[{"data":1,"prerenderedAt":322},["ShallowReactive",2],{"project-18487327":3},{"id":4,"name":5,"line":5,"line_source":6,"title":7,"url":8,"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":35,"aspects":36,"strip":44,"post_text":46,"what":47,"said":78,"maker_in_thread":167,"shape":180,"grid":184,"attempts":286,"same_week":287,"maker_shows":40,"maker_hidden":315,"reader_version":316,"card":317},"18487327","Self-Driving Pi Car","title","Show HN: Self-Driving Pi Car","https:\u002F\u002Fgithub.com\u002Ffelipessalvatore\u002Fself_driving_pi_car","github.com","felsal",1542643509,2018,304,42,85,2155,4,"legend","ai","self-driving toy car","other",[23,24,25,26,27],"self-driving","raspberry pi","neural network","lego mindstorms","python","curious",0.22,{"positive":31,"neutral":32,"mixed":33,"critical":34},6,8,0,2,16,{"idea":37,"design":39,"execution":41,"docs":42,"performance":43},{"positive":38,"critical":33},3,{"positive":40,"critical":40},1,{"positive":33,"critical":40},{"positive":33,"critical":33},{"positive":33,"critical":33},[33,33,33,45,45,33,45,33,33,33,33,33,33,33,38,33,38,33,38,45,38,33,33,33,33,40,33,33,33,40,38,33,33,33,45,33,38,38,38,45],5,null,{"problem":46,"audience":46,"pricing":46,"motivation":46,"time_to_build":46,"stack":48,"openness":75,"stage":76,"team_size":77},[49,56,60,64],{"value":50,"source":51,"evidence":52},"Python 2","maker",[53],{"id":54,"by":10,"text":55},"18488447","Yep, we hate Python 2 too! But we develop the project in Python2 to use the library NXT-Python (the library responsible to control the Lego Mindstorms NXT). But, in our defense,…",{"value":57,"source":51,"evidence":58},"NXT-Python library",[59],{"id":54,"by":10,"text":55},{"value":61,"source":51,"evidence":62},"Lego Mindstorms NXT",[63],{"id":54,"by":10,"text":55},{"value":65,"source":66,"evidence":67},"Raspberry Pi","commenter",[68,72],{"id":69,"by":70,"text":71},"18488402","benn_88","Awesome project, but why Python 2? :( Pre-compiled Python wheels are available for Python 3 on Raspberry Pi at piwheels.org (default for pip in Raspbian)",{"id":73,"by":10,"text":74},"18495519","No, you don't need a GPU at all. It helps, of course, but it not necessary. I don't remember the specs of the computer we used, but to give you an idea we give all the training…","open_source","launched","team",{"praise":79,"objections":99,"requests":115,"questions":130,"alternatives":148},[80,95],{"value":81,"source":66,"evidence":82},"Cool, fun project",[83,87,91],{"id":84,"by":85,"text":86},"18488564","evolutionas","Cool project! Last year I built self driving robot for my bachelor's thesis. Instead of building end-to-end deep learning pipeline I used two neural nets: one trained with…",{"id":88,"by":89,"text":90},"18488760","iinc","Nice work. I worked on a similar project where I created an adaptive cruise control prototype. I used a camera and a CNN to determine the distance from the car ahead of my car.…",{"id":92,"by":93,"text":94},"18489771","normalfaults","Awesome! have y'all seen donkeycar? http:\u002F\u002Fwww.donkeycar.com\u002F great for meetups\u002Fhackathons!",{"value":96,"source":66,"evidence":97},"Useful resource for meetups and hackathons (donkeycar)",[98],{"id":92,"by":93,"text":94},[100,107],{"value":101,"source":66,"evidence":102},"Turns in place at boundaries, unrealistic turning radius",[103],{"id":104,"by":105,"text":106},"18491879","tintor","Looking at the video, the toy car is turning in-place when it gets to the boundary. There is no realistic turning radius proportional to its size.",{"value":108,"source":66,"evidence":109},"Uses Python 2, which is being deprecated",[110,111],{"id":69,"by":70,"text":71},{"id":112,"by":113,"text":114},"18490215","newaccoutnas","No, but the project will be dead in a year (or rather bitrot will set in), so if there are old dependencies then perhaps effort should be put into porting or working out the…",[116,123],{"value":117,"source":66,"evidence":118},"Shrink the large README image",[119],{"id":120,"by":121,"text":122},"18488293","rusbus","Cool experiment! Tiny nit, can you resize the image in the README so it isn't 12MB?",{"value":124,"source":66,"evidence":125},"Switch to Ackermann steering for realistic dynamics",[126],{"id":127,"by":128,"text":129},"18503830","pksm","The toy car used differential steering with 2-wheels and a castor wheel. One of our ideas of future work was to change the current steering method for an Ackerman model, giving…",[131,138],{"value":132,"source":66,"evidence":133},"Does it use a single frame or previous frames?",[134],{"id":135,"by":136,"text":137},"18489470","Aspos","Does it \"look\" into a single frame or does it take previous steps