Overview
Skild AI ibasa remarobhoti rakarukwa kubva muCarnegie Mellon riri kuvaka imwe chete, chinangwa-chakawanda 'nheyo modhi' uropi hwemarobhoti, inonzi Skild Brain. Izvo zvine basa nekuti ine chinangwa chekuita imwe yakagovaniswa AI kushanda kune akawanda akasiyana marobhoti miviri nemabasa, pane kudzidzisa modhi nyowani yemuchina wega wega.
Skild AI Robot Foundation Models inonzwisiswa zvakanyanya mumamiriro ehurongwa, kuwana modhi, sarudzo dzepuratifomu, uye ecosystem kudyidzana.
Deep Dive
Yakavambwa muna 2023 nemapurofesa eCMU Deepak Pathak naAbhinav Gupta, Skild AI yakasimudza hombe Series A (inenge mazana matatu emamiriyoni emadhora) pamutengo unosvika bhiriyoni imwe nemazana mashanu emadhora, inotsigirwa nevanoita mari vanosanganisira SoftBank, Lightspeed, Coatue, naJeff Bezos. Thesis yayo ndeyekuti marobhoti akashaya iyo 'GPT nguva' nekuti modhi dzaive dzakatetepa uye dzakatetepa. Skild inodzidzisa yakajairika robhoti hwaro modhi pane yakakura uye yakasiyana data, kusanganisira simulation, internet vhidhiyo, uye teleoperation, saka huropi humwe hunogona kudzora akasiyana embodiments, quadrupeds, humanoids, uye maoko, uye kujairana nemabasa matsva nenharaunda. Iyo kambani inosimbisa kusimba, generalization kune zvisingaonekwe zviitiko, uye kubuda kwehunyanzvi, kuisa iyo Skild Brain seye embodiment-agnostic middleware yekuuya kwemafungu emarobhoti.
Technical Insight
Skild's approach inomira pachiyero uye kusiyana-siyana kwedata rekudzidzisa kuti riite generalization. Nekudzidziswa kuyambuka akawanda marobhoti embodiments uye nekushandisa yakakura simulation padivi pechaiyo uye webhu vhidhiyo, modhi inodzidza hunyanzvi hwesensorimotor inotamisa kwete kukwirisa kumuchina mumwe. Iko kubheti kunoratidza mhando dzemitauro mikuru: data rakawanda uye paramita zvinopa kusimba kwechimbichimbi, kurega mutemo iwoyo uchibata zvinhu zvitsva, terrain, uye zvinokanganisa, uye kupora kubva mukukundikana segumbo rinosundirwa kana kutsvedza.
Mastering Skild AI Robot Foundation Models
Skild AI ibasa remarobhoti rakarukwa kubva muCarnegie Mellon riri kuvaka imwe chete, chinangwa-chakawanda 'nheyo modhi' uropi hwemarobhoti, inonzi Skild Brain. Izvo zvine basa nekuti ine chinangwa chekuita imwe yakagovaniswa AI kushanda kune akawanda akasiyana marobhoti miviri nemabasa, pane kudzidzisa modhi nyowani yemuchina wega wega. Skild AI Robot Foundation Models inonzwisiswa zvakanyanya mumamiriro ehurongwa, kuwana modhi, sarudzo dzepuratifomu, uye ecosystem kudyidzana. Kuti uvake kunzwisisa kwakadzama, bata Skild AI Robot Foundation Models semuenzaniso wekushandisa, kwete chinhu chimwe chete: tsanangura zvinodiwa, kujekesa fungidziro, uye patsanura izvo system inogona kuita nekuvimbika kubva kune ichiri kuda kutonga kwenyanzvi.
Mukuita, zvikwata zvakasimba zvinoshandisa Skild AI Robot Foundation Models inoongorora zano revatengesi, kuvimbika kwemepu yemugwagwa, uye njodzi yekuvhara isati yaita. Ivo vanonyora zvakajeka maitiro ebudiriro, bvunzo vachipokana ne data rechokwadi uye mafambiro ebasa, uye iterate zvichibva pane zvakacherechedzwa maitiro ekutadza kwete kuhwina-nguva imwe chete yebhenji. Apa ndipo apo kunzwisisa kwe theoretical kunoshanduka kuve kugona kwakasimba pane chigadzirwa, mutemo, uye mashandiro.
