Svemirdb#1044

Hodajući roboti ubrzavaju istraživanje Mjeseca i Marsa

(2w ago)
San Francisco, US
phys.org
Hodajući roboti ubrzavaju istraživanje Mjeseca i Marsa

Hodajući roboti ubrzavaju istraživanje Mjeseca i Marsa📷 © Tech&Space

  • 22 minute kašnjenja u komunikaciji s Marsom ograničavaju operacije
  • Energetska učinkovitost i sigurnost usporavaju trenutačna vozila
  • Noge umjesto kotača otvaraju nove mogućnosti za terenske misije

Planetarna istraživanja već desetljećima ovise o vozilima na kotačima — ali njihova predvidljivost i sporo kretanje postaju sve većim ograničenjem. Marsovska vozila poput Perseverancea moraju čekati do 22 minute na potvrdu svake naredbe s Zemlje, a ograničenja prijenosa podataka prisiljavaju znanstvenike na unaprijed planirane rute. To nije samo pitanje efikasnosti: terenski izazovi, poput oštrih stijena ili labavog tla, često zahtijevaju trenutačne odluke koje trenutačni roveri jednostavno ne mogu donijeti.

Prema najnovijim istraživanjima objavljenim u Science Robotics, hodajući roboti bi mogli riješiti oba problema. Dok kotači zahtijevaju ravne površine i postepeno kretanje, noge omogućuju dinamičniju interakciju s terenom — od penjanja po strmim padinama do izbjegavanja zapinjanja u pijesku. To nije samo teorija: ANYmal, robot razvijen na ETH Zürichu, već demonstrira sposobnost samostalnog kretanja po neravnim površinama uz minimalnu ljudsku intervenciju.

Važnost ove promjene leži u operativnoj slobodi. Umjesto da čekaju signale s Zemlje, budući robotski istraživači mogli bi donositi odluke u realnom vremenu, koristeći lokalne senzore i algoritme za navigaciju. To bi smanjilo rizik od oštećenja opreme i ubrzalo prikupljanje uzoraka — ključno za misije poput Artemis, gdje je vrijeme na površini Mjeseca ograničeno na samo nekoliko dana po letu.

Zašto bi promjena dizajna mogla promijeniti dinamiku planetarnih istraživanja

Zašto bi promjena dizajna mogla promijeniti dinamiku planetarnih istraživanja📷 © Tech&Space

Zašto bi promjena dizajna mogla promijeniti dinamiku planetarnih istraživanja

Međutim, prelazak s kotača na noge nije samo pitanje mehanike — zahtijeva potpunu promjenu pristupa planiranju misija. Trenutačni roveri, poput Curiosityja, optimizirani su za energetsku učinkovitost i postepeno mapiranje teritorija. Hodajući roboti, s druge strane, zahtijevaju više energije po metru, ali tu „cijenu“ nadoknađuju bržim pokrivanjem teritorija i mogućnošću pristupa dotad nedostupnim lokacijama. ESA-in projekt LEAP već testira hibridne modele koji kombiniraju kotače i noge, tražeći optimalan balans između stabilnosti i pokretljivosti.

Najveće nepoznato ostaje dugoročna izdržljivost u ekstremnim uvjetima. Marsovska prašina, koja je već onesposobila solarne panele rovera Opportunity, predstavlja isti rizik i za pokretne dijelove hodajućih robota. Ipak, potencijalne prednosti nadmašuju izazove: prema simulacijama NASA-inog Jet Propulsion Laboratoryja, robot s nogama mogao bi preći udvostručenu udaljenost u istom vremenu, čime bi se znatan dio misije mogao posvetiti znanstvenom radu umjesto navigaciji.

Konačno, ova tehnologija nije samo o bržem kretanju — ona mijenja samu logiku istraživanja. Umjesto da se oslanjamo na statičke planove, buduće misije mogle bi biti dinamičnije, prilagodljivije i, što je najvažnije, sigurnije za dragocjenu opremu. To je korak prema autonomnijem istraživanju, gdje roboti nisu samo alati, već partneri u otkrivanju.

