search
HomeTechnology peripheralsAIAfter two and a half years of practice, the second generation of Tesla's humanoid robot Optimus is online

The second generation of Tesla humanoid robot "Optimus" suddenly appeared without any advance notice

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

On the morning of December 13th , Musk suddenly released a video on the .

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is onlineIt took two and a half years of training from conception to toddlerhood to triggering the uncanny valley effect. Optimus’s appearance this time stunned the world.

Under Musk’s tweet, people expressed their welcome and expectations. Some people couldn’t wait to ask: “When can I buy it?” Significant improvements include:

Actuators and sensors designed by Tesla

2-Dof (degrees of freedom ) of the neck

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

Walking speed increased by 30%

    Weight reduced by 10 kg
  • Foot strength/ Torque Sensing
  • Articulated Toe Section
  • Human Foot Geometry
  • Faster , 11-DoF new hands
  • ## Judging from the picture, Optimus Gen2 has flexible hands, the fingers can be stretched as flexibly as a real person, and the 2-degree-of-freedom neck can make the robot Turn your head within a certain range:
  • Although the walking speed has increased by 30%, it still looks a bit slow

However, judging from the close-ups of the feet and legs, Optimus Gen2's feet are very similar to humans, and the way they walk is similar to humans.

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

In addition, the new generation of Optimus Gen2 is lighter than its predecessor. Even if it is 10 kg lighter, it will not affect other performance

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

#It can even do an even 90-degree squat. Doing this action requires mobilizing multiple joints throughout the body to maintain balance.

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

Optimus Gen2 is also equipped with a brand new hand, which has 11 degrees of freedom and is very dexterous to move.

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

All fingers are tactile and can handle delicate objects such as eggs. The right side of the screen displays finger pressure in real time

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

At the end of the video, you can see the Tesla robot Dance to the music.

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

Importantly, Milan Kovac from Tesla's AI team said: Everything in the video is real-time (1x speed), there is no CGI. Is this cue Google?

It seems that Optimus Gen2 has made great progress compared to the previous generation. It seems that we are not far away from the idea of ​​having a robot butler?

Tesla Humanoid Robot "Evolutionary History"

Tesla humanoid robot first originated from "Tesla" in August 2021 AI Day" event, at that time Musk disclosed for the first time his vision for manufacturing a humanoid robot (Tesla robot)

This humanoid robot is about 1.72 meters tall and weighs about 112 meters Jin, well-proportioned, and equipped with a facial screen that can move at a speed of about 8 kilometers per hour

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

##2022 In October 2019, at this year’s “Tesla AI Day”, the Optimus humanoid robot made its debut. At that time, it could not perform dance and other fancy performances. The robot consumes 500W of power when working, weighs 73 kilograms, and has 27 degrees of freedom for hand movement.

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

However, in the demo, Optimus showed it carrying boxes, watering and working in the Tesla Gigafactory

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

In May of this year, after half a year of waiting, Tesla’s Optimus was finally able to walk smoothly and grab objects

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

#In September, Tesla Optimus evolved again and can classify objects autonomously. The highlight is the complete end-to-end training of the neural network: input video, output control. In his spare time, he can also do yoga for fun.

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

Now, with the arrival of the second generation of Optimus, Tesla’s humanoid robots are progressing at a terrifying rate .

After two and a half years of practice, the second generation of Teslas humanoid robot Optimus is online

Source: https://twitter.com/AdrianDittmann/status/1734758246991405426

Indeed It looks a bit like the movie "Mechanical Enemy". I hope Musk can hold it.

The above is the detailed content of After two and a half years of practice, the second generation of Tesla's humanoid robot Optimus is online. For more information, please follow other related articles on the PHP Chinese website!