Mamepu emigwagwa emutengesi anopesvedzera izvo izvo timu yako inogona kugadzira inotevera. Panguva imwecheteyo, zviziviso zveLaunch zvinogona kupfuura kugadzikana mune chaiyo yekugadzira workflows. Nzira yakatsiga ndeyekubatanidza kukurumidza kuyedza nekutonga: mhanyisa vatyairi vendege, tora humbowo, buritsa matanda esarudzo, uye urambe uchivandudza chengetedzo semaitiro emuenzaniso, zvinotarisirwa nemushandisi, uye zvinodikanwa zvekutonga.
Strategic Impact
Mamepu emigwagwa emutengesi anopesvedzera izvo izvo timu yako inogona kugadzira inotevera.
Mamepu emigwagwa emutengesi anopesvedzera izvo izvo timu yako inogona kugadzira inotevera. Mukutumirwa kwemhando yepamusoro, izvi zvinoshandurirwa kuita mitemo inoyerwa yekushanda, miganhu yevaridzi, uye tsika dzekudzokorora dzinodzokororwa kuitira kuti zvikwata zvikwire kuvimba pane kukwidza kusajeka.
Mamiriro ezvekutengeserana uye sarudzo dzekuendesa dzinokanganisa mutengo wenguva refu uye njodzi.
Mamiriro ezvekutengeserana uye sarudzo dzekuendesa dzinokanganisa mutengo wenguva refu uye njodzi. Mukutumirwa kwemhando yepamusoro, izvi zvinoshandurirwa kuita mitemo inoyerwa yekushanda, miganhu yevaridzi, uye tsika dzekudzokorora dzinodzokororwa kuitira kuti zvikwata zvikwire kuvimba pane kukwidza kusajeka.
Kambani inokurudzira inogadzirisa kusarudzika kwechigadzirwa, mamiriro ekuchengetedza, uye kuvhurika.
Kambani inokurudzira inogadzirisa kusarudzika kwechigadzirwa, mamiriro ekuchengetedza, uye kuvhurika. Mukutumirwa kwemhando yepamusoro, izvi zvinoshandurirwa kuita mitemo inoyerwa yekushanda, miganhu yevaridzi, uye tsika dzekudzokorora dzinodzokororwa kuitira kuti zvikwata zvikwire kuvimba pane kukwidza kusajeka.
Real-World Implementation
Ruoko rwekuchengetera zvinhu uye patrol akapetwa quadruped yakafanana Skild Brain, achigovana hunyanzvi hwakadzidzwa pachinzvimbo chesoftware yakaparadzana.
Robhoti rakadzidziswa zvakanyanya mukuenzanisa rinotamisa hunyanzvi hwaro hwekufamba uye kubata kumuchina chaiwo panzvimbo yausina kujaira.
Humanoid inodzoreredza chiyero chayo mushure mekusundirwa, ichiratidza kusimba kweiyo modhi kune kukanganisa kwemuviri.
Iyo hardware yekutanga marezinesi Skild's hwaro modhi seAI 'brain' pane kuvaka yayo yekudzora stack kubva kutanga.
Maitiro Ekuita
Skild AI Robot Foundation Models mukuita
Ruoko rwekuchengetera zvinhu uye patrol akapetwa quadruped yakafanana Skild Brain, achigovana hunyanzvi hwakadzidzwa pachinzvimbo chesoftware yakaparadzana.
Ruoko rwekuchengetera zvinhu uye patrol quadruped inomhanya yakafanana Skild Brain, kugovana hunyanzvi hwakadzidzwa pachinzvimbo cheakaparadzana bespoke software Matimu anowanzo kuwana mhedzisiro iri nani kana achinge atsanangura zvikumbaridzo zvemhando yepamusoro kumberi, chengetedza nzira yekukwira kwevanhu yemakesi emupendero, uye kuteedzera zvese zvakawanikwa zvechigadzirwa nemitengo yekukanganisa nekufamba kwenguva.
