E. van Kampen
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
153 records found
1
...
Exploring planetary bodies using robot swarms can potentially increase the value of the exploration missions; enabling the execution of novel measurements and explorations previously deemed impractical or unattainable. Despite its potential, the technology readiness level of planetary swarms is not very mature. This work uses multi-agent reinforcement learning to find control policies that allow swarms to autonomously explore unknown areas in a decentralized manner, contributing towards the technology readiness of the field. A multi-agent proximal policy optimization (MAPPO) algorithm is proposed for this end, where the policy uses LIDAR perception information, and the input of the value function contains local and global environment information. The algorithm finds control policies that achieve cooperation behaviors and generalize to unseen swarm sizes and environments learning with simple, sparse reward functions. Moreover, different types of reward functions, value inputs, and environment configurations are investigated.
...
Exploring planetary bodies using robot swarms can potentially increase the value of the exploration missions; enabling the execution of novel measurements and explorations previously deemed impractical or unattainable. Despite its potential, the technology readiness level of planetary swarms is not very mature. This work uses multi-agent reinforcement learning to find control policies that allow swarms to autonomously explore unknown areas in a decentralized manner, contributing towards the technology readiness of the field. A multi-agent proximal policy optimization (MAPPO) algorithm is proposed for this end, where the policy uses LIDAR perception information, and the input of the value function contains local and global environment information. The algorithm finds control policies that achieve cooperation behaviors and generalize to unseen swarm sizes and environments learning with simple, sparse reward functions. Moreover, different types of reward functions, value inputs, and environment configurations are investigated.
Incremental Dual Heuristic Programming (IDHP) is a successor to the Dual Heuristic Programming (DHP) algorithm that uses an online identified incremental system model, this algorithm showed promising online learning and fault tolerance in simulated flights. This paper studies the potential for extending IDHP through augmenting the computation of agent updates and returns, more specifically, by using eligibility trace updates and multi-step temporal difference error. This results in the IDHP, multi-step IDHP (MIDHP), and MIDHP variants, which are compared against IDHP in simulated flight scenarios with faults introduced mid-flight. The results demonstrate that flight controllers derived from the proposed variants have improved reference tracking & fault tolerance over the baseline IDHP, with the most improvement observed in MIDHP.
...
Incremental Dual Heuristic Programming (IDHP) is a successor to the Dual Heuristic Programming (DHP) algorithm that uses an online identified incremental system model, this algorithm showed promising online learning and fault tolerance in simulated flights. This paper studies the potential for extending IDHP through augmenting the computation of agent updates and returns, more specifically, by using eligibility trace updates and multi-step temporal difference error. This results in the IDHP, multi-step IDHP (MIDHP), and MIDHP variants, which are compared against IDHP in simulated flight scenarios with faults introduced mid-flight. The results demonstrate that flight controllers derived from the proposed variants have improved reference tracking & fault tolerance over the baseline IDHP, with the most improvement observed in MIDHP.
The Flying-V aircraft could revolutionize commercial aviation, boasting a potential 25% increase in aerodynamic efficiency. Due to inherent design limitations regarding static stability, a proper Flight Control System (FCS) is essential for the development of the aircraft. The concept of Hybrid Incremental Nonlinear Dynamic Inversion (INDI) was introduced to mitigate the insufficient stability margin encountered in existing sensor-based INDI systems due to sensor time delays to achieve Level 1 Handling Qualities (HQ). Furthermore, the research introduces an exponential potential function-based command limiting Flight Envelope Protection (FEP) to enhance safety compared to the currently implemented linear-based FEP. The study compares and evaluates the effectiveness of the updated system under various flight conditions and parametric uncertainties. Results show improved stability margins and a safer FEP. However, additional research is required into actuator saturation and control allocation issues during the approach condition and to enhance robustness.
...
The Flying-V aircraft could revolutionize commercial aviation, boasting a potential 25% increase in aerodynamic efficiency. Due to inherent design limitations regarding static stability, a proper Flight Control System (FCS) is essential for the development of the aircraft. The concept of Hybrid Incremental Nonlinear Dynamic Inversion (INDI) was introduced to mitigate the insufficient stability margin encountered in existing sensor-based INDI systems due to sensor time delays to achieve Level 1 Handling Qualities (HQ). Furthermore, the research introduces an exponential potential function-based command limiting Flight Envelope Protection (FEP) to enhance safety compared to the currently implemented linear-based FEP. The study compares and evaluates the effectiveness of the updated system under various flight conditions and parametric uncertainties. Results show improved stability margins and a safer FEP. However, additional research is required into actuator saturation and control allocation issues during the approach condition and to enhance robustness.
