Technology Stocks : Drones, Autonomous Vehicles and Flying Cars

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
From: Glenn Petersen9/19/2017 6:47:13 AM
1 Recommendation

Recommended By

   of 1841
Swarm intelligence (SI) is the collective behavior of decentralized, self-organized systems, natural or artificial. The concept is employed in work on artificial intelligence. The expression was introduced by Gerardo Beni and Jing Wang in 1989, in the context of cellular robotic systems. [1]

SI systems consist typically of a population of simple agents or boids interacting locally with one another and with their environment. The inspiration often comes from nature, especially biological systems. The agents follow very simple rules, and although there is no centralized control structure dictating how individual agents should behave, local, and to a certain degree random, interactions between such agents lead to the emergence of "intelligent" global behavior, unknown to the individual agents. Examples in natural systems of SI include ant colonies, bird flocking, animal herding, bacterial growth, fish schooling and microbial intelligence.

The application of swarm principles to robots is called swarm robotics, while 'swarm intelligence' refers to the more general set of algorithms. 'Swarm prediction' has been used in the context of forecasting problems.

Swarm intelligence key to successful operation of drones, says study

Sam Clark
The Stack
Tue 22 Aug 2017 5.27pm

Using swarm intelligence may be a way to combat many of the challenges faced by drone operators, both in business and by governments, according to a group of academics.

Researchers from British and French universities have written a paper noting how drones can now add value to these organisations due to low cost and mobilisation time – for example, checking the structural integrity of a building in a much cheaper way than with helicopters or high-rise cranes. They are also cheaper and quicker than helicopters for use by police services.

However, the study argues that drones rarely work effectively as individual units in these scenarios – they are best operated as part of a ‘fleet’, often with humans involved in a centralised control environment. This means ‘fleet participants’ need to cooperate with other drones in the same fleet. Similarly, if there are members of other fleets in the same airspace, they need to be able to communicate in order to operate safely.

The paper proposes different ways of managing drones. All decisions could be taken by a control centre – requiring real-time communication between drones in the air and the control centre on the ground. But there may be a number of situations where drones may need to behave autonomously, requiring a level of AI that a single drone is unlikely to have the computing capacity for.

Therefore, the authors suggest that ‘AI algorithms designed for the Swarm Intelligence paradigm can be applied.’ There are many challenges for a swarm of drones, and the paper finds what it calls mission-critical operations – which are time-sensitive and vital to the successful operation of the fleet.

When approaching these challenges, the authors note that it would be possible to create a set of pre-defined rules based on expected conditions and outcomes before the drones set off, but this does not account for the fact that drones are likely to encounter unexpected situations while in the air.

Instead, they propose using swarm intelligence so the drones can learn and adapt on the basis of the situation in which they find themselves.

Given that assessing the best way for a fleet of drones to operate presents considerable challenges, the paper assesses why a number of drones are preferable to a single drone in many business and emergency applications.

Firstly, there is better resiliency against failure – that is, if something fails on one drone, such as a temperature sensor, it would still be possible to get the same data from other drones.

Groups of drones can cover larger geographic locations, and carry out various, specialised tasks concurrently. They also form a network – meaning if drone B is too far away from the control centre to communicate with, but is close enough to drone A, it can effectively pass a message down the line.

On the advice of this study, organisations employing UAVs may be best utilising ‘self-aware, mission-focussed and independent fleets of drones.’
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  

Copyright © 1995-2018 Knight Sac Media. All rights reserved.Stock quotes are delayed at least 15 minutes - See Terms of Use.