There's a lot of debate around the economic suitability of drones for the delivery of the goods as a direct competitor to traditional trucks and delivery vans. There's an article written by Flexport which highlights two crucial factors that makes drones delivery of general goods not feasible, even in the near future: (1) route density and (2) drop size. Route density is the number of drop-offs you can make on a delivery route and drop-size is the number of parcels per stop on that delivery route. Given the strict airspace regulations on drone size and weight, it has become quite evident, particularly in the African context, that the delivery of general goods will not be an economically viable option even though the obvious need might say otherwise.  However, further analysis and demonstration have shown, from companies like Matternet and others, that the transport of the time-sensitive and high-value parcels (legal-documents, medicine samples, high-value spices...

We've reviewed a document on the impact of the blue-green algae on the irrigation of the agricultural farmlands.  Our investigations follows the trend of the bursts of blue-green algae is the dams using for livestock and plants which has caused many illnesses to the farm workers and their families specifically in small-holding agricultural areas. So we've decided to undergo experimental research into the application of a low-cost drone solution for the analysis, prediction and the eventual eradication of the blue-green algae in dams which has a direct impact in the production yield of the both animals and plants. This research will comprise of the development of the remote sensing system which will generate data that will be used as inputs into a predictive model which will be used to help farmers make alternative plans well-before the blue-green algae has a financial impact the farms' operations and the safety of its workers. The proposal with be prese...

We've reviewed a report by Deloitte discussing issues on how to leverage and protect Africa's innovation for future growth and economic stability. It was highlighted that the traditional focus on exploiting commodities hasn't yielded the redistribution of wealth or improve the standard of living for those working in that sector. Moreover, over 75% of economic activities happen in the informal sector (Nigeria statistics), which is exposed to the volatility that commodity markets are subjected to, which is detrimental to the impoverished communities. One of the major points which directly relates to our mission objective is the following quote from the report: " Yet, as much as innovation is important, there needs to be more focus on the final outcome of innovative solutions. "  In Africa, innovation is part of the daily survival. But it's usually unstructured, very often short-sighted and localized in it's application. Moreover, the growing yout...

As a student completing my final year, I vividly remember the insatiable desire to just complete the degree, graduate and kiss university life goodbye! Even though I actually enjoyed my course and the fact this had been my dream since my second year of high school, I felt I had enough. At that point, the thought of pursuing a postgraduate degree was the further thing from my mind. Such psychological damage was based on the opinions (albeit biased) that academics, the professors and full-time researchers that taught us, seemed detached from reality and their expectations from the feeble and vulnerable students, were beyond unreasonable. I vividly remember the insatiable desire to just complete my course, graduate and kiss university life goodbye! Even though I saw myself pursuing a postgraduate degree, the notion of having to face the same ordeal of my last few months as an undergraduate, was enough to convince me otherwise. I just didn't see myself having to deal with t...

The objective for this milestone was to integrate the same model functionality developed and analyzed within the Matlab/Simulink environment into a mature environment that will be able to test most functionalities of the Flight controller software that will be flashed for real-flight testing. The decision was to either migrate the Ardupilot (in this case ArduCopter ) software into the Matlab environment or integrate the highly nonlinear quadcopter model with flapping dynamics into the Ardupilot environment. The former option would mean no easy integration with Mission Planner and the real-time sofware-in-the-loop ( SITL ) testing tool (which also includes the infrastructure to communicate with the Flightgear 3D visualization environemt, while the later with make use of singular environment although the software development effort would quite tedious and error-prone. It was chosen to go with the first option as this was thought to be lead to more mature verification method prior...

Our H1 drone was finally ready to be tested with new detachable landing gear, 3-axis gimbal and the Gopro camera (powered by an extra 3S-lipo battery). The objective of the test was to test the flight modes (mainly altitude control and position control) via 3DR telemetry connection to an Android phone and the Tower app. It was quite noticeable that the quad needs alot more power to overcome in-ground effects at take-off. This is mainly due to the mass balance with the camera at the nose of the airframe. The altitude control mode worked quite well even at low elevation of 3-4 metres. Unfortunately, at low-battery voltage an automated landing doesn't occur and this resulted in hard-landing (more like a hard crash!). This piece of software will have to be investigated. The manual operation of the Gopro is a bit cumbersome. The alternative of using the WIFI link to operate the camera was investigated but was not deemed a good idea given the potential inteference...

So i took the challenge of setting up the Tarot gimbal not just for inherent stable video footage but also the flexibility of controlling it from the radio control. However, I encountered quite a few challenges which made me aware that I'm not the one only in this battle . It's quite clear that the setup of the Tarot gimbal using its own software is completely different from how it's been described in the Ardupilot/Arducopter webpage and in mission Planner. In Mission Planner and it's associated site makes one believe that it should be done through software, only to realize that in actual fact the setup is more complex than that.  After two evenings of trying various combinations, I realized the getting the pixhawk Aux channels to communicate with the T4 gimbal requires the following steps: - The Pixhawk Pin9 (Aux1) needed to be activated to pass through user-chosen channel from the transmitter. For the Dx6 Gen2 it was the channel 6, which can assigned the ...

We stumbled on the organization that's making head waves around the globe called Drones for Good Award . Although the coveted prize money is not openly advertised, various companies have participated over the past few years such as: PrecisionHawk , LoonCopter , Drones against Tsetse and many more. We were pretty impressed especially with LoonCopter. This is drone which is capable of air, surface and underwater navigation. The aim is mainly for search and rescue and the proof of concept was demonstrated at the award. But what's more fascinating is the culture and ethos this organization promotes. The idea that drones CAN be used for good and SHOULD be used for good. This is something we at Uav4africa believe immensely . The notion that you can use technology, whether in the air or under the sea, to uplift, educate and empower underprivileged communities is beyond a nice gesture, it's calling all of us should respond to. One of our projects is to investigate...