Commercial applications of flying wing aircraft present a unique opportunity to improve fuel efficiency in aviation but also pose significant challenges in stability and control. This paper improves the existing flight control laws of a commercial flying wing concept called the Flying V. The paper designs and evaluates normal law flight controls through piloted flight simulations on a moving base flight simulator, assessing handling qualities, certification compliance, and flight envelope protection capabilities. Industry-inspired outer guidance loops include envelope protections for angle of attack, bank, pitch, and load factor, using command-limiting exponential potential functions to smoothly enforce limits and prevent longitudinal instability. The inner loop employs incremental nonlinear dynamic inversion. Results demonstrate that the Flying V model, augmented with the proposed controller, achieves Level 1 handling qualities and meets nearly all certification requirements. Flight envelope protection maneuvers confirm that exponential potential functions deliver protection performance comparable to commercial aircraft and successfully prevent unstable behavior.
...
Commercial applications of flying wing aircraft present a unique opportunity to improve fuel efficiency in aviation but also pose significant challenges in stability and control. This paper improves the existing flight control laws of a commercial flying wing concept called the Flying V. The paper designs and evaluates normal law flight controls through piloted flight simulations on a moving base flight simulator, assessing handling qualities, certification compliance, and flight envelope protection capabilities. Industry-inspired outer guidance loops include envelope protections for angle of attack, bank, pitch, and load factor, using command-limiting exponential potential functions to smoothly enforce limits and prevent longitudinal instability. The inner loop employs incremental nonlinear dynamic inversion. Results demonstrate that the Flying V model, augmented with the proposed controller, achieves Level 1 handling qualities and meets nearly all certification requirements. Flight envelope protection maneuvers confirm that exponential potential functions deliver protection performance comparable to commercial aircraft and successfully prevent unstable behavior.
Simultaneous actuator and inertial measurement unit faults pose a significant challenge for flight safety. This study analytically demonstrates the impact of such faults on incremental nonlinear dynamic inversion (INDI)-based controllers and proposes an active fault-tolerant control method that concurrently mitigates these faults and accounts for in-flight turbulence. The method employs an optimal two-stage extended Kalman filter with a higher-order sliding mode differentiator (OTSEKF-HOSM) for inertial measurement unit fault identification, together with a variable forgetting factor recursive least squares (VFF-RLS) algorithm for online on-board model estimation, collectively forming the Active-Adaptive (AA) INDI framework. Numerical simulation results show that AA-INDI outperforms conventional and Adaptive INDI in terms of tracking performance under time-varying inertial measurement faults and sudden actuator failures.
...
Simultaneous actuator and inertial measurement unit faults pose a significant challenge for flight safety. This study analytically demonstrates the impact of such faults on incremental nonlinear dynamic inversion (INDI)-based controllers and proposes an active fault-tolerant control method that concurrently mitigates these faults and accounts for in-flight turbulence. The method employs an optimal two-stage extended Kalman filter with a higher-order sliding mode differentiator (OTSEKF-HOSM) for inertial measurement unit fault identification, together with a variable forgetting factor recursive least squares (VFF-RLS) algorithm for online on-board model estimation, collectively forming the Active-Adaptive (AA) INDI framework. Numerical simulation results show that AA-INDI outperforms conventional and Adaptive INDI in terms of tracking performance under time-varying inertial measurement faults and sudden actuator failures.
Sustainability is a key commitment for future innovation and improvement of the aerospace industry and to realise active research is invested towards advanced and new aircraft designs such as the Flying V. The Flying V is a flying wing design for commercial aviation, promising higher efficiency against conventional tube-and-wing aircraft. The Flight Control System (FCS) has to be designed to prove the airworthiness of the aircraft. In this work, a fault-tolerant FCS is designed that includes an adaptive incremental dynamic inversion inner loop rate control law with an outer loop that consists of longitudinal C* control law and Rate Control Attitude Hold roll control laws for lateral control. Research and activities has led to an updated geometry design with aerodynamic data from RANS simulation, which requires tuning of its outer loop flight controls to be within level 1 handling quality. To investigate the fault tolerance of the aircraft with a structural fault case that results in a loss of effectiveness. It is shown that the adaptation allows the aircraft to cope with the faults and maintain satisfactory tracking performance.
...
