


Tesla RobotOptimusThe latest video is released, and it can already work in the factory.
At normal speed, it sorts batteries (Tesla’s 4680 battery) like this:
The official also released the video at 20x speed - picking and picking and picking at the small "work station":
The video released this time One of the highlights is that Optimus completes this work in the factory, completely autonomously, without human intervention throughout the process. And from the perspective of Optimus, it can also pick up and place the crooked battery, featuring an
automatic error correction:
Regarding Optimus’s hand
Jim Fan gave a high evaluation:
MuskNot only does its hand have tactile sensing, but it also has 11 degrees of freedom
(DoF), while its peers basically only have 5-6 degrees of freedom. And is durable enough to withstand a lot of object interaction without constant maintenance.
And in Jim Fan’s comment area,
also appeared and revealed a more important news:
Later this year At that time, theOptimus hand's degree of freedom will reach 22!
However, the video showing Optimus sorting its own batteries is just an "appetizer".
This time, Tesla rarely announced the details of robot training.
Similar logic to Tesla cars
First of all, in terms of neural networks, we can know from the subtitles in the video that Tesla deployed a
end-to-end End-to-end neural networkis used to train the task of sorting batteries. Because of this, the data used by Optimus only comes from the 2D camera and the tactile and force sensors of the hand, and directly generates joint control sequences.
Tesla engineer
further revealed that this neural network runs entirely on the robot’s embedded FSD computer and is powered by an onboard battery. Powered by:
A single neural network can perform multiple tasks as we add more diverse data during training.In terms of training data, we can see that humans wear VR glasses and gloves and collect it through remote operation:
Regarding this point, Jim Fan believes:
It is very important to set up the software for first-person video streaming input and precise control of the streaming output while maintaining extremely low latency.
This is because humans are very sensitive to even the smallest delay between their own movements and those of the robot.
And Optimus happens to have a fluid full-body controller that can perform human poses in real time.
And Tesla Robot has extended this model to other tasks:
Such a scale is also what shocked Jim Fan:
To collect data in parallel, one robot is not enough, and humans have to work in shifts every day.
An operation of this scale may be unimaginable in an academic laboratory.
Not only that, judging from the tasks Optimus are performing in the video, they are also diverse, including sorting batteries, folding clothes, and organizing items.
Milan Kovac said Tesla has deployed several robots in one of its factories, and they are being tested and continuously improved at real workstations every day.
# In short, Optimus trains based solely on vision and human demonstration, which is somewhat similar to the logic of Tesla cars.
At the end of the video, the official also revealed another improvement in Optimus' abilities - can go further:
One More Thing
Jim Fan's laboratory has also released a new development in the past two days-
Let the robot dog walk on the yoga ball!
Its training method is completely different from Tesla Optimus. It is completely conducted in a simulation environment, and then migrated to the real world with zero samples, without fine-tuning, and runs directly .
The specific technology behind it is the team’s newly launched DrEureka, which is based on Eureka, the technology behind the previous five-finger robot pen-turning machine.
DrEureka is an LLM agent that can write code to train robots’ skills in simulations and write more code to bridge the difficult gap between simulations and reality.
In short, it completely automates the process from new skill learning to real-world deployment.
Remote Operation is a necessary but not sufficient condition for solving humanoid robot problems. Fundamentally, it doesn't scale.And some netizens agreed with this:
The above is the detailed content of Tesla robots work in factories, Musk: The degree of freedom of hands will reach 22 this year!. For more information, please follow other related articles on the PHP Chinese website!

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

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

“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

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,

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

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

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

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


Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

AI Hentai Generator
Generate AI Hentai for free.

Hot Article

Hot Tools

EditPlus Chinese cracked version
Small size, syntax highlighting, does not support code prompt function

Safe Exam Browser
Safe Exam Browser is a secure browser environment for taking online exams securely. This software turns any computer into a secure workstation. It controls access to any utility and prevents students from using unauthorized resources.

Dreamweaver CS6
Visual web development tools

SublimeText3 Linux new version
SublimeText3 Linux latest version

mPDF
mPDF is a PHP library that can generate PDF files from UTF-8 encoded HTML. The original author, Ian Back, wrote mPDF to output PDF files "on the fly" from his website and handle different languages. It is slower than original scripts like HTML2FPDF and produces larger files when using Unicode fonts, but supports CSS styles etc. and has a lot of enhancements. Supports almost all languages, including RTL (Arabic and Hebrew) and CJK (Chinese, Japanese and Korean). Supports nested block-level elements (such as P, DIV),
