Journal
[1]ALFA: A dataset for UAV fault and anomaly detection, The International Journal of Robotics Research, vol. 40, no. 2-3. pp. pp. 515–520, 2021
@journal{keipour_mousaei_jrr21, author = {Keipour, Azarakhsh and Mousaei, Mohammadreza and Scherer, Sebastian}, title = {ALFA: A dataset for UAV fault and anomaly detection}, journal = {The International Journal of Robotics Research}, volume = {40}, number = {2-3}, pages = {515-520}, year = {2021}, tag = {journal}, doi = {10.1177/0278364920966642}, url = {https://doi.org/10.1177/0278364920966642}, eprint = {https://doi.org/10.1177/0278364920966642} }
We present a dataset of several fault types in control surfaces of a fixed-wing unmanned aerial vehicle (UAV) for use in fault detection and isolation (FDI) and anomaly detection (AD) research. Currently, the dataset includes processed data for 47 autonomous flights with 23 sudden full engine failure scenarios and 24 scenarios for 7 other types of sudden control surface (actuator) faults, with a total of 66 minutes of flight under normal conditions and 13 minutes of post-fault flight time. It additionally includes many hours of raw data of fully autonomous, autopilot-assisted and manual flights with tens of fault scenarios. The ground truth of the time and type of faults is provided in each scenario to enable evaluation of the methods using the dataset. We have also provided the helper tools in several programming languages to load and work with the data and to help the evaluation of a detection method using the dataset. A set of metrics is proposed to help to compare different methods using the dataset. Most of the current fault detection methods are evaluated in simulation and, as far as we know, this dataset is the only one providing the real flight data with faults in such capacity. We hope it will help advance the state of the art in AD or FDI research for autonomous aerial vehicles and mobile robots to enhance the safety of autonomous and remote flight operations further. The dataset and the provided tools can be accessed from https://doi.org/10.1184/R1/12707963.
Conference
[1]
VTOL Failure Detection and Recovery by Utilizing Redundancy.
By Mousaei, M., Keipour, A., Geng, J. and Scherer, S.
In arXiv preprint arXiv:2206.00588, 2022.
@article{mousaei_icra22vtol, title = {VTOL Failure Detection and Recovery by Utilizing Redundancy}, author = {Mousaei, Mohammadreza and Keipour, Azarakhsh and Geng, Junyi and Scherer, Sebastian}, journal = {arXiv preprint arXiv:2206.00588}, year = {2022}, tag = {conference}, url = {https://arxiv.org/abs/2206.00588} }
Offering vertical take-off and landing (VTOL) capabilities and the ability to travel great distances are crucial for Urban Air Mobility (UAM) vehicles. These capabilities make hybrid VTOLs the clear front-runners among UAM platforms. On the other hand, concerns regarding the safety and reliability of autonomous aircraft have grown in response to the recent growth in aerial vehicle usage. As a result, monitoring the aircraft status to report any failures and recovering to prevent the loss of control when a failure happens are becoming increasingly important. Hybrid VTOLs can withstand some de- gree of actuator failure due to their intrinsic redundancy. Their aerodynamic performance, design, modeling, and control have all been addressed in the previous studies. However, research on their potential fault tolerance is still a less investigated field. In this workshop, we will present a summary of our work on aircraft fault detection and the recovery of our hybrid VTOL. First, we will go over our real-time aircraft-independent system for detecting actuator failures and abnormal behaviors. Then, in the context of our custom tiltrotor VTOL aircraft design, we talk about our optimization-based control allocation system, which utilizes the vehicle’s configuration redundancy to recover from different actuation failures. Finally, we explore the ideas of how these parts can work together to provide a fail-safe system. We present our simulation and real-life experiments.
[2]
Design, Modeling and Control for a Tilt-rotor VTOL UAV in the Presence of Actuator Failure.
By Mousaei, M., Geng, J., Keipour, A., Bai, D. and Scherer, S.
In arXiv preprint arXiv:2205.05533, 2022.