Sustainability is a key commitment for future innovation and improvement of the aerospace industry and to realise active research is invested towards advanced and new aircraft designs such as the Flying V. The Flying V is a flying wing design for commercial aviation, promising higher efficiency against conventional tube-and-wing aircraft. The Flight Control System (FCS) has to be designed to prove the airworthiness of the aircraft. In this work, a fault-tolerant FCS is designed that includes an adaptive incremental dynamic inversion inner loop rate control law with an outer loop that consists of longitudinal C* control law and Rate Control Attitude Hold roll control laws for lateral control. Research and activities has led to an updated geometry design with aerodynamic data from RANS simulation, which requires tuning of its outer loop flight controls to be within level 1 handling quality. To investigate the fault tolerance of the aircraft with a structural fault case that results in a loss of effectiveness. It is shown that the adaptation allows the aircraft to cope with the faults and maintain satisfactory tracking performance.
A morphing wing can create an optimal aerodynamic shape for different flight regimes, such as takeoff, cruising, and landing. This minimizes energy use and improves the sustainability of flight. Using meta-materials in the wing structure allows for a smooth transition when morphing between the wing box and the trailing edge. This article contributes a design for an automatic flight control system that can control an airplane under aerodynamic model uncertainties due to changes in the wing shape. The controller uses a cascaded design of nonlinear dynamic inversion (NDI) and incremental nonlinear dynamic inversion (INDI) structures. The outer-loop NDI controller uses a kinematic transformation to calculate the angular rates needed for the inner-loop INDI rate controller. The INDI controller uses dynamic inversion of the control effectiveness model to predict the necessary control surface deflections. The incremental part of the INDI controller reduces the dependency on the full aerodynamic model.
...
A morphing wing can create an optimal aerodynamic shape for different flight regimes, such as takeoff, cruising, and landing. This minimizes energy use and improves the sustainability of flight. Using meta-materials in the wing structure allows for a smooth transition when morphing between the wing box and the trailing edge. This article contributes a design for an automatic flight control system that can control an airplane under aerodynamic model uncertainties due to changes in the wing shape. The controller uses a cascaded design of nonlinear dynamic inversion (NDI) and incremental nonlinear dynamic inversion (INDI) structures. The outer-loop NDI controller uses a kinematic transformation to calculate the angular rates needed for the inner-loop INDI rate controller. The INDI controller uses dynamic inversion of the control effectiveness model to predict the necessary control surface deflections. The incremental part of the INDI controller reduces the dependency on the full aerodynamic model.
Commercial applications of flying wing aircraft present a unique opportunity to improve fuel efficiency in aviation, but also pose significant challenges in stability and control. This paper improves the existing flight control laws of a commercial flying wing concept called the Flying-V. The paper designs and evaluates normal law flight controls through piloted flight simulations on a moving base flight simulator, assessing handling qualities, certification compliance, and flight envelope protection capabilities. Industry-inspired outer guidance loops include envelope protections for angle of attack, bank, pitch, and load factor, using command limiting exponential potential functions to smoothly enforce limits and prevent longitudinal instability. The inner loop employs incremental nonlinear dynamic inversion. Results demonstrate that the Flying-V model, augmented with the proposed controller, achieves Level 1 handling qualities and meets nearly all certification requirements. Flight envelope protection maneuvers confirm that exponential potential functions deliver protection performance comparable to commercial aircraft and successfully prevent unstable behavior.
...
Commercial applications of flying wing aircraft present a unique opportunity to improve fuel efficiency in aviation, but also pose significant challenges in stability and control. This paper improves the existing flight control laws of a commercial flying wing concept called the Flying-V. The paper designs and evaluates normal law flight controls through piloted flight simulations on a moving base flight simulator, assessing handling qualities, certification compliance, and flight envelope protection capabilities. Industry-inspired outer guidance loops include envelope protections for angle of attack, bank, pitch, and load factor, using command limiting exponential potential functions to smoothly enforce limits and prevent longitudinal instability. The inner loop employs incremental nonlinear dynamic inversion. Results demonstrate that the Flying-V model, augmented with the proposed controller, achieves Level 1 handling qualities and meets nearly all certification requirements. Flight envelope protection maneuvers confirm that exponential potential functions deliver protection performance comparable to commercial aircraft and successfully prevent unstable behavior.
