[{"data":1,"prerenderedAt":259},["ShallowReactive",2],{"project-3417830":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":9,"maker":10,"posted_at":11,"year":12,"points":13,"comments":14,"rank_in_year":15,"shown_in_year":16,"top":17,"tier":18,"category":19,"subcategory":20,"format":21,"keywords":22,"reception":28,"sentiment":29,"stance_mix":30,"scored_comments":34,"aspects":35,"strip":42,"post_text":44,"what":45,"said":79,"maker_in_thread":154,"shape":163,"grid":166,"attempts":221,"same_week":222,"maker_shows":17,"maker_hidden":251,"reader_version":252,"card":253},"3417830","nnrccar","How I built a self-driving (RC) car.","title","Show HN: How I built a self-driving (RC) car.",null,"dps",1325546270,2012,300,21,37,1677,3,"legend","ai","neural network robotics","hardware",[23,24,25,26,27],"neural network","self-driving car","rc car","machine learning","arduino","loved",0.5,{"positive":31,"neutral":32,"mixed":33,"critical":33},8,4,0,12,{"docs":36,"idea":38,"performance":40,"execution":41},{"positive":37,"critical":33},2,{"positive":39,"critical":33},1,{"positive":33,"critical":33},{"positive":39,"critical":33},[33,33,33,33,43,43,17,17,33,43,33,17,33,43,33,17,33,43,43,43,43],5,"I have been taking Andrew Ng's Machine Learning course. The lecture module on Neural Networks ends with an intriguing video of the ALVINN autonomous car driving itself along normal roads at CMU in the mid 90s.\n\nI was inspired by that video to see what I could build myself.  A link to my incomplete write up was posted a couple of weeks ago (ouch!) but I finally finished it and open sourced the code tonight (so you can build your own self driving car).\n\nWhat do you think?\nhttp:\u002F\u002Fblog.davidsingleton.org\u002Fnnrccar\nhttps:\u002F\u002Fgithub.com\u002Fdps\u002Fnnrccar",{"problem":46,"audience":9,"pricing":9,"motivation":52,"time_to_build":9,"stack":56,"openness":76,"stage":77,"team_size":78},{"value":47,"source":48,"evidence":49},"Building a self-driving RC car using a neural network trained on camera input","maker",[50],{"id":51},"post",{"value":53,"source":48,"evidence":54},"Inspired by the ALVINN autonomous car video from Andrew Ng's course",[55],{"id":51},[57,65,72],{"value":58,"source":59,"evidence":60},"Octave","commenter",[61],{"id":62,"by":63,"text":64},"3419280","leoedin","How practical is running the software onboard? Would you have to port it out of Octave to Java? There seems to be a useful library in the form of [jlmath] that may well let you…",{"value":66,"source":59,"evidence":67},"Android phone camera",[68],{"id":69,"by":70,"text":71},"3418675","jakejake","super cool! it would be even more cool to see the arduino hooked up directly to the android so there was no separate computer involved and it was totally autonomous. even still,…",{"value":73,"source":59,"evidence":74},"Microcontroller (Arduino)",[75],{"id":69,"by":70,"text":71},"open_source","launched","solo",{"praise":80,"objections":104,"requests":112,"questions":124,"alternatives":143},[81,100],{"value":82,"source":59,"evidence":83},"Impressive project that combines course learning with a hands-on build",[84,88,92,96],{"id":85,"by":86,"text":87},"3418811","aiurtourist","Sorry, let me be more precise. After completing a course you correctly associated new knowledge with the potential for a cool project in an area which has been made very…",{"id":89,"by":90,"text":91},"3418378","Game_Ender","Very cool robotics project. Were you aware of FANN (http:\u002F\u002Fleenissen.dk\u002Ffann\u002Fwp) before you started your neural network implementation? Also have you tried any other machine…",{"id":93,"by":94,"text":95},"3418288","geekfactor","Wow, very nice. Congrats on putting the course into practice!",{"id":97,"by":98,"text":99},"3417978","noeltock","Well done, that's pretty awesome.",{"value":101,"source":59,"evidence":102},"Good write-up that works as a portfolio piece",[103],{"id":85,"by":86,"text":87},[105],{"value":106,"source":59,"evidence":107},"Budget DIY setup is not a realistic path to real driverless cars",[108],{"id":109,"by":110,"text":111},"3419135","unwind","If you were to copy this project using slightly more powerful components (higher resolution video, faster processing pipeline, more powerful servos) to automate