@article{mousaei2022design, title = {Design, Modeling and Control for a Tilt-rotor VTOL UAV in the Presence of Actuator Failure}, author = {Mousaei, Mohammadreza and Geng, Junyi and Keipour, Azarakhsh and Bai, Dongwei and Scherer, Sebastian}, journal = {arXiv preprint arXiv:2205.05533}, year = {2022}, tag = {conference}, url = {https://arxiv.org/abs/2205.05533} }
Enabling vertical take-off and landing while pro- viding the ability to fly long ranges opens the door to a wide range of new real-world aircraft applications while improving many existing tasks. Tiltrotor vertical take-off and landing (VTOL) unmanned aerial vehicles (UAVs) are a better choice than fixed-wing and multirotor aircraft for such applications. Prior works on these aircraft have addressed the aerodynamic performance, design, modeling, and control. However, a less ex- plored area is the study of their potential fault tolerance due to their inherent redundancy, which allows them to tolerate some degree of actuation failure. This paper introduces tolerance to several types of actuator failures in a tiltrotor VTOL aircraft. We discuss the design and modeling of a custom tiltrotor VTOL UAV, which is a combination of a fixed-wing aircraft and a quadrotor with tilting rotors, where the four propellers can be rotated individually. Then, we analyze the feasible wrench space the vehicle can generate and design the dynamic control allocation so that the system can adapt to actuator failures, benefiting from the configuration redundancy. The proposed approach is lightweight and is implemented as an extension to an already-existing flight control stack. Extensive experiments validate that the system can maintain the controlled flight under different actuator failures. This work is the first study of the tiltrotor VTOL’s fault-tolerance that exploits the configuration redundancy to the best of our knowledge.
[3]
Detection and Physical Interaction with Deformable Linear Objects.
By Keipour, A., Mousaei, M., Bandari, M., Schaal, S. and Scherer, S.
In arXiv preprint arXiv:2205.08041, 2022.
@article{keipour_mousaei_icra22detection, title = {Detection and Physical Interaction with Deformable Linear Objects}, author = {Keipour, Azarakhsh and Mousaei, Mohammadreza and Bandari, Maryam and Schaal, Stefan and Scherer, Sebastian}, journal = {arXiv preprint arXiv:2205.08041}, year = {2022}, tag = {conference}, url = {https://arxiv.org/abs/2205.08041} }
Deformable linear objects (e.g., cables, ropes, and threads) commonly appear in our everyday lives. However, perception of these objects and the study of physical interaction with them is still a growing area. There have already been successful methods to model and track deformable linear objects. However, the number of methods that can automatically extract the initial conditions in non-trivial situations for these methods has been limited, and they have been introduced to the community only recently. On the other hand, while physical interaction with these objects has been done with ground manipulators, there have not been any studies on physical interaction and manipulation of the deformable linear object with aerial robots. This workshop describes our recent work on detecting deformable linear objects, which uses the segmentation output of the existing methods to provide the initialization required by the tracking methods automatically. It works with crossings and can fill the gaps and occlusions in the segmentation and output the model desirable for physical interaction and simulation. Then we present our work on using the method for tasks such as routing and manipulation with the ground and aerial robots. We discuss our feasibility analysis on extending the physical interaction with these objects to aerial manipulation applications.
[4]
Integration of Fully-Actuated Multirotors into Real-World Applications.
By Keipour, A., Mousaei, M., Ashley, A.T. and Scherer, S.
In arXiv preprint arXiv:2011.06666, 2020.
@article{keipour_mousaei_2020integration, title = {Integration of Fully-Actuated Multirotors into Real-World Applications}, author = {Keipour, Azarakhsh and Mousaei, Mohammadreza and Ashley, Andrew T and Scherer, Sebastian}, journal = {arXiv preprint arXiv:2011.06666}, tag = {conference}, url = {https://arxiv.org/abs/2011.06666}, year = {2020} }
The introduction of fully-actuated multirotors has opened the door to new possibilities and more efficient solutions to many real-world applications. However, their integration had been slower than expected, partly due to the need for new tools to take full advantage of these robots. As far as we know, all the groups currently working on the fully-actuated multirotors develop new full-pose (6-D) tools and methods to use their robots, which is inefficient, time- consuming, and requires many resources. We propose a way of bridging the gap between the tools already available for underactuated robots and the new fully- actuated vehicles. The approach can extend the existing under- actuated flight controllers to support the fully-actuated robots, or enhance the existing fully-actuated controllers to support existing underactuated flight stacks. We introduce attitude strategies that work with the underactuated controllers, tools, planners and remote control interfaces, all while allowing taking advantage of the full actuation. Moreover, new methods are proposed that can properly handle the limited lateral thrust suffered by many fully-actuated UAV designs. The strategies are lightweight, simple, and allow rapid integration of the available tools with these new vehicles for the fast development of new real-world applications.
[5]
Automatic Real-time Anomaly Detection for Autonomous Aerial Vehicles.
By Keipour, A., Mousaei, M. and Scherer, S.
In 2019 International Conference on Robotics and Automation (ICRA), pp. 5679–5685, 2019.