Commercial applications of flying wing aircraft, as the Flying-V here considered, can contribute to reducing carbon and nitrogen emissions produced by the aviation sector. However, because of the lack of a tail, all flying wing aircraft have reduced controllability. For this reason, the placement and sizing of the control surfaces along the wing is a non-trivial problem. The paper focuses on solving this problem using offline handling quality simulations based on certification requirements. In different flight conditions, the aircraft must be able to perform a certain set of maneuvers as defined by the certifying authorities. First, offline simulations calculate the minimum control authority required from the elevator, aileron, and rudder to perform each maneuver. Then, based on the global minimum for all maneuvers, the control surfaces are sized and placed along the wings. The aerodynamic model employed uses a combination of Reynolds-averaged Navier-Stokes (RANS) and vortex lattice method (VLM) simulations. The control authority of the control surfaces is estimated with VLM and VLM calibrated with RANS simulations, showing significant differences between the two.
...
Commercial applications of flying wing aircraft, as the Flying-V here considered, can contribute to reducing carbon and nitrogen emissions produced by the aviation sector. However, because of the lack of a tail, all flying wing aircraft have reduced controllability. For this reason, the placement and sizing of the control surfaces along the wing is a non-trivial problem. The paper focuses on solving this problem using offline handling quality simulations based on certification requirements. In different flight conditions, the aircraft must be able to perform a certain set of maneuvers as defined by the certifying authorities. First, offline simulations calculate the minimum control authority required from the elevator, aileron, and rudder to perform each maneuver. Then, based on the global minimum for all maneuvers, the control surfaces are sized and placed along the wings. The aerodynamic model employed uses a combination of Reynolds-averaged Navier-Stokes (RANS) and vortex lattice method (VLM) simulations. The control authority of the control surfaces is estimated with VLM and VLM calibrated with RANS simulations, showing significant differences between the two.
Commercial applications of flying wing aircraft, such as the Flying-V considered herein, can contribute to reducing carbon and nitrogen emissions produced by the aviation sector. However, because of the lack of a tail, all flying wing aircraft have reduced controllability. For this reason, the placement and sizing of the control surfaces along the wing is a nontrivial problem. The paper focuses on solving this problem using offline handling quality simulations based on certification requirements. In different flight conditions, the aircraft must be able to perform a set of maneuvers as defined by the certification specifications. First, offline simulations calculate the minimum control authority required from the elevator, aileron, and rudder to perform each maneuver. Then, based on the global minimum for all maneuvers, the control surfaces are sized and placed along the wings. The aerodynamic model employed uses a combination of Reynolds-averaged Navier–Stokes (RANS) and vortex lattice method (VLM) simulations. The control authority of the control surfaces is estimated with VLM and VLM calibrated with RANS simulations, showing significant differences between the two.
...
Commercial applications of flying wing aircraft, such as the Flying-V considered herein, can contribute to reducing carbon and nitrogen emissions produced by the aviation sector. However, because of the lack of a tail, all flying wing aircraft have reduced controllability. For this reason, the placement and sizing of the control surfaces along the wing is a nontrivial problem. The paper focuses on solving this problem using offline handling quality simulations based on certification requirements. In different flight conditions, the aircraft must be able to perform a set of maneuvers as defined by the certification specifications. First, offline simulations calculate the minimum control authority required from the elevator, aileron, and rudder to perform each maneuver. Then, based on the global minimum for all maneuvers, the control surfaces are sized and placed along the wings. The aerodynamic model employed uses a combination of Reynolds-averaged Navier–Stokes (RANS) and vortex lattice method (VLM) simulations. The control authority of the control surfaces is estimated with VLM and VLM calibrated with RANS simulations, showing significant differences between the two.
In the rapidly evolving aviation sector, the quest for safer and more efficient flight operations has historically relied on traditional Automatic Flight Control Systems (AFCS) based on high-fidelity models. However, such models not only incur high development costs but also struggle to adapt to new, complex aircraft designs and unexpected operational conditions. As an alternative, deep Reinforcement Learning (RL) has emerged as a promising solution for model-free, adaptive flight control. Yet, RL-based approaches pose significant challenges in terms of sample efficiency and safety assurance. Addressing these gaps, this paper introduces Returns Uncertainty-Navigated Distributional Soft Actor-Critic (RUN-DSAC). Designed to enhance the learning efficiency, adaptability, and safety of flight control systems, RUN-DSAC leverages the rich uncertainty information inherent in the returns distribution to refine the decision-making process. When applied to the attitude tracking task on a high-fidelity, non-linear fixed-wing aircraft model, RUN-DSAC demonstrates superior performance in learning efficiency, adaptability to varied and unforeseen flight scenarios, and robustness in fault tolerance that outperforms the current state-of-the-art SAC and DSAC algorithms.