Lunar ExplorationMars ExplorationPlanetary Robotics

//Comments

AIAmazon’s $50B OpenAI bet: Trainium’s real test begins nowRoboticsHumanoid Tennis: Demo Sparkle vs. Real-World DustAIGoogle’s Gemini games flop: AI hype hits gamer realityRoboticsAtlas Redefines Humanoid DesignAINvidia’s AI tax: half your salary or half your careerRoboticsOne antenna, two worlds: robot sniffs out realityAITriangle Health’s $4M AI won’t replace your doctor—yetRoboticsDrone swarms take flight—but not off the demo lot yetAIHumble AI is just healthcare’s latest buzzword for ‘don’t trust us yet’RoboticsRobots share skills—but can they work outside the lab?AIOpenAI’s teen safety tools: open source or open question?SpaceMapping the Local Bubble’s magnetic field reshapes cosmic scienceAITinder’s AI gambit: swiping left on endless swipingSpaceStarship’s Tenth Test: The Reusability Threshold CrossedAINVIDIA’s Alpamayo AI: Self-Driving’s Hardest Problem or Just Another Demo?SpaceMeta Shuts VR PiratesAIWaymo’s police problem exposes AV’s real-world blind spotsSpaceJWST peels back dust to reveal star birth in W51AILittlebird’s $11M bet: AI that reads your screen—without the screenshotsSpaceAI’s Copyright Chaos Threatens Space Exploration DataAIUK firms drown in AI hype, emerge with empty spreadsheetsSpaceExoplanet spins confirm a planetary mass ruleAIOpenAI’s erotic chatbot pause is a rare win for ethics over hypeGamingCrimson Desert’s AI art fail: a mockup that slipped throughAIApple’s Gemini Distillation: On-Device AI Without the Cloud HypeGamingPearl Abyss hid AI assets in Crimson Desert—now players want answersAICapcom’s AI partner talk is just corporate speak for ‘we’ll use it carefully’GamingCapcom Rejects AI AssetsAIOpenSeeker’s open gambit: Can 11K data points break AI’s data monopoly?GamingWine 11: Linux gaming just got its first real power-up in yearsAIGimlet Labs Solves AI BottleneckGamingGod of War spinoff shifts focus—what it means for players and SonyAIHelion Powers OpenAITechnologyTaiwan’s chip giants bet on helium and nukes to dodge supply shocksAINVIDIA’s OpenShell: Security for AI Agents or Just Another Hype Shell?TechnologySignal’s phishing crisis exposes the limits of encrypted trustAIDRAFT Boosts AI SafetyTechnologyEU Chat Control Blocked—But Privacy Isn’t Safe YetAIProject Glasswing: AI finds flaws everywhere—except in its own hypeMedicineProstate cancer atlas maps earliest cellular changesAIPAM: Complex Math for a 10% Performance HitMedicineTelmisartan Boosts Cancer TreatmentAIOpenAI’s erotic chatbot pause exposes AI’s adult content dilemmaMedicineXaira Unveils X-CellAIAI Ranks Recovery Factors—but Who’s Really Listening?MedicineAI Fails to Speed Lung Cancer DiagnosisAIDeepMind’s AI safety play: real guardrails or just another demo?MedicineA Faster Path to Covalent Protein Therapies—With LimitsAILSD for MLLMs: Reinforcement Learning Cuts the Demo FatAIMicrosoft’s 700B AI bet: Hype or a real retail crystal ball?AIAdobe & NVIDIA’s real-time trick shouldn’t work—but it doesAIEmbeddings hit their limits—and no one’s checking the fine printAIAI Chatbots Break Rational ThinkersAIUS AI FrameworkAIAxra’s stablecoin banking: AI hype meets emerging marketsAISlimes Get AIAIAmazon’s $50B OpenAI bet: Trainium’s real test begins nowRoboticsHumanoid Tennis: Demo Sparkle vs. Real-World DustAIGoogle’s Gemini games flop: AI hype hits gamer realityRoboticsAtlas Redefines Humanoid DesignAINvidia’s AI tax: half your salary or half your careerRoboticsOne antenna, two worlds: robot sniffs out realityAITriangle Health’s $4M AI won’t replace your doctor—yetRoboticsDrone swarms take flight—but not off the demo lot yetAIHumble AI is just healthcare’s latest buzzword for ‘don’t trust us yet’RoboticsRobots share skills—but can they work outside the lab?AIOpenAI’s teen safety tools: open source or open question?SpaceMapping the Local Bubble’s magnetic field reshapes cosmic scienceAITinder’s AI gambit: swiping left on endless swipingSpaceStarship’s Tenth Test: The Reusability Threshold CrossedAINVIDIA’s Alpamayo AI: Self-Driving’s Hardest Problem or Just Another Demo?SpaceMeta Shuts VR PiratesAIWaymo’s police problem exposes AV’s real-world blind spotsSpaceJWST peels back dust to reveal star birth in W51AILittlebird’s $11M bet: AI that reads your screen—without the screenshotsSpaceAI’s Copyright Chaos Threatens Space Exploration DataAIUK firms drown in AI hype, emerge with empty spreadsheetsSpaceExoplanet spins confirm a planetary mass ruleAIOpenAI’s erotic chatbot pause is a rare win for ethics over hypeGamingCrimson Desert’s AI art fail: a mockup that slipped throughAIApple’s Gemini Distillation: On-Device AI Without the Cloud HypeGamingPearl Abyss hid AI assets in Crimson Desert—now players want answersAICapcom’s AI partner talk is just corporate speak for ‘we’ll use it carefully’GamingCapcom Rejects AI AssetsAIOpenSeeker’s open gambit: Can 11K data points break AI’s data monopoly?GamingWine 11: Linux gaming just got its first real power-up in yearsAIGimlet Labs Solves AI BottleneckGamingGod of War spinoff shifts focus—what it means for players and SonyAIHelion Powers OpenAITechnologyTaiwan’s chip giants bet on helium and nukes to dodge supply shocksAINVIDIA’s OpenShell: Security for AI Agents or Just Another Hype Shell?TechnologySignal’s phishing crisis exposes the limits of encrypted trustAIDRAFT Boosts AI SafetyTechnologyEU Chat Control Blocked—But Privacy Isn’t Safe YetAIProject Glasswing: AI finds flaws everywhere—except in its own hypeMedicineProstate cancer atlas maps earliest cellular changesAIPAM: Complex Math for a 10% Performance HitMedicineTelmisartan Boosts Cancer TreatmentAIOpenAI’s erotic chatbot pause exposes AI’s adult content dilemmaMedicineXaira Unveils X-CellAIAI Ranks Recovery Factors—but Who’s Really Listening?MedicineAI Fails to Speed Lung Cancer DiagnosisAIDeepMind’s AI safety play: real guardrails or just another demo?MedicineA Faster Path to Covalent Protein Therapies—With LimitsAILSD for MLLMs: Reinforcement Learning Cuts the Demo FatAIMicrosoft’s 700B AI bet: Hype or a real retail crystal ball?AIAdobe & NVIDIA’s real-time trick shouldn’t work—but it doesAIEmbeddings hit their limits—and no one’s checking the fine printAIAI Chatbots Break Rational ThinkersAIUS AI FrameworkAIAxra’s stablecoin banking: AI hype meets emerging marketsAISlimes Get AI
⊞ Foto Review