Abstract

This paper presents a simple method for stabilizing the quadrotor dynamics under complete loss of one actuator using two-stage optimal control. Detailed equilibrium analysis and subsequent selection of operating point under actuator loss are provided, incorporating constraints on the maximum available thrust. A detailed simulation study using a high-fidelity nonlinear model of the quadrotor is presented showing the stability and performance of the closed-loop system under complete actuator loss, in the presence of external disturbances.

Abstract

Crack segmentation plays a crucial role in ensuring the structural integrity and seismic safety of civil structures. However, existing crack segmentation algorithms encounter challenges in maintaining accuracy with domain shifts across datasets. To address this issue, we propose a novel deep network that employs incremental training with unsupervised domain adaptation (UDA) using adversarial learning, without a significant drop in accuracy in the source domain. Our approach leverages an encoder-decoder architecture, consisting of both domain-invariant and domain-specific parameters. The encoder learns shared crack features across all domains, ensuring robustness to domain variations. Simultaneously, the decoder's domain-specific parameters capture domain-specific features unique to each domain. By combining these components, our model achieves improved crack segmentation performance. Furthermore, we introduce BuildCrack, a new crack dataset comparable to sub-datasets of the well-established CrackSeg9K dataset in terms of image count and crack percentage. We evaluate our proposed approach against state-of-the-art UDA methods using different sub-datasets of CrackSeg9K and our custom dataset. Our experimental results demonstrate a significant improvement in crack segmentation accuracy and generalization across target domains compared to other UDA methods - specifically, an improvement of 0.65 and 2.7 mIoU on source and target domains respectively. Code, models, and dataset will be made available.

Abstract

This paper explores the critical issue of enhancing cybersecurity measures for low-cost, Wi-Fi-based Unmanned Aerial Vehicles (UAVs) against Distributed Denial of Service (DDoS) attacks. In the current work, we have explored three variants of DDoS attacks, namely Transmission Control Proto col (TCP), Internet Control Message Protocol (ICMP), and TCP + ICMPflooding attacks, and developed a detection mechanism that runs on the companion computer of the UAV system. As a part of the detection mechanism, we have evaluated various machine learning, and deep learning algorithms, such as XGBoost, Isolation Forest, Long Short-Term Memory (LSTM), Bidirectional-LSTM (Bi-LSTM), LSTM with attention, Bi LSTM with attention, and Time Series Transformer (TST) in terms of various classification metrics. Our evaluation reveals that algorithms with attention mechanisms outperform their counterparts in general, and TST stands out as the most efficient model with a run time of ∼0.1 seconds. TST has demonstrated an F1 score of 0.999, 0.997, and 0.943 for TCP, ICMP, and TCP + ICMP flooding attacks respectively. In this work, we present the necessary steps required to build an on board DDoS detection mechanism. Further, we also present the ablation study to identify the best TST hyperparameters for DDoS detection, and we have also underscored the advantage of adapting learnable positional embeddings in TST for DDoS detection with an improvement in F1 score from 0.94 to 0.99.

Abstract

Flapping-wing robots (FWR) have domain-specific applications, where the lack of a fast-rotating propeller makes them safer when operating in complex environments with human proximity. However, most existing research in flapping-wing robots focuses on improving range/endurance or increasing payload capacity. This paper proposes a modular powertrain-based flapping-wing robot as a versatile solution to a mission-specific priority switch between payload or range for the same FWR. As the flapping frequency and stroke amplitude directly influence the flight characteristics of the FWR, we exploit this relation when designing our swappable powertrain with different motorgearbox combinations and 4-bar crank lengths to obtain the desired frequency and amplitude. We calculate initial estimates for default configuration and simulate it using pterasoftware. We then fabricate two powertrain modules - a default configuration with a higher flapping frequency for payload purposes and an extended-range configuration with a tandem propeller for higher flight velocity for longer range and endurance. To verify the results, we compare the flight test data of both power train configurations using the same FWR platform.

Abstract

In this study, we address the challenge of obstacle avoidance for Unmanned Aerial Vehicles (UAVs) through an innovative composite imitation learning ap- proach that combines Proximal Policy Optimization (PPO) with Behavior Cloning (BC) and Generative Adversarial Imitation Learning (GAIL), enriched by the integration of ray-tracing techniques. Our research underscores the sig- nificant role of ray-tracing in enhancing obstacle detection and avoidance capabilities. Moreover, we demonstrate the effectiveness of incorporating GAIL in coordinating the flight paths of two UAVs, showcasing improved collision avoidance capabilities. Extending our methodology, we apply our combined PPO, BC, GAIL, and ray-tracing framework to scenarios involving four UAVs, illustrating its scalability and adaptability to more complex scenarios. The findings indicate that our approach not only improves the reliability of basic PPO based obstacle avoidance but also paves the way for advanced autonomous UAV operations in crowded or dynamic environments.