Skild AI Robot Foundation Models mukuita
Robhoti rakadzidziswa zvakanyanya mukuenzanisa rinotamisa hunyanzvi hwaro hwekufamba uye kubata kumuchina chaiwo panzvimbo yausina kujaira.
Robhoti rakadzidziswa zvakanyanya mukuedzesera rinoendesa hunyanzvi hwaro hwekufamba uye kubata kumuchina chaiwo panzvimbo yausingazivi Matimu anowanzo kuwana mhedzisiro iri nani kana achinge atsanangura mabindu emhando kumberi, chengetedza nzira yekukwira kwevanhu yemakesi ekumucheto, uye kuteedzera zvese zvakawanikwa zvechigadzirwa nemitengo yekukanganisa nekufamba kwenguva.
Skild AI Robot Foundation Models mukuita
Humanoid inodzoreredza chiyero chayo mushure mekusundirwa, ichiratidza kusimba kweiyo modhi kune kukanganisa kwemuviri.
Humanoid inodzoreredza chiyero chayo mushure mekusundirwa, ichiratidza kusimba kweiyo modhi kune kukanganisa kwemuviri Matimu anowanzo kuwana mhedzisiro iri nani kana achinge atsanangura emhando yepamusoro kumberi, chengetedza nzira yekukwira kwevanhu yemakesi emupendero, uye kuteedzera zvese zvakawanikwa zvechigadzirwa nemitengo yekukanganisa nekufamba kwenguva.
Skild AI Robot Foundation Models mukuita
Iyo hardware yekutanga marezinesi Skild's hwaro modhi seAI 'brain' pane kuvaka yayo yekudzora stack kubva kutanga.
Iyo hardware yekutanga marezinesi Skild's hwaro modhi seAI 'brain' pane kuvaka yayo yekudzora stack kubva kutanga Matimu anowanzo kuwana mhedzisiro iri nani kana achinge atsanangura emhando yepamusoro kumberi, chengetedza nzira yekukwira kwevanhu yemakesi emupendero, uye kuteedzera zvese zvakawanikwa zvechigadzirwa uye kukanganisa mutengo nekufamba kwenguva.
Njodzi & Guardrails
Zviziviso zvekutanga zvinogona kupfuura kugadzikana mune chaiyo yekugadzira workflows.
Mitengo yeAPI kana shanduko yepolicy inogona kukanganisa fungidziro husiku.
Kutsamira kune mumwe-mutengesi kunowedzera kukiya-mukati uye mari yekufambisa.
Implementation Roadmap
Ongorora vanopa uchishandisa ako ega mabasa uye dataset.
Ongorora vanopa uchishandisa ako ega mabasa uye dataset. Bata nhanho yega yega segedhi rehumbowo: kana maitiro asina kusangana, imbomira kuburitsa, vhara gaka, uye wobva wawedzera kushandiswa.
Wongorora zvakavanzika, chengetedzo, uye mazwi emutemo usati wabatanidzwa.
Wongorora zvakavanzika, chengetedzo, uye mazwi emutemo usati wabatanidzwa. Bata nhanho yega yega segedhi rehumbowo: kana maitiro asina kusangana, imbomira kuburitsa, vhara gaka, uye wobva wawedzera kushandiswa.
Chengetedza chirongwa chekudzokera kumashure kune mamodheru kana vatengesi.
Chengetedza chirongwa chekudzokera kumashure kune mamodheru kana vatengesi. Bata nhanho yega yega segedhi rehumbowo: kana maitiro asina kusangana, imbomira kuburitsa, vhara gaka, uye wobva wawedzera kushandiswa.
Tarisa zvinyorwa zvekuburitsa kuitira kuti shanduko yemigwagwa isashamise zvikwata.
Tarisa zvinyorwa zvekuburitsa kuitira kuti shanduko yemigwagwa isashamise zvikwata. Bata nhanho yega yega segedhi rehumbowo: kana maitiro asina kusangana, imbomira kuburitsa, vhara gaka, uye wobva wawedzera kushandiswa.