Multirotors From Takeoff to Real-Time Full Identification Using the Modified Relay Feedback Test and Deep Neural Networks

Ayyad, Abdulla; Chehadeh, Mohamad; Silva, Pedro Henrique; Wahbah, Mohamad; Hay, Oussama Abdul; Boiko, Igor; Zweiri, Yahya

doi:10.1109/tcst.2021.3114265

Cited by 15 publications

(32 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental tests were conducted on a variety of UAV designs as shown in Table . IV. For clarity, we only present results obtained on the QDrone in this section while the remaining experimental results can be found in the appendix and are also presented in the companion video [4]. Optitrack's motion capture system was used for UAVs localization [37].…”

Section: Simulation and Experimental Resultsmentioning

confidence: 99%

“…After auto-tuning, the multirotor UAVs followed a trajectory resembling a square. Both auto-tuning experiments are shown in the video in [4].…”

Section: Discussionmentioning

confidence: 99%

“…To the best of our knowledge, DNN-MRFT is the first UAV full auto-tuning approach to successfully perform such aggressive maneuvers without any prior knowledge of system dynamics. A video demonstration of the DNN-MRFT auto-tuning capability for the three different UAV designs listed in Table IV, and vertical narrow window passage can be found in [4].…”

Section: B Takeoff and Full Channel Identificationmentioning

confidence: 99%

“…Additionally, the presented take-off and selftuning approaches can be used in more advanced applications that requires real-time control gains adaptation while guaranteeing stability limits. A video demonstration of the presented approach applied to multiple multirotor UAVs that shows robustness in identification phase and high performance in the control phase can be found in [4].…”

mentioning

confidence: 99%

See 3 more Smart Citations

Multirotors from Takeoff to Real-Time Full Identification Using the Modified Relay Feedback Test and Deep Neural Networks

Ayyad¹,

Chehadeh²,

Wahbah³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Low cost real-time identification of multirotor unmanned aerial vehicle (UAV) dynamics is an active area of research supported by the surge in demand and emerging application domains. Such real-time identification capabilities shorten development time and cost, making UAVs' technology more accessible, and enable a variety of advanced applications. In this paper, we present a novel comprehensive approach, called DNN-MRFT, for real-time identification and tuning of multirotor UAVs using the Modified Relay Feedback Test (MRFT) and Deep Neural Networks (DNN). The first contribution is the development of a generalized framework for the application of DNN-MRFT to higher-order systems. The second contribution is a method for the exact estimation of identified process gain which mitigates the inaccuracies introduced due to the use of the describing function method in approximating the response of Lure's systems. The third contribution is a generalized controller based on DNN-MRFT that takes-off a UAV with unknown dynamics and identifies the inner loops dynamics in-flight. Using the developed generalized framework, DNN-MRFT is sequentially applied to the outer translational loops of the UAV utilizing in-flight results obtained for the inner attitude loops. DNN-MRFT takes on average 15 seconds to get the full knowledge of multirotor UAV dynamics and was tested on multiple designs and sizes. The identification accuracy of DNN-MRFT is demonstrated by the ability of a UAV to pass through a vertical window without any further tuning, calibration, or feedforward terms. Such demonstrated accuracy, speed, and robustness of identification pushes the limits of state-of-the-art in real-time identification of UAVs.

show abstract

Section: Simulation and Experimental Resultsmentioning

confidence: 99%

“…After auto-tuning, the multirotor UAVs followed a trajectory resembling a square. Both auto-tuning experiments are shown in the video in [4].…”

Section: Discussionmentioning

confidence: 99%

Section: B Takeoff and Full Channel Identificationmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Multirotors from Takeoff to Real-Time Full Identification Using the Modified Relay Feedback Test and Deep Neural Networks

Ayyad¹,

Chehadeh²,

Wahbah³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…τ i n, T 1 , etc.). Selection of inner dynamics parameters is detailed in [25], and selection of lateral dynamics parameters is detailed in [24]. 2) Discretize the time parameters' domain with adequate discretization resolution that guarantees a certain upper bound of sub-optimality in performance.…”

Section: Model Parameters Identificationmentioning

confidence: 99%

Learning to Navigate Through Reinforcement Across the Sim2Real Gap

Azzam¹,

Chehadeh²,

Abdulhay³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>Amid the recent advances in robotics and machine learning, unmanned aerial vehicles (UAVs) have shown evident proliferation across various applications. Consequently, the involvement of UAVs in populated environments has progressively become inevitable, putting forward stringent safety and security measures. In this work, we develop a deep reinforcement learning-based UAV-navigation approach that blends decision making with behavioral intelligence. In particular, a reinforcement learning (RL) agent is trained to instruct the UAV on how to accomplish a goal-oriented task, while assuring the safety of the UAV and its surroundings. Upon arriving at the goal position, the RL agent slows the UAV down preparing it for landing. The safety of the UAV and the environment are attained through a robust collision avoidance capability, embedded into the RL-based navigation system and considers both static and dynamic obstacles in the environment. Training is exclusively carried out in simulation, where a high fidelity UAV controller model is used to perform the simulated maneuver. The proposed approach was tested in simulation and then shown to directly transfer to reality without explicit sim2real gap transfer techniques. Experimental results demonstrated the agent's capability to achieve the navigation task with 90% success rate.</p>

show abstract