Update: this has now morphed into https://www.theplastictide.com/
A project I have been thinking about and wanting to do for a very long time is to build a fully autonomous litter collecting robot. This driven by the annoyance I always feel when passing a nearby park, littered with Twix wrappers, coke cans, and the like. Challenging? Very much so. Impossible? No. You just have to pick your constraints.
I wish this was the blog post I would explain how I built the robot and how it all works, including snazzy youtube video. However, while I have already started down the path I still have a long (but fun!) way to go. In particular my Orangutans have been keeping me busy and will continue to do so for a while. I have also changed my professional affiliation but that’s a topic for the next post. It does explain though why my interest was piqued when Peter Kohler (GIS expert from SESexplore, and Fishackathon fame) told me about his project to raise awareness around marine litter. And that is the real topic of this post.
In my last post I discussed my little flying object detector project that I’ve been doing for fun. While it worked it relied on communication with an external laptop in order to work (the on board odroid was not powerful enough to run the convnet model).
Hence, what better excuse to buy an NVIDIA Jetson TK1 dev board which should have more than enough juice to run everything on board the drone itself. As added benefit it should come in useful for my litter robot. I then added websocket support to the flask web app and you can now see the detections appear in real time on a map.
It took some fiddling to get the wifi to work with the Jetson and Im still surprised at how quickly the wifi degrades (even though Im using the 5GHz band to avoid collisions with the Tx/Rx). But it did work in the end:
It wasn’t the best place to test it out but I was short on time and it should be good enough to illustrate the concept
Still lots to do and too little time, but we keep chipping away. In particular the awesome folk from ErleBotics were kind enough to send me a Brain2, looking forward to try that out as well.
PS: on a related note, love what the guys from vertical.ai are working on
About a year and a half ago I saw Jetpac’s video of their Spotter app and I remember thinking at the time that it would be so cool to get this flying on a drone. I didn’t have the bandwidth to work on it at the time but ended up poking at it with Markus Aschinger at the ASI and with two A level students (Jawad / Isaac) from the Nuffield Foundation. While they did good work and it got me a step closer, it still hadn’t quite come together. Hence I sat down the past week to do a full rewrite, integrate it with a quad I had lying around and do a little demo. The result can be seen in the video below.
One of the projects that has taken up a lot of my time the past few months is that of a UAV (drone) based Ground Penetrating Radar (GPR) system. There are a number of applications for this but the one we have been focussing on initially is landmine and UXO clearance. The elements that make up such a system are quite broad. Ranging from sensor design, UAV integration, positioning, terrain following to data analysis. As with many drone projects most of the attention tends to go to the hardware and the flying. While that is certainly important and I have been working on those elements too, the whole system is only as good as the quality and interpretability of the data you get back. That is key. With this post I’ll aim to give a brief summary of the work I have been leading on this front.
There has been a lot going on recently and I thought I would give an update of the main projects I have been working on. I will aim to post more detailed updates and results as things progress and confidentiality agreements allow.
Its late and I’m on my way back from the final demo evening of the Advanced Skills Initiative (ASI). The ASI programme takes disgruntled academics and puts them through an intensive 8 week data science course so they can move into the bustling data science job market. I was a mentor on the machine learning front and it was great to see the fellows evolve and battle through their projects.
One thing struck me though. Something that has been bugging me for a while. Projects pitched at events and meetups like this invariably cover product recommendation, preference learning, financial NLP, churn prediction, adclick prediction, social media trending analysis, etc.
As somebody who likes tangible things, I can’t help but wonder. Where are the projects & startups from aerospace, automotive, marine and other engineering disciplines? Why aren’t we seeing projects from Airbus on smart IVHM, from Jaguar on crumple zones, from Reaction Engines on engine performance, from ASV on marine autopilots, from Princess on vibration control, from McLaren on race strategy, from Dyson on path planning, etc. I personally find these things hugely interesting and fascinating topics. The possibilities for data science / machine learning are endless, prognostics being the obvious example.
Update: These courses have now been taught successfully. If you are interested let me know.
Note: These were originally delivered through Persontyle, however I am no longer affiliated with them in any way after a very unprofessional experience.
I am happy to announce I will be teaching two Machine Learning courses over the summer: A one day high level overview of machine learning is all about and a longer 5 day introductory course that goes into more depth and includes lots of hands on labs with Python scikit-learn. See below for details.
One of the projects I have been involved with recently was a collaboration with the Agents, Interaction, and Complexity group at University of Southampton. The same group who we are also involved with in the Orchid project. This particular project was on Measuring and Predicting Departures from Routine in Human Mobility, building on the PhD work by James McInerney (now at Princeton) and his paper Breaking the Habit.
It is well known that humans generally follow very regular and predicable mobility patterns, both spatially and temporally. Lots of work has looked at exploiting and predicting those patterns but much less so on looking specifically at departures from those regular patterns. What can we learn from those departures from routine? How predictable are they?
Update: Unfortunately I purposely withdrew from the DL meetup after a very unprofessional experience with the co-organisers Persontyle. I Instead I joined forces with the London Machine Learning Meetup.
It has been almost half a year since I announced I would take over the London Big-O Algorithms meetup and bring it back to life. 5 Months later I am very happy to say all has gone extremely well, interest and attendance far exceeding my expectations. We have had a great set of meetups so far and all speaker slots are booked until June with talks from Google, The founder of ZeroMQ, Microsoft Bing, and many others. Really nice to see there is strong interest in good, solid, technical content.
However, enough about Big-O. This post is to announce a new meetup group that I have been convinced into setting up. The Deep Learning London meetup. The aim of this group is to bring together people interested in the family of machine learning methods that are concerned with learning distributed, hierarchical (“deep”) representations. Neural Networks being the most popular implementation. Its an area I have been looking at for a while and will be getting into quite deeply over the next couple of months (no pun intended). The format will be based around guest speakers sharing new research ideas and applications covering a wide range of fields from computer vision and natural language processing to autonomous systems and prognostics.
Note we are not assuming deep learning is the be-all end-all silver bullet of machine learning and welcome critical thoughts and benchmarks.
Sound interesting? Get in touch!