So the notion of upgrading my already awesome (if I can say so myself) looking drone to aerial videography using a 3-axis gimbal has been bugging me for a while now. I mean, why not? At least that will get me to fly the drone alot more and use it for other purposes. The fact that I only need a gimbal and a landing gear (given that I already have the awesome Gopro hero 4 silver), should be providential enough to just spend the dollars required to make this happen. But then one get's to think, why I am doing it for? I mean does my research of intelligent flight control ACTUALLY need aerial capability? One could argue that testing your software with a drone representative of an actual commercial drone could only enhance the validation/justification of the research.  But the ultimate question is, how MUCH distraction will this capability introduce to the essence of what the doctoral research is trying to achieve? Will I gain more information given that I've got now no...

So i've been looking over the last few months how I can get to fly more of my quadcopter drone for both research and leisure. The major drawback of the 1.6kg drone is its form factor at the time. Being a H-frame quad with cross rotor length of over 80cm, I had to purchase 110L storage bin to keep it safe and damage-free. After much research I ended up a natural solution that would involved just a steel saw and good eye for detail. The other (obvious) requirement for this folding mechanism is that it should make the deployment time as fast as possible with a few if not no special equipment. This led the the solution of cutout the area around the second bolt of each arm to allow pivoting action on the first bolt. The cutout should also be such that bolt hole remains to be used as a stopper to maintain symmetry along the quad x and y axis. The high contact friction will be used to ensure the arms remain in the required position throughout a particular flight. After much sawing and...

So the notion that in order for me to proceed scientifically (and practically) towards the design of rotor dynamics identification algorithms that will run in real-time, I first need to model the effects of the rotor failure through experimentation. The two best ways of the doing this are (1) Buy a +R2k Tachometer and record (probably by  recording the display) the speed of the propeller with a pre-determined PWM value. (2) Use the high speed capability of an action cam (such as GoPro) and some clever algorithms to compute the propeller RPM. The latter is the cheaper (and the geekier) option of the two. The setup was such that contrast was created through the use of a black mat cloth on the setup table and painting the opposing blade of the propeller black and white (see below). A RGB (red-green-blue) adaptive algorithm was developed which would mitigate the occurrence of glares on the blade which would in turn give a false reading with the algorithm. Each frame was analyze...

My research drone, given the lack of research funds, was a fourth-hand quadcopter drone which I resuscitated and started getting good flight test results. I even wrote a paper on it with the hope of publishing. However, the previous guys didn't have an appreciation for neatness so the drone looked like a wire fest. See below: So in order to make a clean start (without breaking the bank) was to remodel the airframe into something more commercial (with the hope that it could serve as a aerial photography platform - always wanted a DJI). So what I did was convert the space between the two main plates and layout the power electronics which included the ESCs, the distribution joint and the power module. I cleaned up the residues of double-sided tape that appeared everywhere and made provision for the Pixhawk in a more central position. And this is what it looks like now:   Mission accomplished. Now it's time for testing everything still works and for the first tes...

You can be in a situation where you have every right (and power) to condemn someone for their wrongdoing, but you pause. The person could even concede that he/she should have known better and is gracefully willing to take the punishment, whatever it might be, but you pause. Then in the mist of your rage, you introspect to realize, you could have been YOU on the other side of the table, except through varying (often complex) circumstances. Apathy is often what is being shun down upon in most leadership/christian books, yet in practice it's the very trait that is admired for someone who is decisive and 'getting the job done'. The assumption in believing that Old testament prophets were not apathetic towards the conquered nations is both naive and short-sighted. Not that I have any experience in this, but it's pretty difficult to cut someone's head off, if you're feeling sorry for him (unless you're really twisted upstairs). Back to my story... As some...

So one of the main objectives of my PhD research was to achieve the difficult task of developing a learning algorithm for machine learning ( RBF neural networks to be more specific) applications, that would enable the prediction of drone propeller damage in real-time AND without altering the bought-out flight controller ( DJI Naza , APM , Pixhawk , etc...). The only way it could achieve that was by analyzing the outputs of the flight controller sensors and learn when a fault would occur. Well, I believe I'm getting closer to this objective (submission is Nov 2019). I've decided to include the two figures below which illustrates the training process (0.2 sec on desktop) and prediction time (0.008 sec) and the accuracy to the true dynamics of the quadcopter drone. In this case the pitch dynamics are being predicted. Although noise hasn't been introduced, it's quite clear from the graphs, that the learning algorithm has enabled the RBF network to accurately capture th...

So I got the good news last Friday from the IFAC System identification conference, that my paper has been accepted for presentation. Although my professor has confirmed that he will not be able to attend the conference, I'm pretty determine not to miss this opportunity to present at an international event within the System Identification Community. This has given me so much motivation to redouble my efforts in pursuing the objectives set out for the completion of my research. And if enough funding is obtained, I will be able to go with my lovely wife... #crossingfingers Pretty exciting times ahead...

Over the course of the past 2-3 weeks I decided to take the plunge of learning a new training algorithm which had quite alot of attention in the academic community but was also well constructed for easier implementation. The work by Peng et al on developing the Continuous Forward Algorithm (CFA) was my subject of attention. The overall premise behind implementing this algorithm was to investigate less memory-intensive machine learning algorithm that will not sacrifice accuracy or robustness. The ability to have a real-time learning system for low-cost electronics (such as the Teensy 3.6 ) has huge implications for the commercialization and affordable access of intelligent drones specifically for developing and even under-developed economies. The far-reaching impact of having technology leveraging efforts of farmers, herders, game rangers, biologists is the next wave of industrialization. This is the essence of this blog. The journey is very exciting and eventual results even mo...