...
In the rapidly evolving aviation sector, the quest for safer and more efficient flight operations has historically relied on traditional Automatic Flight Control Systems (AFCS) based on high-fidelity models. However, such models not only incur high development costs but also struggle to adapt to new, complex aircraft designs and unexpected operational conditions. As an alternative, deep Reinforcement Learning (RL) has emerged as a promising solution for model-free, adaptive flight control. Yet, RL-based approaches pose significant challenges in terms of sample efficiency and safety assurance. Addressing these gaps, this paper introduces Returns Uncertainty-Navigated Distributional Soft Actor-Critic (RUN-DSAC). Designed to enhance the learning efficiency, adaptability, and safety of flight control systems, RUN-DSAC leverages the rich uncertainty information inherent in the returns distribution to refine the decision-making process. When applied to the attitude tracking task on a high-fidelity, non-linear fixed-wing aircraft model, RUN-DSAC demonstrates superior performance in learning efficiency, adaptability to varied and unforeseen flight scenarios, and robustness in fault tolerance that outperforms the current state-of-the-art SAC and DSAC algorithms.
The Flying-V emerges as a unique flying wing type commercial aircraft design, distinguished by its V-shaped configuration. For such unconventional airframes, flight control systems are vital for ensuring safety and enhancing flight performance. Current Flying-V control systems primarily use incremental nonlinear dynamic inversion (INDI), a sensor-based feedback linearization method requiring an onboard control effectiveness model. Although INDI handles model uncertainties, significant mismatches between actual and onboard models caused by damages or faults degrade performance and compromise flight safety. This study proposes an adaptive strategy for incremental nonlinear dynamic inversion, employing an online two-step method to estimate changes in the aircraft’s control effectiveness. Estimates are used to update the onboard control effectiveness model to minimize the mismatch between the actual and onboard representation of control effectiveness.
...
The Flying-V emerges as a unique flying wing type commercial aircraft design, distinguished by its V-shaped configuration. For such unconventional airframes, flight control systems are vital for ensuring safety and enhancing flight performance. Current Flying-V control systems primarily use incremental nonlinear dynamic inversion (INDI), a sensor-based feedback linearization method requiring an onboard control effectiveness model. Although INDI handles model uncertainties, significant mismatches between actual and onboard models caused by damages or faults degrade performance and compromise flight safety. This study proposes an adaptive strategy for incremental nonlinear dynamic inversion, employing an online two-step method to estimate changes in the aircraft’s control effectiveness. Estimates are used to update the onboard control effectiveness model to minimize the mismatch between the actual and onboard representation of control effectiveness.
The Flying-V is a novel flying wing aircraft design that aims to improve aerodynamic efficiency and fuel consumption. In recent years, there has been an increased effort to evaluate the handling qualities (HQs) of the Flying-V, and to develop new flight control strategies. One of the latest flight control designs for the Flying-V uses Incremental Nonlinear Dynamic Inversion (INDI) with a Flight Envelope Protection system. The purpose of this research is to validate this FCS design and its conclusions on handling qualities by conducting piloted experiments. To facilitate a sound comparison, the aerodynamic model, flight control structure, and airframe characteristics are taken as is from the existing study. For the experiment, numerous maneuvers are designed and carried out. The experiment is performed on the SIMONA Research Simulator of the Delft University of Technology, with three real-life test pilots as participants. The results show a significant correlation with offline findings and demonstrate the improvement in HQs provided by the flight control system.
...
The Flying-V is a novel flying wing aircraft design that aims to improve aerodynamic efficiency and fuel consumption. In recent years, there has been an increased effort to evaluate the handling qualities (HQs) of the Flying-V, and to develop new flight control strategies. One of the latest flight control designs for the Flying-V uses Incremental Nonlinear Dynamic Inversion (INDI) with a Flight Envelope Protection system. The purpose of this research is to validate this FCS design and its conclusions on handling qualities by conducting piloted experiments. To facilitate a sound comparison, the aerodynamic model, flight control structure, and airframe characteristics are taken as is from the existing study. For the experiment, numerous maneuvers are designed and carried out. The experiment is performed on the SIMONA Research Simulator of the Delft University of Technology, with three real-life test pilots as participants. The results show a significant correlation with offline findings and demonstrate the improvement in HQs provided by the flight control system.
