An official website of the United States government
ABSTRACT Unmanned aerial vehicles (UAVs) are revolutionizing a wide range of military and civilian applications. Since mission failures caused by malfunctions of UAVs can incur significant economic losses, modeling and ensuring the reliability of UAV‐based mission systems is a crucial area of research with challenges posed by multiple dependent phases of operations and collaborations among heterogeneous UAVs. The existing reliability models are mostly applicable to single‐UAV or homogeneous multi‐UAV systems. This paper advances the state of the art by proposing a new analytical modeling method to assess the reliability of a multi‐phased mission performed by heterogeneous collaborative UAVs. The proposed method systematically integrates an integral‐based Markov approach with a binary decision diagram‐based combinatorial method, addressing inter‐ and intraphase collaborations as well as phase‐dependent configurations of heterogeneous UAVs for accomplishing different tasks. As demonstrated by a detailed analysis of a two‐phase rescue mission performed by six UAVs, the proposed method has no limitations on UAV's time‐to‐failure and time‐to‐detection distributions. Another contribution is to formulate and solve UAV allocation problems, achieving a balance between mission success probability and total cost. Given the uncertainties inherent in the mission scenario, the random phase duration problem is also examined.
more »
« less
A Path Planning Algorithm for Collective Monitoring Using Autonomous Drones
This paper presents a novel mission-oriented path planning algorithm for a team of Unmanned Aerial Vehicles (UAVs). In the proposed algorithm, each UAV takes autonomous decisions to find its flight path towards a designated mission area while avoiding collisions to stationary and mobile obstacles. The main distinction with similar algorithms is that the target destination for each UAV is not apriori fixed and the UAVs locate themselves such that they collectively cover a potentially time-varying mission area. One potential application for this algorithm is deploying a team of autonomous drones to collectively cover an evolving forest wildfire and provide virtual reality for firefighters. We formulated the algorithm based on Reinforcement Learning (RL) with a new method to accommodate continuous state space for adjacent locations. To consider a more realistic scenario, we assess the impact of localization errors on the performance of the proposed algorithm. Simulation results show that the success probability for this algorithm is about 80% when the observation error variance is as high as 100 (SNR:-6dB).
more »
« less
- Award ID(s):
- 1755984
- PAR ID:
- 10133281
- Date Published:
- Journal Name:
- 53rd Annual Conference on Information Sciences and Systems (CISS)
- Page Range / eLocation ID:
- 1 to 6
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Unmanned aerial vehicles (UAVs) have various applications in different settings, including e.g., surveillance, packet delivery, emergency response, data collection in the Internet of Things (IoT), and connectivity in cellular networks. However, this technology comes with many risks and challenges such as vulnerabilities to malicious cyber-physical attacks. This paper studies the problem of path planning for UAVs under GPS sensor permanent faults in a cyber-physical system (CPS) perspective. Based on studying and analyzing the CPS architecture of the UAV, the cyber “attacks and threats” are differentiated from attacks on sensors and communication components. An efficient way to address this problem is to introduce a novel approach for UAV’s path planning resilience to GPS permanent faults artificial potential field algorithm (RCA-APF). The proposed algorithm completes the three stages in a coordinated manner. In the first stage, the permanent faults on the GPS sensor of the UAV are detected, and the UAV starts to divert from its initial path planning. In the second stage, we estimated the location of the UAV under GPS permanent fault using Received Signal Strength (RSS) trilateration localization approach. In the final stage of the algorithm, we implemented the path planning of the UAV using an open-source UAV simulator. Experimental and simulation results demonstrate the performance of the algorithm and its effectiveness, resulting in efficient path planning for the UAV.more » « less
-
null (Ed.)The main objective of an unmanned aerial vehicle (UAV) path planning is to generate a flight path that links a start point to an endpoint in an indoor space avoiding obstacles. Path planning is essential for many real-life applications such as an autonomous car, surveillance mission, farming robots, unmanned aerial vehicles package delivery, space exploration, and many others. To create an optimal path, we need to adopt a specific criterion to minimize the distance the UAV must travel such as the Euclidean distance. In this paper, we provide our initial idea of creating an optimal path for indoor UAV using both A* and the Late Acceptance Hill Climbing (LAHC) algorithms. We are adopting an indoor search environment with various complexity and utilize the Probabilistic Roadmap algorithm (PRM) as a search space for both algorithms. The basic idea following PRM is to generate random sample points in the space and search these points for an optimal path. The developed results show that the LAHC algorithm outperforms the A* algorithm.more » « less
-
Autonomous systems, such as Unmanned Aerial Vehicles (UAVs), are expected to run complex reinforcement learning (RL) models to execute fully autonomous positionnavigation-time tasks within stringent onboard weight and power constraints. We observe that reducing onboard operating voltage can benefit the energy efficiency of both the computation and flight mission, however, it can also result in on-chip bit failures that are detrimental to mission safety and performance. To this end, we propose BERRY, a robust learning framework to improve bit error robustness and energy efficiency for RL-enabled autonomous systems. BERRY supports robust learning, both offline and on-board the UAV, and for the first time, demonstrates the practicality of robust low-voltage operation on UAVs that leads to high energy savings in both compute-level operation and systemlevel quality-of-flight. We perform extensive experiments on 72 autonomous navigation scenarios and demonstrate that BERRY generalizes well across environments, UAVs, autonomy policies, operating voltages and fault patterns, and consistently improves robustness, efficiency and mission performance, achieving up to 15.62% reduction in flight energy, 18.51% increase in the number of successful missions, and 3.43× processing energy reduction.more » « less
-
Localization of radio-tagged wildlife is essential in environmental research and conservation. Recent advancements in Uncrewed Aerial Vehicles (UAVs) have expanded the potential for improving this process. However, a key challenge lies in the optimal choice of waypoints for UAVs to localize animals with high precision. This study addresses the intelligent selection of waypoints for UAVs assigned to localize multiple stationary Very High Frequency (VHF)-tagged wildlife simultaneously, with a primary emphasis on minimizing localization uncertainty in the shortest possible time. At each designated waypoint, the UAV obtains bearing measurements to tagged animals, considering the associated uncertainty. The algorithm then intelligently recommends subsequent locations that minimize predicted localization uncertainty while accounting for constraints related to mission time, keeping the UAV within signal range, and maintaining a suitable distance from targets to avoid disturbing the wildlife. The evaluation of the algorithm’s performance includes comprehensive assessments, featuring the analysis of uncertainty reduction throughout the mission, comparison of estimated animal locations with ground truth data, and analysis of mission time using Monte Carlo simulations.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/CISS.2019.8693023
