Placeholder Image

字幕列表 影片播放

由 AI 自動生成
  • China's Qinglong full-sized general-purpose humanoid robot was just released at the 2024 World Artificial Intelligence Conference, showcasing dexterous task completion by voice instruction.

    中國的青龍全尺寸通用仿人機器人剛剛在 2024 年世界人工智能大會上發佈,展示了通過語音指令完成靈巧任務的能力。

  • But there's a twist.

    但有一個轉折。

  • This is because Qinglong is an open-source humanoid for China's attempt at creating a worldwide development ecosystem from within the existing robotics and AI communities.

    因為 "青龍 "是一個開放源代碼的仿人機器人,中國試圖在現有的機器人和人工智能社區內創建一個世界性的開發生態系統。

  • To this end, the national-local Joint Humanoid Robot Innovation Center showcased its progress building the robot's capabilities and design concepts in a live demonstration.

    為此,國家-地方仿人機器人聯合創新中心在一次現場演示中展示了其在構建機器人能力和設計理念方面取得的進展。

  • And as for its specifications, Qinglong stands at 185 centimeters tall and weighs 80 kilograms.

    至於它的規格,"青龍 "身高 185 釐米,體重 80 千克。

  • It features a highly bionic torso and anthropomorphic motion control, enabling multimodal mobility, perception, interaction, and manipulation.

    它具有高度仿生的軀幹和擬人化的運動控制,可實現多模態移動、感知、交互和操縱。

  • With 43 active degrees of freedom, Qinglong has a maximum joint peak torque of 200 newton meters per kilogram and computational power of 400 tera operations per second.

    青龍 "具有 43 個主動自由度,最大關節峰值扭矩為每公斤 200 牛頓米,計算能力為每秒 400 太赫茲。

  • Its battery has a capacity of 2,052 watt-hours to power its 360-degree LiDAR system.

    其電池容量為 2,052 瓦時,可為 360 度激光雷達系統供電。

  • In terms of performance, the robot's design integrates lightweight legs for agile walking and high-precision arms for dexterous tasks.

    在性能方面,機器人的設計集成了輕便的腿部和高精度的手臂,前者可實現靈活行走,後者可完成靈巧的任務。

  • As a result, Qinglong can walk rapidly around obstacles, move stably on inclines and declines, and even resist impact interference.

    是以,"青龍 "可以繞過障礙物快速行走,在斜坡和下坡上穩定移動,甚至可以抵禦衝擊干擾。

  • These features are to assist in making it an open platform for developing general artificial intelligence software and hardware for robots.

    這些功能有助於使其成為一個開放平臺,用於開發機器人的通用人工智能軟件和硬件。

  • Next, in terms of development, Qinglong is a creation of Humanoid Robots Shanghai Limited, an R&D institution backed by leading industry enterprises with approximately 140 million USD in funding.

    其次,在研發方面,"青龍 "由上海仿人機器人有限公司創建,該公司是一家由行業領先企業支持的研發機構,擁有約 1.4 億美元的資金。

  • In the future, the team aims to introduce a new humanoid robot model annually, each named after one of the Chinese zodiac animals, with the name Qinglong meaning green dragon.

    今後,該團隊計劃每年推出一個新的仿人機器人模型,每個模型都以中國十二生肖之一命名,"青龍 "就是青龍的意思。

  • This is all with the end goal to build an open-source humanoid robot development community in China and beyond.

    這一切的最終目標是在中國和其他地區建立一個開源的仿人機器人開發社區。

  • Additionally, the team also revealed the launch of the OpenLung open-source community as a platform to provide access to Qinglong's hardware structure and parameters, with the robot's embodied intelligence software packages to be open-sourced.

    此外,該團隊還透露將推出 OpenLung 開源社區,作為提供青龍機器人硬件結構和參數訪問權限的平臺,並將開放機器人的體現智能套裝軟體。

  • By creating an open-source culture, this initiative hopes to create a collaborative environment for the development of humanoid robotics worldwide.

    通過創建開源文化,該倡議希望為全球仿人機器人技術的發展創造一個合作環境。

  • But Qinglong was only one of the humanoids at the World Artificial Intelligence Conference, with Tesla's Optimus Gen 2 also being showcased for the very first time in public for this event.

    不過,"青龍 "只是世界人工智能大會上的人形機器人之一,特斯拉的 "擎天柱 2 代 "也是在這次大會上首次公開亮相。

  • The Tesla team highlighted significant advancements in weight reduction, flexibility and functionality, capturing the attention of AI enthusiasts and industry experts alike.

    特斯拉團隊重點介紹了在減重、靈活性和功能性方面取得的重大進展,吸引了人工智能愛好者和行業專家的關注。

  • Key improvements are its in-house components, including actuators and sensors that were entirely designed and manufactured by Tesla, ensuring superior integration and performance.