@inproceedings{keipour_mousaei_icra19, author = {Keipour, Azarakhsh and Mousaei, Mohammadreza and Scherer, Sebastian}, booktitle = {2019 International Conference on Robotics and Automation (ICRA)}, title = {Automatic Real-time Anomaly Detection for Autonomous Aerial Vehicles}, year = {2019}, volume = {}, number = {}, pages = {5679-5685}, tag = {conference}, doi = {10.1109/ICRA.2019.8794286}, url = {https://ieeexplore.ieee.org/abstract/document/8794286} }
The recent increase in the use of aerial vehicles raises concerns about the safety and reliability of autonomous operations. There is a growing need for methods to monitor the status of these aircraft and report any faults and anomalies to the safety pilot or to the autopilot to deal with the emergency situation. In this paper, we present a real-time approach using the Recursive Least Squares method to detect anomalies in the behavior of an aircraft. The method models the relationship between correlated input-output pairs online and uses the model to detect the anomalies. The result is an easy-to-deploy anomaly detection method that does not assume a specific aircraft model and can detect many types of faults and anomalies in a wide range of autonomous aircraft. The experiments on this method show a precision of 88.23%, recall of 88.23% and 86.36% accuracy for over 22 flight tests. The other contribution is providing a new fault detection open dataset for autonomous aircraft, which contains complete data and the ground truth for 22 fixed-wing flights with eight different types of mid-flight actuator failures to help future fault detection research for aircraft.
[6]
Automated Analysis, Reporting, and Archiving for Robotic Nondestructive Assay of Holdup Deposits.
By Jones, H., Maley, S., Yonekawa, K., Mousaei, M., Yesso, J.D., Kohanbash, D. and Whittaker, W.
In arXiv preprint arXiv:1901.10795, 2019.
@article{jones_mousaei_wm19, title = {Automated Analysis, Reporting, and Archiving for Robotic Nondestructive Assay of Holdup Deposits}, author = {Jones, Heather and Maley, Siri and Yonekawa, Kenji and Mousaei, Mohammadreza and Yesso, J David and Kohanbash, David and Whittaker, William}, journal = {arXiv preprint arXiv:1901.10795}, tag = {conference}, url = {https://arxiv.org/abs/1901.10795}, year = {2019} }
To decommission deactivated gaseous diffusion enrichment facilities, miles of contaminated pipe must be measured. The current method requires thousands of manual measurements, repeated manual data transcription, and months of manual analysis. The Pipe Crawling Activity Measurement System (PCAMS), developed by Carnegie Mellon University and in commissioning for use at the DOE Portsmouth Gaseous Diffusion Enrichment Facility, uses a robot to measure Uranium-235 from inside pipes and automatically log the data. Radiation measurements, as well as imagery, geometric modeling, and precise measurement positioning data are digitally transferred to the PCAMS server. On the server, data can be automatically processed in minutes and summarized for analyst review. Measurement reports are auto-generated with the push of a button. A database specially-configured to hold heterogeneous data such as spectra, images, and robot trajectories serves as archive. This paper outlines the features and design of the PCAMS Post-Processing Software, currently in commissioning for use at the Portsmouth Gaseous Diffusion Enrichment Facility. The analysis process, the analyst interface to the system, and the content of auto-generated reports are each described. Example pipe-interior geometric surface models, illustration of how key report features apply in operational runs, and user feedback are discussed.
[7]
A robot for nondestructive assay of holdup deposits in gaseous diffusion piping.
By Jones, H., Maley, S., Mousaei, M., Kohanbash, D., Whittaker, W., Teza, J., Zhang, A., Jog, N. and Whittaker, W.
In arXiv preprint arXiv:1901.10341, 2019.
@article{jones_mousaei_wm19robot, title = {A robot for nondestructive assay of holdup deposits in gaseous diffusion piping}, author = {Jones, Heather and Maley, Siri and Mousaei, Mohammadreza and Kohanbash, David and Whittaker, Warren and Teza, James and Zhang, Andrew and Jog, Nikhil and Whittaker, William}, journal = {arXiv preprint arXiv:1901.10341}, tag = {conference}, url = {https://arxiv.org/abs/1901.10341}, year = {2019} }
Miles of contaminated pipe must be measured, foot by foot, as part of the decommissioning effort at deactivated gaseous diffusion enrichment facilities. The current method requires cutting away asbestos-lined thermal enclosures and performing repeated, elevated operations to manually measure pipe from the outside. The RadPiper robot, part of the Pipe Crawling Activity Measurement System (PCAMS) developed by Carnegie Mellon University and commissioned for use at the DOE Portsmouth Gaseous Diffusion Enrichment Facility, automatically measures U-235 in pipes from the inside. This improves certainty, increases safety, and greatly reduces measurement time. The heart of the RadPiper robot is a sodium iodide scintillation detector in an innovative disc-collimated assembly. By measuring from inside pipes, the robot significantly increases its count rate relative to external through-pipe measurements. The robot also provides imagery, models interior pipe geometry, and precisely measures distance in order to localize radiation measurements. Data collected by this system provides insight into pipe interiors that is simply not possible from exterior measurements, all while keeping operators safer. This paper describes the technical details of the PCAMS RadPiper robot. Key features for this robot include precision distance measurement, in-pipe obstacle detection, ability to transform for two pipe sizes, and robustness in autonomous operation. Test results demonstrating the robot’s functionality are presented, including deployment tolerance tests, safeguarding tests, and localization tests. Integrated robot tests are also shown.