Statement
This article is reproduced at:51CTO.COM. If there is any infringement, please contact admin@php.cn delete
从VAE到扩散模型:一文解读以文生图新范式从VAE到扩散模型:一文解读以文生图新范式Apr 08, 2023 pm 08:41 PM

1 前言在发布DALL·E的15个月后,OpenAI在今年春天带了续作DALL·E 2,以其更加惊艳的效果和丰富的可玩性迅速占领了各大AI社区的头条。近年来,随着生成对抗网络(GAN)、变分自编码器(VAE)、扩散模型(Diffusion models)的出现,深度学习已向世人展现其强大的图像生成能力;加上GPT-3、BERT等NLP模型的成功,人类正逐步打破文本和图像的信息界限。在DALL·E 2中,只需输入简单的文本(prompt),它就可以生成多张1024*1024的高清图像。这些图像甚至

找不到中文语音预训练模型?中文版 Wav2vec 2.0和HuBERT来了找不到中文语音预训练模型?中文版 Wav2vec 2.0和HuBERT来了Apr 08, 2023 pm 06:21 PM

Wav2vec 2.0 [1],HuBERT [2] 和 WavLM [3] 等语音预训练模型,通过在多达上万小时的无标注语音数据(如 Libri-light )上的自监督学习,显著提升了自动语音识别(Automatic Speech Recognition, ASR),语音合成(Text-to-speech, TTS)和语音转换(Voice Conversation,VC)等语音下游任务的性能。然而这些模型都没有公开的中文版本,不便于应用在中文语音研究场景。 WenetSpeech [4] 是

普林斯顿陈丹琦:如何让「大模型」变小普林斯顿陈丹琦:如何让「大模型」变小Apr 08, 2023 pm 04:01 PM

“Making large models smaller”这是很多语言模型研究人员的学术追求,针对大模型昂贵的环境和训练成本,陈丹琦在智源大会青源学术年会上做了题为“Making large models smaller”的特邀报告。报告中重点提及了基于记忆增强的TRIME算法和基于粗细粒度联合剪枝和逐层蒸馏的CofiPruning算法。前者能够在不改变模型结构的基础上兼顾语言模型困惑度和检索速度方面的优势;而后者可以在保证下游任务准确度的同时实现更快的处理速度,具有更小的模型结构。陈丹琦 普

解锁CNN和Transformer正确结合方法,字节跳动提出有效的下一代视觉Transformer解锁CNN和Transformer正确结合方法,字节跳动提出有效的下一代视觉TransformerApr 09, 2023 pm 02:01 PM

由于复杂的注意力机制和模型设计,大多数现有的视觉 Transformer(ViT)在现实的工业部署场景中不能像卷积神经网络(CNN)那样高效地执行。这就带来了一个问题:视觉神经网络能否像 CNN 一样快速推断并像 ViT 一样强大?近期一些工作试图设计 CNN-Transformer 混合架构来解决这个问题,但这些工作的整体性能远不能令人满意。基于此,来自字节跳动的研究者提出了一种能在现实工业场景中有效部署的下一代视觉 Transformer——Next-ViT。从延迟 / 准确性权衡的角度看,

Stable Diffusion XL 现已推出—有什么新功能,你知道吗?Stable Diffusion XL 现已推出—有什么新功能,你知道吗?Apr 07, 2023 pm 11:21 PM

3月27号,Stability AI的创始人兼首席执行官Emad Mostaque在一条推文中宣布,Stable Diffusion XL 现已可用于公开测试。以下是一些事项:“XL”不是这个新的AI模型的官方名称。一旦发布稳定性AI公司的官方公告,名称将会更改。与先前版本相比,图像质量有所提高与先前版本相比,图像生成速度大大加快。示例图像让我们看看新旧AI模型在结果上的差异。Prompt: Luxury sports car with aerodynamic curves, shot in a

五年后AI所需算力超100万倍!十二家机构联合发表88页长文:「智能计算」是解药五年后AI所需算力超100万倍!十二家机构联合发表88页长文:「智能计算」是解药Apr 09, 2023 pm 07:01 PM