Abstract

This research paper presents a novel low computational approach for navigating a micro UAV (Unmanned Aerial Vehicle) through narrow passages using only its onboard camera feed and a PID control system. The proposed method uses edge detection and homography techniques to extract the key features of the passage from the camera feed, and then employs a tuned PID controller to guide the UAV through and out of the passage while avoiding collisions with the walls. To evaluate the effectiveness of the proposed approach, a series of experiments were conducted using a micro-UAV navigating in and out of a custom-built test environment (constrained rectangular box). The results demonstrate that the system is able to successfully guide the UAV through the passages while avoiding collisions with the walls

Abstract

This paper introduces a novel approach for fault detection and localization in a motor of a Hexacopter UAV. The proposed two-stage architecture leverages Long Short-Term Memory (LSTM) networks for latent temporal feature extraction and Random Forest for localization. By combining them, we see improved fault detection and isolation performance. Our evaluations show the robustness of this approach in varying noise levels and real-world-like environments. Analysis of computational efficiency in rapid detection shows that the model identified faults within 2-5 time steps of the flight. Finally, we show that the proposed method surpasses classical statistical models and deep learning techniques in terms of overall accuracy (96.78%).

Abstract

This paper presents a novel algorithm for a swarm of unmanned aerial vehicles to search for an unknown source. The proposed method is inspired by the well-known particle swarm optimization (PSO) algorithm and is called accelerationbased particle swarm optimization (APSO) to address the sourceseeking problem with no a priori information. Unlike the conventional particle swarm optimization algorithm, where the particle velocity is updated based on the self-cognition and socialcognition information, here the update is performed on the particle acceleration. A theoretical analysis is provided, showing the stability and convergence of the proposed acceleration-based particle swarm optimization algorithm. Conditions on the parameters of the resulting third-order update equations are obtained using Jury’s stability test. High-fidelity simulations performed in CoppeliaSim, show the improved performance of the proposed acceleration-based particle swarm optimization algorithm for searching an unknown source when compared with the state-ofthe-art particle swarm-based source-seeking algorithms. From the obtained results, it is observed that the proposed method performs better than the existing methods under scenarios like different inter unmanned aerial vehicle communication network topologies, varying numbers of unmanned aerial vehicles in the swarm, different sizes of search regions, restricted source movement, and in the presence of measurements noise.

Abstract

Deep Reinforcement Learning is quickly becoming a popular method for training autonomous Unmanned Aerial Vehicles (UAVs). Our work analyzes the effects of measurement uncertainty on the performance of Deep Reinforcement Learning (DRL) based waypoint navigation and obstacle avoidance for UAVs. Measurement uncertainty originates from noise in the sensors used for localization and detecting obstacles. Measurement uncertainty/noise is considered to follow a Gaussian probability distribution with unknown non-zero mean and variance. We evaluate the performance of a DRL agent, trained using the Proximal Policy Optimization (PPO) algorithm in an environment with continuous state and action spaces. The environment is randomized with different numbers of obstacles for each simulation episode in the presence of varying degrees of noise, to capture the effects of realistic sensor measurements. Denoising techniques like the low pass filter and Kalman filter improve performance in the presence of unbiased noise. Moreover, we show that artificially injecting noise into the measurements during evaluation actually improves performance in certain scenarios. Extensive training and testing of the DRL agent under various UAV navigation scenarios are performed in the PyBullet physics simulator. To evaluate the practical validity of our method, we port the policy trained in simulation onto a real UAV without any further modifications and verify the results in a real-world environment.

Abstract

The control system design specifications for dynamical systems are typically provided in terms of the desired transient response and steady-state response. Meeting such requirements for dynamical systems whose mathematical models are unavailable is a challenging task. In this paper, we propose a learning-based controller to achieve the desired control system design specifications for unknown dynamical systems. We consider a SoTA model-free reinforcement learning agent (TD3) in the continuous state and action space setting where the agent has no knowledge of system dynamics. The selection of an appropriate reward function is a key factor that shapes the response of the dynamical system when the learning-based controller is implemented. The resulting controller is trained and tested for first-order and second-order linear systems, as well as a nonlinear system. The resulting trajectories of the closed-loop systems indicate that the transient and steady-state response can be altered by choosing the appropriate reward function while adhering to the constraints imposed on the control input.