[8]
Optimizing pilot overhead for ultra-reliable short-packet transmission.
By Mousaei, M. and Smida, B.
In 2017 IEEE International Conference on Communications (ICC), pp. 1–5, 2017.
@inproceedings{mousaei_icc17, author = {Mousaei, Mohammadreza and Smida, Besma}, booktitle = {2017 IEEE International Conference on Communications (ICC)}, title = {Optimizing pilot overhead for ultra-reliable short-packet transmission}, year = {2017}, volume = {}, number = {}, pages = {1-5}, tag = {conference}, doi = {10.1109/ICC.2017.7996416}, url = {https://ieeexplore.ieee.org/abstract/document/7996416} }
In this paper we optimize the pilot overhead for ultra-reliable short-packet transmission and investigate the de- pendence of this overhead on packet size and error probability. In particular, we consider a point-to-point communication in which one sensor sends messages to a central node, or base-station, over AWGN with Rayleigh fading channel. We formalize the optimization in terms of approximate achievable rates at a given block length, pilot length, and error probability. This leads to more accurate pilot overhead optimization. Simulation results show that it is important to take into account the packet size and the error probability when optimizing the pilot overhead.
[9]
ComSens: Exploiting pilot diversity for pervasive integration of communication and sensing in MIMO-TDD-Frameworks.
By Mousaei, M., Soltanalian, M. and Smida, B.
In MILCOM 2017 - 2017 IEEE Military Communications Conference (MILCOM), pp. 617–622, 2017.
@inproceedings{mousaei_milcom17, author = {Mousaei, Mohammadreza and Soltanalian, Mojtaba and Smida, Besma}, booktitle = {MILCOM 2017 - 2017 IEEE Military Communications Conference (MILCOM)}, title = {ComSens: Exploiting pilot diversity for pervasive integration of communication and sensing in MIMO-TDD-Frameworks}, year = {2017}, volume = {}, tag = {conference}, number = {}, pages = {617-622}, doi = {10.1109/MILCOM.2017.8170851}, url = {https://ieeexplore.ieee.org/abstract/document/8170851} }
In this paper, we propose a fully-integrated radar and communication system - named ComSens. We utilize two different pilot sequences (one for uplink and one for downlink) with the condition that they must be uncorrelated to each other. Within such a framework, the signal received from end-user and the back-scattered signal from the desired objects have uncorrelated pilots. Thus, the base-station is able to distinguish data signal from user and back-scattered signal from object. We assume a time division duplex (TDD) framework. The pilot sequences are designed for MIMO channels. We evaluate channel MSE as a figure of merit for communication system. We also show that the designed pilots are uncorrelated for a range of time lags. Moreover, designed uplink pilot has negligable autocorrelation for a range of time lags leading to an impulse-like autocorrelation for radar sensing.
MS Thesis
[1]
Efficient Use of Spectral Resources in Wireless Communication Using Training Data Optimization.
By Mousaei, M.
In arXiv preprint arXiv:1903.12259, 2019.
@article{mousaei2019msthesis, title = {Efficient Use of Spectral Resources in Wireless Communication Using Training Data Optimization}, author = {Mousaei, Mohammadreza}, journal = {arXiv preprint arXiv:1903.12259}, year = {2019}, tag = {msthesis}, url = {https://arxiv.org/abs/1903.12259} }
Wireless communication applications has acquired a vastly increasing range over the past decade. This rapidly increasing demand implies limitations on utilizing wireless resources. One of the most important resources in wireless communication is frequency spectrum. This thesis provides different solutions towards increasing the spectral efficiency. The first solution provided in this thesis is to use a more accurate optimization metric: maximal acheivable rate (compared to traditional metric: ergodic capacity) to optimize training data size in wireless communication. Training data symbols are previously known symbols to the receiver inserted in data packets which are used by receiver to acquire channel state information (CSI). Optimizing training data size with respect to our proposed tight optimization metric, we could achieve higher rates especially for short packet and ultra reliable applications. Our second proposed solution to increase spectral efficiency is to design a multifunction communication and sensing platform utilizing a special training sequence design. We proposed a platform where two training sequences are designed, one for the base-station and the other for the user. By designing these two training sequence such that they are uncorrelated to each other, the base station will be able to distinguish between the two training sequence. Having one of the sequences especially designed for radar purposes (by designing it such that it has an impulse-like autocorrelation), the system will be able to sense the environment, transmit and receive the communication data simultaneously.