您现在的位置是:Berkeley researchers build humanoid that taught itself to walk >>正文
Berkeley researchers build humanoid that taught itself to walk
上海品茶网 - 夜上海最新论坛社区 - 上海千花论坛975人已围观
简介By subscribing, you agree to our Terms of Use and Policies You may unsubscribe at any time.Researche...
By subscribing, you agree to our Terms of Use and Policies You may unsubscribe at any time.
Researchers at the University of California, Berkeley, have built a human-sized bot that uses artificial intelligence (AI) techniques to teach itself how to walk in the physical world.
The teal-colored bot has been roaming around the varied terrains on campus with quite some ease but hasn't quite learned to navigate steps yet.
Humanoid robots are touted as the next big thing in robotics thanks to their ability to operate in various environments at home or in factories. It is hardly a surprise that multiple companies are building them. However, for the robot to be truly effective, it must adapt to changing environments and needs.
See Also Related- Meet Mugatu: A steerable bipedal robot with a single motor
- Watch 'world's most powerful' humanoid robot withstand brutal kicks
- Watch ChatGPT-powered humanoid robot pose funny, play terrifying ghost
UC researchers Ilija Radosavovic and Bike Zhang wondered if "reinforcement learning," a concept made popular by large language models (LLMs) last year, could also teach the robot how to adapt to changing needs. To test their theory, the duo started with one of the most basic functions humans can perform - walking.
Transformer model for learning
The researchers started in the simulation world, running billions of scenarios in Isaac Gym, a high-performance GPU-based physics simulation environment. The algorithm in the simulator rewarded actions that mimicked human-like walking while punishing the ones that didn't. Once the simulation perfected the task, it was transferred to a real-world humanoid bot that did not require further fine-tuning.
The learning system's core is a deep-learning model, now popular as a transformer. The model has been extensively used in LLMs to predict the next element in a series of data sequences. Since the researchers were interested in walking, they deployed a causal transformer that learns from observations and actions and predicts the consequences of actions instead.
This is how the humanoid adjusts its actions in a new landscape, even though it has never encountered it.
we have trained a humanoid transformer with large-scale reinforcement learning in simulation and deployed it to the real world zero-shot pic.twitter.com/WzOIMQXTaD
— Ilija Radosavovic (@ir413) December 10, 2023
How well does the humanoid walk?
Over the past year, the humanoid has strutted around the UC campus, navigating through its patches of grass and roads. Interestingly, the researchers noticed that the humanoid had picked up "emergent" traits that weren't intentional parts of the algorithm.
For instance, the humanoid swings its left arm while putting its right foot forward or takes smaller steps to balance itself while walking down the slopes, much like how humans do. While this might not sound revolutionary, it is still impressive, considering that it does not possess any sensors that help it perceive its environment.
This is likely the reason why the robot cannot navigate steps for now. But its extensive learning ability has made it resilient enough to maintain its balance, even when the researchers poked it with large sticks or threw exercise balls at the robot.
There are areas for improvement as well. The gait of the humanoid isn't as refined as that of a human and comes across as jerky. When the metal bot's foot hits harder material like concrete or asphalt, it resembles a military march. The worst, however, is the robot does not know it will run into an obstacle until it hits it.
These are things that the researchers plan to work on next. While it might be far away from being an ideal factory or home bot, it is still a good start for a self-learning humanoid.
Tags:
转载:欢迎各位朋友分享到网络,但转载请说明文章出处“上海品茶网 - 夜上海最新论坛社区 - 上海千花论坛”。http://www.jz08.com.cn/news/7768.html
相关文章
Bitcoin hard forks, Bitcoin Cash and Bitcoin SV in the spotlight with double
Berkeley researchers build humanoid that taught itself to walkAt press time, BCH price had risen by 52% in the last seven days and 28% in the last 24 hours.BSV, o...
阅读更多
Chancer could be the next big thing in sports and social betting
Berkeley researchers build humanoid that taught itself to walkCryptocurrenciesand stocks had a mixed performance this week as the corporate earnings season contin...
阅读更多
Shiba Inu price outlook as Shiba Memu’s presale tops $2.2M
Berkeley researchers build humanoid that taught itself to walkKey takeawaysThe broader crypto market rallied over the last 24 hours, but Shiba Inu continues to un...
阅读更多
热门文章
- Showing the colored world of animals via a new camera system
- SEC rejects Ark21Shares spot Bitcoin ETF for the second time
- Google & Ambient signal shift to sustainable electronics era
- Bitcoin could hit $120,000 by the end of 2024: Standard Chartered
- Neural Lab’s air gesture technology could be a game
- Chainlink price prediction: LINK just formed a double top pattern
最新文章
North Korea hackers may try to sell $40M in Bitcoin, FBI says
Shiba Memu token is thriving despite the painful crypto sell
XDC price prediction as coin rallies by 31% in a week
Crypto price prediction for BNB (BNB) and Dogecoin (DOGE)
zkSync Era protocol Kannagi Finance latest crypto rugpull
BNB price declines 10% amid negative news around BUSD