the driving a…",[113,120],{"value":114,"source":59,"evidence":115},"Asks for latency measurements",[116],{"id":117,"by":118,"text":119},"3418760","endianswap","What sort of latencies did you see in this project while the car was running? Specifically, from the point where you have access to the camera's preview buffer to encoding it,…",{"value":121,"source":59,"evidence":122},"Asks for a fully onboard version without a separate computer",[123],{"id":69,"by":70,"text":71},[125,132],{"value":126,"source":59,"evidence":127},"How well would it scale to real routes?",[128],{"id":129,"by":130,"text":131},"3418401","EwanG","So I have to ask, how well do you think this would scale? AM I but a month of effort away from never having to actively drive to work again (given I follow the same route most…",{"value":133,"source":59,"evidence":134},"Why is the input layer one unit larger than the pixel count?",[135,139],{"id":136,"by":137,"text":138},"3421656","tzs","The input layer for the neural net has 25345 units. The input is a 176x144 image, which is 25344 pixels. Why is there one more input unit than pixels?",{"id":140,"by":141,"text":142},"3429046","iori42","I guess it's a constant bias term.",[144,148],{"value":145,"source":59,"evidence":146},"FANN neural network library",[147],{"id":89,"by":90,"text":91},{"value":149,"source":48,"evidence":150},"Romo smartphone robot",[151],{"id":152,"by":10,"text":153},"3419142","Yes, agreed - I do plan to try this next - just discovered this http:\u002F\u002Fwww.kickstarter.com\u002Fprojects\u002Fpeterseid\u002Fromo-the-smartphone-robot?ref=category (not self driving :-( ) robot…",{"comments":17,"answered":39,"key":155},[156,159,162],{"id":157,"text":158},"3417838","The links: http:\u002F\u002Fblog.davidsingleton.org\u002Fnnrccar https:\u002F\u002Fgithub.com\u002Fdps\u002Fnnrccar",{"id":160,"text":161},"3419137","A great question - I haven't actually measured it directly, but it's probably \u003C 200ms (video feels 'live' when you watch it). The prediction step takes circa 20ms on a MacBook…",{"id":152,"text":153},{"commenters":164,"max_depth":17,"maker_replies":17,"first_comment_mins":37,"lifespan_hours":165},18,64,[167,169,173,176,179,182,183,185,187,188,190,195,198,200,202,204,206,208,213,215,216],[157,33,33,168,10,39],"maker\u002Fneutral\u002Fnone",[170,39,33,171,172,33],"3419104","commenter\u002Fneutral\u002Fnone","JoachimSchipper",[174,39,33,171,175,33],"3419173","TeMPOraL",[177,39,33,171,178,33],"3419456","llambda",[180,37,43,181,86,33],"3418779","maker\u002Fpositive\u002Fdocs",[85,37,43,181,86,33],[89,17,17,184,90,33],"maker\u002Fneutral\u002Fidea",[117,32,17,186,118,33],"project\u002Fneutral\u002Fperformance",[160,32,33,186,10,39],[62,43,43,189,63,33],"project\u002Fpositive\u002Fexecution",[191,192,33,193,194,33],"3418489",6,"other\u002Fneutral\u002Fidea","richardburton",[129,196,17,197,130,33],7,"project\u002Fneutral\u002Fidea",[109,196,33,199,110,33],"commenter\u002Fcritical\u002Fidea",[69,31,43,201,70,33],"project\u002Fpositive\u002Fidea",[152,31,33,203,10,39],"project\u002Fneutral\u002Fexecution",[136,205,17,203,137,33],9,[140,205,33,207,141,33],"commenter\u002Fneutral\u002Fexecution",[209,210,43,211,212,33],"3419333",10,"maker\u002Fpositive\u002Fnone","josscrowcroft",[93,214,43,211,94,33],11,[97,34,43,211,98,33],[217,218,43,219,220,33],"3418308",13,"project\u002Fpositive\u002Fnone","jack83",[],[223,228,232,237,242,247],{"id":224,"name":225,"points":226,"category":227},"3413594","Scrollorama",395,"dev_tools",{"id":229,"name":230,"points":231,"category":227},"3404330","Honeybadger",147,{"id":233,"name":234,"points":235,"category":236},"3422493","momentum",85,"infrastructure",{"id":238,"name":239,"points":240,"category":241},"3416952","Damn Simple Carpooling",53,"productivity",{"id":243,"name":244,"points":245,"category":246},"3422721","Pjs",52,"languages",{"id":248,"name":249,"points":250,"category":246},"3419840","Tofu",49,false,"v2",{"id":254,"name":5,"line":6,"ai":251,"cat":19,"year":12,"points":13,"comments":14,"rec":28,"s":29,"top":17,"kw":255,"maker":10,"domain":256,"tier":18,"attempts":33,"strip":257,"url":-1,"mix":258,"praise":82,"objection":106,"sub":20},3417830,[23,24,25,26,27],"","000055330503050305555",[31,32,33,33],1794036492178]