The critical challenge for employing autonomous control systems in aircraft is ensuring robustness and safety. This study introduces an intelligent and fault-tolerant controller that merges two Reinforcement Learning (RL) algorithms in a hybrid approach: the Distributional Soft Actor-Critic (DSAC) and the Incremental Dual Heuristic Programming (IDHP). The integration combines the strengths of DSAC in learning a robust control strategy and IDHP in allowing real-time control adaption. Compared to earlier controllers, such as a hybrid using the Soft Actor-Critic (SAC) algorithm and strictly offline DSAC and SAC, our hybrid demonstrates enhanced robustness against changing flight conditions and in the face of sensor noise and bias. During fault tolerance tests, it maintains superior control even when the effectiveness of the aircraft’s ailerons and elevators is compromised. By demonstrating the potential of RL-based controllers to provide robustness and fault tolerance, this research advances the feasibility of safe and autonomous flight control operations.
...
The critical challenge for employing autonomous control systems in aircraft is ensuring robustness and safety. This study introduces an intelligent and fault-tolerant controller that merges two Reinforcement Learning (RL) algorithms in a hybrid approach: the Distributional Soft Actor-Critic (DSAC) and the Incremental Dual Heuristic Programming (IDHP). The integration combines the strengths of DSAC in learning a robust control strategy and IDHP in allowing real-time control adaption. Compared to earlier controllers, such as a hybrid using the Soft Actor-Critic (SAC) algorithm and strictly offline DSAC and SAC, our hybrid demonstrates enhanced robustness against changing flight conditions and in the face of sensor noise and bias. During fault tolerance tests, it maintains superior control even when the effectiveness of the aircraft’s ailerons and elevators is compromised. By demonstrating the potential of RL-based controllers to provide robustness and fault tolerance, this research advances the feasibility of safe and autonomous flight control operations.
Reinforcement Learning applied to flight control has shown to have several benefits over classical, linear flight controllers, as it eliminates the need for gain scheduling and it could provide fault-tolerance. The application to civil aviation in practice, however, is non-existent as there are multiple safety concerns. This research demonstrates the evaluation of longitudinal Handling Qualities of the Soft Actor-Critic Deep Reinforcement Learning framework with the aim to translate the unpredictable black box of Reinforcement Learning into classical flight control terminology. The framework is applied to a pitch rate command system of a jet aircraft and shows robustness to off-nominal flight conditions, center of gravity shifts and biased sensor noise. Accurate tracking performance is achieved, while adhering to Level 1 longitudinal Handling Qualities for all conditions.
...
Reinforcement Learning applied to flight control has shown to have several benefits over classical, linear flight controllers, as it eliminates the need for gain scheduling and it could provide fault-tolerance. The application to civil aviation in practice, however, is non-existent as there are multiple safety concerns. This research demonstrates the evaluation of longitudinal Handling Qualities of the Soft Actor-Critic Deep Reinforcement Learning framework with the aim to translate the unpredictable black box of Reinforcement Learning into classical flight control terminology. The framework is applied to a pitch rate command system of a jet aircraft and shows robustness to off-nominal flight conditions, center of gravity shifts and biased sensor noise. Accurate tracking performance is achieved, while adhering to Level 1 longitudinal Handling Qualities for all conditions.
Evolutionary Reinforcement Learning
Hybrid Approach for Safety-Informed Fault-Tolerant Flight Control
Recent research in artificial intelligence potentially provides solutions to the challenging problem of fault-tolerant and robust flight control. This paper proposes a novel Safety-Informed Evolutionary Reinforcement Learning algorithm (SERL), which combines Deep Reinforcement Learning (DRL) and neuroevolution to optimize a population of nonlinear control policies. Using SERL, the work has trained agents to provide attitude tracking on a high-fidelity nonlinear fixed-wing aircraft model. Compared to a state-of-the-art DRL solution, SERL achieves better tracking performance in nine out of ten cases, remaining robust against faults and changes in flight conditions, while providing smoother action signals.
...
Recent research in artificial intelligence potentially provides solutions to the challenging problem of fault-tolerant and robust flight control. This paper proposes a novel Safety-Informed Evolutionary Reinforcement Learning algorithm (SERL), which combines Deep Reinforcement Learning (DRL) and neuroevolution to optimize a population of nonlinear control policies. Using SERL, the work has trained agents to provide attitude tracking on a high-fidelity nonlinear fixed-wing aircraft model. Compared to a state-of-the-art DRL solution, SERL achieves better tracking performance in nine out of ten cases, remaining robust against faults and changes in flight conditions, while providing smoother action signals.