    改進的關鍵在於其內部組件,包括完全由特斯拉設計和製造的致動器和傳感器,從而確保了卓越的集成性和性能。

  • Additionally, with a 30% increase in walking speed, Optimus Gen 2 can now operate even more efficiently.

    此外,由於行走速度提高了 30%,Optimus Gen 2 現在可以更加高效地運行。

  • Furthermore, the robot is 10 kilograms lighter than its predecessor, resulting in improved balance and battery lifespan.

    此外,該機器人比上一代產品輕 10 千克,從而提高了平衡性和電池壽命。

  • Plus, its new hands are capable of gripping heavier objects and performing delicate tasks that expand the robot's range of potential applications.

    此外,它的新雙手還能抓取較重的物體並執行精細的任務,從而擴大了機器人的潛在應用範圍。

  • And with all of this progress, Tesla plans to deploy Optimus Gen 2 in its own manufacturing factories to test the robot's practicality first.

    在取得這些進展的同時,特斯拉計劃在自己的製造工廠部署 Optimus Gen 2,首先測試機器人的實用性。

  • This initial phase will allow the company to fine-tune the robot's capabilities in a controlled environment, and once proven effective, Tesla will then begin commercial sales of the robot, making it available to a broader market sometime in 2025.

    這一初始階段將使公司能夠在受控環境中對機器人的能力進行微調,一旦證明有效,特斯拉將開始對機器人進行商業銷售,在 2025 年的某個時候向更廣泛的市場推出機器人。

  • But how can these robots quickly learn thousands of dexterous tasks to work with their human-like hands, you ask?

    但是,你要問,這些機器人如何能快速學會數千種靈巧的任務,用它們那雙像人類一樣的手來工作?

  • To this end, Meta just introduced a new dataset named HOT3D to advance artificial intelligence research in the realm of 3D hand-object interactions.

    為此,Meta 剛剛推出了一個名為 HOT3D 的新數據集,以推進三維手與物體交互領域的人工智能研究。

  • This extensive dataset comprises over one million frames captured from multiple perspectives, offering a rich resource for researchers delving into the complexities of how humans manipulate objects with their hands.

    這個龐大的數據集包括從多個角度捕捉的 100 多萬幀影像,為研究人員深入探討人類如何用手操作物體的複雜性提供了豐富的資源。

  • According to Meta, understanding these interactions remains a crucial challenge in computer vision research.

    Meta 認為,理解這些交互作用仍然是計算機視覺研究中的一項重要挑戰。

  • And the HOT3D dataset is a treasure trove of over 800 minutes of egocentric video recordings, with these recordings being synchronized across multiple perspectives and including high-quality 3D pose annotations for both hands and objects.

    HOT3D 數據集是一個由 800 多分鐘自我中心視頻記錄組成的寶庫,這些記錄在多個視角下同步進行,其中包括手和物體的高質量三維姿態註釋。

  • The dataset also features 3D object models, with physically-based rendering materials, 2D bounding boxes, gaze signals, and 3D scene-point clouds generated from simultaneous localization and mapping techniques.

    該數據集還包括三維物體模型、基於物理的渲染材料、二維邊界框、注視信號以及由同步定位和繪圖技術生成的三維場景點雲。

  • Impressively, this dataset encapsulates interactions from 19 subjects handling 33 common household objects, with scenarios ranging from simple activities, such as picking up and examining are typical in kitchen, office, and living room environments.

    令人印象深刻的是,該數據集囊括了 19 名受試者在處理 33 件常見家用物品時的交互行為,場景包括廚房、辦公室和客廳環境中典型的拿起和檢查等簡單活動。

  • And in another breakthrough, a new text to video competitor named Kling just launched its web version.

    另一項突破是,一家名為 Kling 的新文字轉視頻競爭對手剛剛推出了網絡版。

  • This allows users to generate videos up to 10 seconds long, with the enhanced model providing control over camera movements such as panning, tilting, and zooming, giving creators more flexibility and creativity.

    這使用戶能夠製作長達 10 秒的視頻,增強的型號還能控制攝影機的移動,如平移、傾斜和縮放,為創作者提供了更大的靈活性和創造力。

  • Users can also freely create up to three 10-second videos per day using the enhanced model, making it accessible to a wide audience.

    用戶還可以使用增強型模式每天自由製作最多三段 10 秒鐘的視頻,使廣大閱聽人都能使用。

  • The only catch is that currently a Chinese cell phone number is still required to register with Kling, even for the web version.

    唯一的問題是,目前在 Kling 註冊仍然需要中國手機號碼,即使是網絡版也不例外。

  • Finally, Meta has announced their breakthrough AI system named 3DGen that's capable of generating high-quality 3D objects from simple text descriptions in less than one minute.

