您现在的位置是:MIT AI system enhances household robots’ problem solving skills >>正文
MIT AI system enhances household robots’ problem solving skills
上海品茶网 - 夜上海最新论坛社区 - 上海千花论坛18人已围观
简介By subscribing, you agree to our Terms of Use and Policies You may unsubscribe at any time.MIT resea...
By subscribing, you agree to our Terms of Use and Policies You may unsubscribe at any time.
MIT researchers have developed PIGINet, a new system that aims to efficiently enhance the problem-solving capabilities of household robots, reducing planning time by 50-80 percent.
This is according to a press release by the institution published on Friday.
Under normal conditions, household robots follow predefined recipes for performing tasks, which isn’t always suitable for diverse or changing environments. PIGINet, as described by MIT, is a neural network that takes in “Plans, Images, Goal, and Initial facts,” then predicts the probability that a task plan can be refined to find feasible motion plans.
The team evaluated the new system’s ability in helping a robot function in the kitchen. They measured the time taken to solve problems with PIGINet’s assistance against prior approaches.
See Also Related- This robot butler will tackle all your household chores
- Elon Musk: There will likely be a humanoid robot in every home by 2050
- Where are all the personal robots we were promised?
They found that PIGINet significantly reduced planning time by 80 percent in simpler scenarios and 20-50 percent in more complex scenarios.
“Systems such as PIGINet, which use the power of data-driven methods to handle familiar cases efficiently, but can still fall back on “first-principles” planning methods to verify learning-based suggestions and solve novel problems, offer the best of both worlds, providing reliable and efficient general-purpose solutions to a wide variety of problems,” said MIT Professor and CSAIL Principal Investigator Leslie Pack Kaelbling.
The researchers also made use of pretrained vision language models and data augmentation tricks to deal with the scarcity of good training data for the household robots.
“Because everyone’s home is different, robots should be adaptable problem-solvers instead of just recipe followers. Our key idea is to let a general-purpose task planner generate candidate task plans and use a deep learning model to select the promising ones. The result is a more efficient, adaptable, and practical household robot, one that can nimbly navigate even complex and dynamic environments. Moreover, the practical applications of PIGINet are not confined to households,” said Zhutian Yang, MIT CSAIL PhD student and lead author on the work.
“Our future aim is to further refine PIGINet to suggest alternate task plans after identifying infeasible actions, which will further speed up the generation of feasible task plans without the need of big datasets for training a general-purpose planner from scratch. We believe that this could revolutionize the way robots are trained during development and then applied to everyone’s homes.”
“This paper addresses the fundamental challenge in implementing a general-purpose robot: how to learn from past experience to speed up the decision-making process in unstructured environments filled with a large number of articulated and movable obstacles,” said in the statement Beomjoon Kim PhD ’20, assistant professor in the Graduate School of AI at Korea Advanced Institute of Science and Technology (KAIST).
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/719485.html
相关文章
CES 2023: A truly wireless TV with rechargeable batteries and vacuum lock
MIT AI system enhances household robots’ problem solving skillsBy subscribing, you agree to our Terms of Use and Policies You may unsubscribe at any time.Imagine a...
阅读更多
This bioinspired seed carrier has an 80 percent success rate
MIT AI system enhances household robots’ problem solving skillsBy subscribing, you agree to our Terms of Use and Policies You may unsubscribe at any time.Researche...
阅读更多
Wrapped Bitcoin contributes to Bitcoin's current rally
MIT AI system enhances household robots’ problem solving skillsThe Bitcoin price has been rallying in recent weeks, and one of the significant contributors are wra...
阅读更多
热门文章
- CES 2024: Kohler's latest bidet brings Alexa and Google to your buttocks
- As the Sandbox usage slows, is Memeinator the next big thing?
- Mastercard's new anti
- ETH price has hit its highest price level in 30 months
- This new bifacial solar cell tech can deliver 3X power!
- How can blockchain be integrated with mobile applications