Otonom & Robotik
1737 haber
Yarı Otonom Araçlarda İnsan Kontrolü: Güvenlik ve Sorumluluk Dengesi Nasıl Sağlanacak?
Yarı otonom sürüş sistemleri, sürücülerin yasal sorumluluğunu korurken aktif kontrolünü azaltarak güvenlik ve müdahale yeteneğini zayıflatıyor. Yeni araştırmalar, bu sistemlerde "anlamlı insan kontrolü"nün sağlanması için davranış ve algının nasıl ilişkilendirilebileceğini inceliyor.
Japan Airlines to begin humanoid robot trials at Haneda airport this month
Humanoid robots loading your luggage at the airport isn't a far-off scenario. Japan Airlines (JAL) has announced a pilot program...
Video Friday: Figure, 1X Ramp Up Humanoid Robot Production
Figure and 1X start mass humanoid robot production and Mars rovers Curiosity and Perseverance feature in this Video Friday, showcasing robotics advances.
Young researchers drive development of robotics industry in China's Hefei
Researchers test a humanoid robot at Youibot Robotics Co., Ltd. in Hefei, east China's Anhui Province, April 29, 2026.(Xinhua/Zhang Duan)...
GS Retail Co Ltd Aktie (KR7007070006): GS25 führt humanoid Robot als Familienmonatsprodukt ein
GS Retail hat über 130 Spezialprodukte für den Mai eingeführt, darunter als Branchenerste einen humanoid Robot. Die Convenience-Store-Kette GS25 meldet...
Humanoid Robot Motor Driver Chips Market Share Driven
Press release - Valuates Reports - Humanoid Robot Motor Driver Chips Market Share Driven by Advancements in Robotics Automation and High-Efficiency Power...
Humanoid robot passenger delays US flight over seating, battery issues
A Southwest Airlines flight from Oakland to San Diego was delayed for almost an hour after crew members had to reseat a child-sized humanoid robot and...
Humanoid robot Bebop delays California flight over battery safety concerns
Weighing in at around 32 kg, Bebop was set to travel “for work” with its human team However, this only prompted further questions and delays.
AI drives new career frontiers in China
A trainer supervises the training of a humanoid robot in a domestic tidy-up scenario at the Qingdao.
Meta acquires humanoid robot developer Assured Robot Intelligence
It's the latest move in a race to add artificial intelligence to consumer-facing home technology, with xAI and Amazon also competing for future category...
Meta Acquires ARI to Fuel Humanoid Robot Push
Meta has acquired Assured Robot Intelligence (ARI), a startup developing artificial intelligence models for general-purpose, humanoid robots.
The Humanoid Robot Market Is Smaller Than It Looks
Humanoid robot narratives usually begin with market size, not with the physics of the work, and that leads to distorted expectations.
Toyota Is Taking The Fight To BMW And Tesla, But Not With Cars
Toyota Motor Manufacturing Canada has just hired "Digit," a humanoid robot that is designed to load and unload parts bins on the assembly floor.
Affordance Agent Harness: Verification-Gated Skill Orchestration
Affordance grounding requires identifying where and how an agent should interact in open-world scenes, where actionable regions are often small, occluded, reflective, and visually ambiguous. Recent systems therefore combine multiple skills (e.g., detection, segmentation, interaction-imagination), yet most orchestrate them with fixed pipelines that are poorly matched to per-instance difficulty, offer limited targeted recovery from intermediate errors, and fail to reuse experience from recurring o...
Paired-CSLiDAR: Height-Stratified Registration for Cross-Source Aerial-Ground LiDAR Pose Refinement
We introduce Paired-CSLiDAR (CSLiDAR), a cross-source aerial-ground LiDAR benchmark for single-scan pose refinement: refining a ground-scan pose within a 50 m-radius aerial crop. The benchmark contains 12,683 ground-aerial pairs across 6 evaluation sites and per-scan reference 6-DoF alignments for sub-meter root-mean-square error (RMSE) evaluation. Because aerial scans capture rooftops and canopy while ground scans capture facades and under-canopy, the two modalities share only a fraction of the...
Recovering Hidden Reward in Diffusion-Based Policies
This paper introduces EnergyFlow, a framework that unifies generative action modeling with inverse reinforcement learning by parameterizing a scalar energy function whose gradient is the denoising field. We establish that under maximum-entropy optimality, the score function learned via denoising score matching recovers the gradient of the expert's soft Q-function, enabling reward extraction without adversarial training. Formally, we prove that constraining the learned field to be conservative re...
Robust Fusion of Object-Level V2X for Learned 3D Object Detection
Perception for automated driving is largely based on onboard environmental sensors, such as cameras and radar, which are cost-effective but limited by line-of-sight and field-of-view constraints. These inherent limitations may cause onboard perception to fail under occlusions or poor visibility conditions. In parallel, cooperative awareness via vehicle-to-everything (V2X) communication is becoming increasingly available, enabling vehicles and infrastructure to share their own state as object-lev...
Yapay Zeka Modelleri İçin Kenar Cihazlarda Performans Sınırlarını Zorlayan Yeni Bir Çözüm: Tempus
Büyük Dil Modellerinin (LLM) kenar cihazlarda verimli çalışması için kritik öneme sahip olan genel matris çarpımı (GEMM) işlemlerini hızlandırmak amacıyla geliştirilen Tempus, AMD Versal AI Edge platformları için çığır açıyor. Bu yeni çerçeve, yapay zeka hızlandırmasında performans ve verimlilik dengesini yeniden tanımlıyor.
Yüksek Hızlı Görüntü İşleme ile Robotlar İnsan Hareketlerini Daha İyi Anlayacak
Yeni bir araştırma, yüksek hızlı görüntü işleme tekniklerinin, robotların daha önce görmediği veya etiketlenmemiş insan eylemlerini anlama yeteneğini önemli ölçüde geliştirdiğini ortaya koyuyor. Bu sayede, robotlar karmaşık ve hızlı insan etkileşimlerine daha etkin bir şekilde adapte olabilecek.
Robotlar Artık Daha Hassas ve Hızlı: Yeni Yöntem İki Kollu İşlemlerde Çığır Açıyor
Yeni geliştirilen MSACT yöntemi, robotların hassas manipülasyon görevlerinde daha düşük gecikme süresi ve daha kararlı görsel konumlandırma sağlayarak, iki kollu robotların gerçek dünya uygulamalarındaki performansını önemli ölçüde artırıyor.
Mobil Robotlar İçin Yeni Bir Görsel Zeka: Ölçek Değişimine Dayanıklı Manipülasyon
Mobil robotların gerçek dünya ortamlarında nesneleri algılaması ve manipüle etmesi, kamera açılarındaki değişimler nedeniyle zorlaşır. Yeni bir derin öğrenme yöntemi, bu görsel ölçek değişimlerine rağmen robotların gerçek zamanlı ve hassas görevleri yerine getirmesini sağlıyor.