    最後,Meta 公司發佈了名為 3DGen 的突破性人工智能系統,該系統能夠在一分鐘內根據簡單的文字描述生成高質量的 3D 物體。

  • This innovation will likely revolutionize the creation of 3D content, making it faster and more accessible than ever before.

    這一創新可能會徹底改變 3D 內容的創作,使其比以往任何時候都更快、更易獲得。

  • In fact, 3DGen leverages the power of not one, but two of Meta's existing models, AssetGen and TextureGen.

    事實上,3DGen 利用了 Meta 現有的兩個模型,即 AssetGen 和 TextureGen。

  • AssetGen is responsible for generating the initial 3D objects, while TextureGen handles the texturing process.

    AssetGen 負責生成初始三維對象,而 TextureGen 則處理紋理製作過程。

  • By integrating these models, Meta has created a system that produces superior 3D objects efficiently, enhancing the quality of immersive content creation.

    通過整合這些模型,Meta 創建了一個系統,可以高效地生成卓越的 3D 物體,從而提高身臨其境的內容創作品質。

  • The operation of 3DGen involves two key steps.

    3DGen 的運行涉及兩個關鍵步驟。

  • In the first step, AssetGen creates a 3D object complete with texture and physical-based rendering from a text description in approximately 30 seconds.

    第一步,AssetGen 可在大約 30 秒內根據文字描述創建一個 3D 物體,並提供紋理和基於物理的渲染。

  • This rapid generation sets the stage for high-quality asset creation.

    這種快速生成為高質量的資產創造奠定了基礎。

  • In the second step, TextureGen can either refine the texture of the object generated in the first step based on the original description, or create a texture for any unstructured 3D mesh using new specifications.

    在第二步中,TextureGen 可以根據原始描述完善第一步中生成的對象紋理,也可以使用新的規範為任何非結構化三維網格創建紋理。

  • This process takes about 20 seconds per object.

    每個對象的處理過程大約需要 20 秒鐘。

  • Thanks to PBR support, the generated assets can be relit, adding another layer of realism and versatility.

    由於支持 PBR,生成的資產可以重新點亮,從而又增加了一層真實感和多功能性。

  • Both stages of 3DGen are built upon Meta's text-to-image models from the EMU family.

    3DGen 的兩個階段都建立在 Meta 的 EMU 系列文本到影像模型的基礎上。

  • These models are optimized with synthetic 3D data to enable multi-view generation in both image and UV space, which significantly enhances the texture quality of the final product.

    這些模型通過合成三維數據進行優化,能夠在影像和 UV 空間中生成多視圖,從而顯著提高最終產品的紋理品質。

  • According to Meta, 3DGen not only outpaces existing methods, but also delivers superior results.

    據 Meta 公司稱,3DGen 不僅超越了現有的方法,而且還能提供卓越的效果。

  • User studies have shown that professional 3D artists prefer 3DGen over leading industry solutions, particularly for complex tasks.

    用戶研究表明,與業界領先的解決方案相比,專業 3D 藝術家更喜歡 3DGen,尤其是在複雜任務方面。

  • Meta claims that 3DGen is three to sixty times faster than comparable systems, a significant leap that could drastically reduce the time and effort required for 3D content creation.

    Meta 聲稱,3DGen 的速度比同類系統快三到六十倍,這是一個重大的飛躍,可以大大減少 3D 內容創建所需的時間和精力。

  • Overall, Meta envisions 3DGen as a pivotal step toward a future where personalized, user-generated 3D content becomes commonplace.

    總之,Meta 認為 3DGen 是邁向未來的關鍵一步,在未來,個性化、用戶生成的 3D 內容將變得非常普遍。

  • The system's ability to quickly and accurately generate high-quality 3D objects from text descriptions opens up numerous possibilities.

    該系統能夠根據文字描述快速準確地生成高質量的 3D 物體,這為我們帶來了無限可能。

  • AI-assisted 3D creation tools could enable users to build intricate virtual worlds in the metaverse, offering new opportunities for creativity and interaction.

    人工智能輔助三維創作工具可以讓用戶在元宇宙中構建錯綜複雜的虛擬世界,為創造力和互動提供新的機會。

  • AI itself could even use this same tech in the future to create video games in real time, but that's for another video.

    未來,人工智能本身甚至可以利用同樣的技術實時創建視頻遊戲,但這是另一個視頻的內容。

China's Qinglong full-sized general-purpose humanoid robot was just released at the 2024 World Artificial Intelligence Conference, showcasing dexterous task completion by voice instruction.

中國的青龍全尺寸通用仿人機器人剛剛在 2024 年世界人工智能大會上發佈,展示了通過語音指令完成靈巧任務的能力。

字幕與單字
由 AI 自動生成

單字即點即查 點擊單字可以查詢單字解釋