An update on the A* pathfinding system I’m doing for my prototype. I’ve added smoothing to the paths so I get a more natural looking movement. I’ve also added weights, which means I can add a penalty to moving on different surfaces, which the AI will take into account when finding a path.
For example if there is puddle of mud between the unit and its target location (and walking through mud slows the units speed), it will figure out if its better to walk around the mud or walk through it. Another example as shown in the GIF, the grass has a small movement penalty, making the AI prefer to walk along the road instead of straight to the target, despite the path being longer.
The always-fantastic Art & Tech resource Creative Applications have put together their list of highlights from the year:
As 2017 comes to a close, we take a moment to look back at the outstanding work done this year. From spectacular performances, large scale installations, devices and tools to the new virtual spaces for artistic exploration – so many great projects are being added to the CAN archive! Here are a just few, 25 in total, that we and you enjoyed the most this year.
Have a look for yourself here
Bitsquare, decentralised #bitcoin exchange
SP. Gynoid (Fembot)
A.I. Artificial Intelligence (2001)
Things auto-tagged ‘Jungle Gym’ on Flickr
Flickr has introduced auto-tagging, aided by Machine Learning (I checked that it is with ML and found this Yahoo machine learning presentation). The user response has been quite negative so far, this Flickr forum post has a lot of angry pro users having to correct thousands of photographs for inexact tagging. Flickr openly say they want people to correct their tags because that will further help train their ML algorithms.
Alex Hern of the Guardian wrote about some contentious cases such as when people have been auto-tagged ‘ape’ and when concentration camps get tagged ‘sport’ and ‘jungle gym’. In isolation these cases seem really outrageous so I did a search for ‘jungle gym’ and found many false positives, painting a much more systemic problem; it seems Flickr’s strategy is to auto-tag as much as possible, forcing their users, often not bothered about tags, to respond by curating a better set of tags for each image. So the bigger strategy seems to pitch machine learning against human labour in an attempt to make their algos smarter and their image service perfectly tagged.
Motion capture- you never know when I may need to do one of The Rock’s Baywatch stunts/ better safe than sorry.
We worked on adding even more to the guns game! Here you can see guns stats displaying on UI, gun animations, and below, you can see enemies using some basic state engine based AI to hunt down and track the player!
继续阅读
Nueral Network applies Sesame Street to Trumps - Chris Rodley
Artist Chris Rodley - “I used deep learning to turn the Trump family into Sesame St characters. Was not prepared for the nameless horror”
100 cans of spray paint, 60 hours of painting, 24 individual frames
INSA is a graffiti artist who makes gif animations out of his physical art. Here he paints and animates the beautiful original painting by James Jean, which was created for Paramount’s new movie mother!
Click here to watch INSA bring this painting to life
Vimeo pitch of the founders of Ethereum, who want to use the Bitcoin architecture to reinvent the rest of our political economy—smart contracts, distributed corporations, and even decentralized political parties
Little visual experiment by Henry Everett employs iOS ARKit to produce that familiar computer crash effect:
Getting some errors in #ARKit today. Cc: @comboldn pic.twitter.com/PWjS0npiUI
— Henry Everett (@henryeverett)
August 16, 2017
Link