A drone that monitors its own health during long package-delivery missions: stakes, realities, actors and challenges.

The most exciting when it comes to algorithm, it is the unmatched abilities of this genial and simplest approach to predict, tackle, and solve scary issues and problems. It is also exciting to observe how in our real-live this sequential methodology improves our living conditions, our health, our business and helps us appropriate the good practices in our day-to-day existence. 

Those (researchers, scientists, students, engineers, decision-makers, and entrepreneurs) who use Connectikpeople.co, soon #Retinknow®, know that, we are there to share and to delight this tremendous wealth. 

Knowledge is power, and we are henceforth living in the new IT Convergence world where the intelligence is the Ins and Outs.

That said; now, let’s dive in the near future, where the package that you ordered online may be deposited at your entrance way by a drone in real-time.

Connectikpeople.co, soon #Retinknow®, talks about drone-based delivery; and we can remember that, last December 2013, online retailer Amazon suggested that fleets of flying robots might serve as autonomous messengers that carry packages to customers within 30 minutes of an order.

All this, is exciting, but until now a set of uncertainties related to factors such as high winds, sensor measurement errors, drops in fuel, and more remain weighty.

In fact the stake is how to ensure relevant, safe, timely, and accurate delivery. The smile comes from MIT researchers. They have come up with a two-pronged approach (vehicle-level planning, and mission-level), that can significantly reduces the computation associated with lengthy delivery missions. 

Connectikpeople.co, soon #Retinknow®, can observe that, the team first developed an algorithm that enables a drone to monitor aspects of its “health” in real time.

 Connectikpeople.co, soon #Retinknow®, recalls that, with this algorithm, a drone can predict its fuel level and the condition of its propellers, cameras, and other sensors throughout a mission, and take proactive measures: rerouting to a charging station, if needed.

The method devised for a drone can proficiently compute its possible future locations offline, before it takes off. 

It is also encouraging to observe that, the method can simplify all potential routes a drone may take to reach a destination without colliding with obstacles.

The researchers found that their drones delivered as many packages as those that lacked health-monitoring algorithms, but with far fewer failures or breakdowns.

Agha-mohammadi will present details of the group’s approach in September 2014 at the IEEE/RSJ International Conference on Intelligent Robots and Systems, in Chicago. His co-authors are MIT graduate student Kemal Ure; Jonathan How, the Richard Cockburn Maclaurin Professor of Aeronautics and Astronautics; and John Vian of Boeing.