power. The second is Variable Pitch Control, which is applied in strong winds to keep power constant at its nominal value, as well as protecting the wind turbine from high winds. For this, linear and non-linear control laws (PI, SC) respectively are implemented to achieve the defined objective. The simulation results show the feasibility and effectiveness of the techniques used.

Pilot Behavior Recognition Based on Multi-Modality Fusion Technology Using Physiological Characteristics.

With the development of the autopilot system, the main task of a pilot has changed from controlling the aircraft to supervising the autopilot system and making critical decisions. Therefore, the human–machine interaction system needs to be improved accordingly. A key step to improving the human–machine interaction system is to improve its understanding of the pilots’ status, including fatigue, stress, workload, etc. Monitoring pilots’ status can effectively prevent human error and achieve optimal human–machine collaboration. As such, there is a need to recognize pilots’ status and predict the behaviors responsible for changes of state. For this purpose, in this study, 14 Air Force cadets fly in an F-35 Lightning II Joint Strike Fighter simulator through a series of maneuvers involving takeoff, level flight, turn and hover, roll, somersault, and stall. Electro cardio (ECG), myoelectricity (EMG), galvanic skin response (GSR), respiration (RESP), and skin temperature (SKT) measurements are derived through wearable physiological data collection devices. Physiological indicators influenced by the pilot’s behavioral status are objectively analyzed. Multi-modality fusion technology (MTF) is adopted to fuse these data in the feature layer. Additionally, four classifiers are integrated to identify pilots’ behaviors in the strategy layer. The results indicate that MTF can help to recognize pilot behavior in a more comprehensive and precise way.