人工智能就是一个「拼财力」的行业,如果没有高性能计算设备,别说开发基础模型,就连微调模型都做不到。但如果只靠拼硬件,单靠当前计算性能的发展速度,迟早有一天无法满足日益膨胀的需求,所以还需要配套的软件来协调统筹计算能力,这时候就需要用到「智能计算」技术。最近,来自之江实验室、中国工程院、国防科技大学、浙江大学等多达十二个国内外研究机构共同发表了一篇论文,首次对智能计算领域进行了全面的调研,涵盖了理论基础、智能与计算的技术融合、重要应用、挑战和未来前景。论文链接:​https://spj.scien

​什么是Transformer机器学习模型?​什么是Transformer机器学习模型?Apr 08, 2023 pm 06:31 PM

译者 | 李睿审校 | 孙淑娟​近年来, Transformer 机器学习模型已经成为深度学习和深度神经网络技术进步的主要亮点之一。它主要用于自然语言处理中的高级应用。谷歌正在使用它来增强其搜索引擎结果。OpenAI 使用 Transformer 创建了著名的 GPT-2和 GPT-3模型。自从2017年首次亮相以来,Transformer 架构不断发展并扩展到多种不同的变体,从语言任务扩展到其他领域。它们已被用于时间序列预测。它们是 DeepMind 的蛋白质结构预测模型 AlphaFold

AI模型告诉你,为啥巴西最可能在今年夺冠!曾精准预测前两届冠军AI模型告诉你,为啥巴西最可能在今年夺冠!曾精准预测前两届冠军Apr 09, 2023 pm 01:51 PM

说起2010年南非世界杯的最大网红,一定非「章鱼保罗」莫属!这只位于德国海洋生物中心的神奇章鱼,不仅成功预测了德国队全部七场比赛的结果,还顺利地选出了最终的总冠军西班牙队。不幸的是,保罗已经永远地离开了我们,但它的「遗产」却在人们预测足球比赛结果的尝试中持续存在。在艾伦图灵研究所(The Alan Turing Institute),随着2022年卡塔尔世界杯的持续进行,三位研究员Nick Barlow、Jack Roberts和Ryan Chan决定用一种AI算法预测今年的冠军归属。预测模型图

See all articles

Hot AI Tools

Undresser.AI Undress

Undresser.AI Undress

AI-powered app for creating realistic nude photos

AI Clothes Remover

AI Clothes Remover

Online AI tool for removing clothes from photos.

Undress AI Tool

Undress AI Tool

Undress images for free

Clothoff.io

Clothoff.io

AI clothes remover

AI Hentai Generator

AI Hentai Generator

Generate AI Hentai for free.

Hot Article

R.E.P.O. Energy Crystals Explained and What They Do (Yellow Crystal)
3 weeks agoBy尊渡假赌尊渡假赌尊渡假赌
R.E.P.O. Best Graphic Settings
3 weeks agoBy尊渡假赌尊渡假赌尊渡假赌
R.E.P.O. How to Fix Audio if You Can't Hear Anyone
3 weeks agoBy尊渡假赌尊渡假赌尊渡假赌

Hot Tools

Dreamweaver CS6

Dreamweaver CS6

Visual web development tools

MantisBT

MantisBT

Mantis is an easy-to-deploy web-based defect tracking tool designed to aid in product defect tracking. It requires PHP, MySQL and a web server. Check out our demo and hosting services.

ZendStudio 13.5.1 Mac

ZendStudio 13.5.1 Mac

Powerful PHP integrated development environment

Notepad++7.3.1

Notepad++7.3.1

Easy-to-use and free code editor

DVWA

DVWA

Damn Vulnerable Web App (DVWA) is a PHP/MySQL web application that is very vulnerable. Its main goals are to be an aid for security professionals to test their skills and tools in a legal environment, to help web developers better understand the process of securing web applications, and to help teachers/students teach/learn in a classroom environment Web application security. The goal of DVWA is to practice some of the most common web vulnerabilities through a simple and straightforward interface, with varying degrees of difficulty. Please note that this software