into account as well?",{"value":139,"source":66,"evidence":140},"Does training need a GPU?",[141,145],{"id":142,"by":143,"text":144},"18491986","dmurthy","So all of the training was done without a GPU?",{"id":146,"by":143,"text":147},"18492652","Elaborating on my question. In your read me it says - \"In the computer that you will perform the training -- protip: don't train the model in the Raspberry Pi! -- install all the…",[149,153,160],{"value":150,"source":66,"evidence":151},"Donkeycar",[152],{"id":92,"by":93,"text":94},{"value":154,"source":66,"evidence":155},"FormulaPi",[156],{"id":157,"by":158,"text":159},"18493695","eddie_catflap","FormulaPi is a robot car racing series along similar lines. Submit your own code and race against teams from around the world. I've participated in the last couple of seasons and…",{"value":161,"source":66,"evidence":162},"DIY Robocars",[163],{"id":164,"by":165,"text":166},"18491732","diyrobocars","There's also https:\u002F\u002Fdiyrobocars.com\u002F and https:\u002F\u002Fdiyrobocars.com.au in Australia.",{"comments":168,"answered":169,"key":170},9,7,[171,174,177],{"id":172,"text":173},"18488668","Nice project and cool video! (our video is not so well produced :P). Our project was a summer project, we did it in this January. The evolution of the project will be something…",{"id":175,"text":176},"18489953","I didn't know about it, thanks!",{"id":178,"text":179},"18495482","Great! Our project had the same idea of combining different skills: I was working with ML and my colleague was the TA from a robotics class.",{"commenters":181,"max_depth":45,"maker_replies":168,"first_comment_mins":182,"lifespan_hours":183},28,118,60,[185,187,189,192,194,197,200,202,203,204,207,208,211,213,214,216,218,220,223,226,229,232,234,235,238,241,243,245,248,250,253,256,258,262,265,268,272,275,278,281,282,283],[84,33,33,186,85,33],"other\u002Fneutral\u002Fnone",[172,33,33,188,10,40],"commenter\u002Fneutral\u002Fnone",[190,33,33,186,191,33],"18497331","qxzw",[88,40,45,193,89,33],"project\u002Fpositive\u002Fidea",[195,40,45,196,128,33],"18488885","project\u002Fpositive\u002Fdesign",[198,40,33,186,199,33],"18489030","dominotw",[92,34,45,201,93,33],"project\u002Fpositive\u002Fnone",[175,34,33,188,10,40],[164,34,33,186,165,33],[205,38,33,186,206,33],"18494376","moftz",[178,38,33,188,10,40],[209,17,33,186,210,33],"18488569","luizb",[212,17,33,186,10,40],"18489332",[157,45,33,186,158,33],[135,31,38,215,136,33],"project\u002Fneutral\u002Fexecution",[217,31,33,215,10,40],"18489497",[120,169,38,219,121,33],"project\u002Fneutral\u002Fdocs",[221,169,33,222,10,40],"18488392","maker\u002Fneutral\u002Fdocs",[224,169,38,219,225,33],"18491662","myroon5",[227,32,45,193,228,33],"18504402","nazz",[230,168,33,186,231,33],"18507721","sdan",[69,233,38,215,70,33],10,[54,233,33,215,10,40],[236,233,33,188,237,33],"18489010","mehrdadn",[239,233,33,188,240,33],"18489054","markovbot",[242,233,33,188,237,33],"18489229",[112,233,40,244,113,33],"project\u002Fcritical\u002Fexecution",[246,233,33,186,247,33],"18490594","1manowar1",[249,233,33,186,237,33],"18497288",[251,233,33,188,252,33],"18490706","diminoten",[104,254,40,255,105,33],11,"project\u002Fcritical\u002Fdesign",[127,254,38,257,128,33],"project\u002Fneutral\u002Fdesign",[259,260,33,186,261,33],"18489638",12,"antoniuschan99",[263,260,33,186,264,33],"18489979","5874-4b22-a4e0",[266,260,33,186,267,33],"18492193","VectorLock",[269,270,45,193,271,33],"18489066",13,"prando",[273,270,33,274,10,40],"18489142","project\u002Fneutral\u002Fnone",[276,270,38,277,128,33],"18489217","project\u002Fneutral\u002Fidea",[142,279,38,280,143,33],14,"project\u002Fneutral\u002Fperformance",[146,279,38,280,143,33],[73,279,33,280,10,40],[284,279,45,285,143,33],"18500136","maker\u002Fpositive\u002Fnone",[],[288,293,298,302,307,311],{"id":289,"name":290,"points":291,"category":292},"18480115","DoodleMaster",302,"dev_tools",{"id":294,"name":295,"points":296,"category":297},"18492899","Shortcut Roulette",253,"productivity",{"id":299,"name":300,"points":301,"category":297},"18475527","Gmail Classic",226,{"id":303,"name":304,"points":305,"category":306},"18469632","Stacks",217,"learning_science",{"id":308,"name":309,"points":310,"category":292},"18484795","Shodan Snippets",145,{"id":312,"name":313,"points":314,"category":306},"18489459","SkillUpper",143,false,"v2",{"id":318,"name":5,"line":5,"ai":315,"cat":19,"year":12,"points":13,"comments":14,"rec":28,"s":29,"top":17,"kw":319,"maker":10,"domain":9,"tier":18,"attempts":33,"strip":320,"url":8,"mix":321,"praise":81,"objection":101,"sub":20},18487327,[23,24,25,26,27],"0005505000000030303530000100013000503335",[31,32,33,34],1793990982234]