Multi-UAV target search using decentralized gradient-based negotiation with expected observation

Lanillos, Pablo; Gan, Seng Keat; Besada-Portas, Eva; Pajares, Gonzalo; Sukkarieh, Salah

doi:10.1016/j.ins.2014.05.054

Cited by 94 publications

(60 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Overall, the articles surveyed in Sections 4–6 propose various solution approaches to optimize operations of drones. In addition to presenting centralized optimization methods, some articles design agent‐based, or decentralized, algorithms . Such algorithms are scalable to new drones entering the system, are robust, since drones may not be connected to the control station at all times, and naturally enable parallelized computation with each drone optimizing its own local subproblem.…”

Section: Planning Drone Operationsmentioning

confidence: 99%

“…In the case of a moving object, the probability map evolves over time . Due to imperfect sensors, a drone detects an object with some probability

π < 1

Section: Planning Drone Operationsmentioning

confidence: 99%

“…Due to imperfect sensors, a drone detects an object with some probability

π < 1

if it visits the cell where the object is located , so it may make sense to visit some cells several times. The probability of detecting the object may be higher in the center of the sensor's footprint and decline at the footprint's edge . Given the information collected by a drone and the initial base rate, we can perform a Bayesian update of the cell label .…”

Section: Planning Drone Operationsmentioning

confidence: 99%

See 2 more Smart Citations

Optimization approaches for civil applications of unmanned aerial vehicles (UAVs) or aerial drones: A survey

et al. 2018

View full text Add to dashboard Cite

Unmanned aerial vehicles (UAVs), or aerial drones, are an emerging technology with significant market potential. UAVs may lead to substantial cost savings in, for instance, monitoring of difficult‐to‐access infrastructure, spraying fields and performing surveillance in precision agriculture, as well as in deliveries of packages. In some applications, like disaster management, transport of medical supplies, or environmental monitoring, aerial drones may even help save lives. In this article, we provide a literature survey on optimization approaches to civil applications of UAVs. Our goal is to provide a fast point of entry into the topic for interested researchers and operations planning specialists. We describe the most promising aerial drone applications and outline characteristics of aerial drones relevant to operations planning. In this review of more than 200 articles, we provide insights into widespread and emerging modeling approaches. We conclude by suggesting promising directions for future research.

show abstract

Section: Planning Drone Operationsmentioning

confidence: 99%

“…In the case of a moving object, the probability map evolves over time . Due to imperfect sensors, a drone detects an object with some probability

π < 1

Section: Planning Drone Operationsmentioning

confidence: 99%

“…Due to imperfect sensors, a drone detects an object with some probability

π < 1

Section: Planning Drone Operationsmentioning

confidence: 99%

See 1 more Smart Citation

Optimization approaches for civil applications of unmanned aerial vehicles (UAVs) or aerial drones: A survey

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Such approaches have utilized the concept of distributed support for a proposition. Newer work by Lanillos et al [13] has moved beyond strictly hand designed fusion architectures for the DDF problem but must share larger amount of data between agents to perform fusion.…”

Section: Prior Workmentioning

confidence: 99%

Financialized methods for market-based multi-sensor fusion

Abernethy

Johnson-Roberson

2015

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Autonomous systems rely on an increasing number of input sensors of various modalities, and the problem of sensor fusion has received attention for many years. Autonomous system architectures are becoming more complex with time, and the number and placement of sensors will be modified regularly, sensors will fail for many reasons, information will arrive asynchronously, and the system will need to adjust to rapidly changing environments. To address these issues we propose a new paradigm for fusing information from multiple sources that draws from the rich of field pertaining to financial markets, particularly recent research on prediction market design. Among the many benefits of this financialized approach is that, both in theory and in practice, markets are wellequipped to robustly synthesize information from diverse sources in a decentralized fashion. Our framework poses sensor processing algorithms as profit-seeking market participants, data is incorporated via financial transactions, and the joint estimation is represented as a price equilibrium. We use pedestrian detection as a motivating application. Pedestrian detection is a well studied field and essential to autonomous driving. Real world fusion results are presented on RGB and LIDAR data from the KITTI Vision Benchmark Suite. We demonstrate we can achieve comparable performance to state-of-the-art hand designed fusion techniques using the proposed approach.

show abstract

“…This characteristic of the swarm is what makes each individual autonomous in nature. This decentralized nature of a swarm offers improved scalability, modularity, and redundancy to the system [5]. After properly laying down the foundations of what constitutes a swarm, a formal definition can be stated as: "A swarm is a completely decentralized and autonomous mechanism that comprises of autonomous agents as its individuals" [4].…”

Section: Introductionmentioning

confidence: 99%

Optimization of decentralized information dissemination in quadrotor swarm using genetic algorithm

Maningo

Faelden

Nakano

et al. 2014

2014 International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and M

View full text Add to dashboard Cite

There is a glaring problem in communication systems when it comes to a decentralized robotic swarm. Since a decentralized swarm would limit the awareness of each agent to its immediate surroundings/neighbors, the exchange of information between agents may now prove to be challenging. An epidemic-based broadcasting technique is then presented to resolve the problem of end-to-end agent communication. This paper aims to optimize the information diffusion by means of implementing genetic algorithm to optimize the time it will take for each quadrotor individual to acquire the information coming from a single source (i.e. the quadrotor who first received the information from an external stimulus). The method by which this is done is epidemic in nature. Due to this, for each time there would be a signal broadcasting, the genetic algorithm would be run to determine the next ideal location of each individual. A genetic algorithm was looped several times to achieve the desired solution. The results showed that for each run of the GA, the number of quadrotors having received the information continually increased until the output converges to a fitness level. However this only worked under certain constraints that need to be weighed out properly. This includes the readjustment of the fitness and crossover functions. Also, the parameters of the GA must be well calibrated for proper output response. IndexTerms-quadrotor swarm, decentralized communication, optimization, genetic algorithm.

show abstract

Multi-UAV target search using decentralized gradient-based negotiation with expected observation

Cited by 94 publications

References 31 publications

Optimization approaches for civil applications of unmanned aerial vehicles (UAVs) or aerial drones: A survey

Optimization approaches for civil applications of unmanned aerial vehicles (UAVs) or aerial drones: A survey

Financialized methods for market-based multi-sensor fusion

Optimization of decentralized information dissemination in quadrotor swarm using genetic algorithm

Contact Info

Product

Resources

About