Robots and Physical Computing

I suspect someone from Anki was watching Wall-E (not the first to notice that see verge article http://www.theverge.com/2016/6/27/12007772/anki-cozmo-robot-ai-toy-wall-e-pixar ) when they designed Cozmo it sounds, looks a bit like and has cuteness of Wall-E; but resembles the little cleaning robot M-O (which it is hard not to like); all crossed with a cute bulldozer. That is two ‘cutes’ in one sentence – this is a robot has this in abundance. From saying your name, to excitedly tapping the blocks, to victory dances when it wins a game. This is a smart little robot full of a lot of features that are revealed over the days you play with it. The video from the manufacturer, Anki, above gives some idea of the technical aspects of it. Anki have already produced an open-source SDK https://developer.anki.com/en-gb that is Python-based. Powering up Cozmo for the first time and connecting to the App is relatively easy and quickly you are into playing with it (I am tr...

Robot insect for the home, Antbo, started as a crowdfunded project (see the video below) ( https://www.indiegogo.com/projects/antbo-an-insect-robot-anyone-can-build-steam-diy#/ ) from the DFRobot Robotics.  This is post is not really a fully review, just some initial thoughts, as I haven't spent enough time playing with it; but what I have seen so far does interest me. The price during the crowdsource was around the $59-$69 which because of the range of sensors and features does seem reasonable. The screenshot below is taken from the funding website discussing some of the features. An intriguing point in the literature is the self-learning - using 30 neuron neural network – I would love to have more details of this one. At the moment I have been controlling it through the iPad app which gives a variety of modes - directly driving; setting it on patrol (first picture below); drawing a path on screen for it to follow (third picture below) and even voic...

I will start with a confession, I only had about 2 1/2 hours at BETT 2017  due to external time pressures so to say I didn't yet a chance for a good (or even a bad) look around is an understatement; so I am not reviewing the show just a few notes on what I did manage to see. STEAM Village First and mostly, it was great to talk to so many people, only few I had met face to face previously, about robots, micro:bits, Raspberry Pis and coding. Most of this happen in the relatively small (compared to the event space) STEAM village and nearby stalls. It was great to see the strong presence of both Raspberry Pi and Micro:Bit Foundation, along the variety of different activities and example usage of both, with Code Club (I know it is part of Raspberry Pi Foundation) there was well. This was all alongside some other companies Four of these stuck in my mind. 1. DFRobot ( https://www.dfrobot.com/ ) with their range of Arduino-based robots and non-programmable kits....

In the last post experimentation with an artificial neuron controlling the Bit:Bot to follow the edge of a line (it follows the left-hand side of the line). More details can be found in the previous post. The neurons (well two separate ones, S1 and S2) are produced using  weighted sums - summing the  weights x inputs [ right-hand sensor (rs) and left-hand sensor (ls)] plus a bias for each neuron in this case w[0] and w[3].     net=w[0]+w[1]*rs+w[2]*ls           net2=w[3]+w[4]*rs+w[5]*ls If weighted sum >=0 then its output 1 otherwise 0 What actual causes S1 to be either 1 or 0 is all defined by a set of weights w (three for the first neurone, S1,  three for S2). w=[0,-1,1,-1,1,-1] Modifications to the code in the  last post  have been around fine tuning the values in c onverting the outputs of the two neurons S1 and S2 into actions as shown below.     if s1=...