AI agents test and improve robot code in virtual worlds before deployment
AI agents test and improve robot code in virtual worlds before deployment
Researchers at UC Berkeley and NVIDIA introduce 'agentic robotics,' using AI agents to generate, simulate, and refine robot control programs via Graph-as-Policy and open benchmarks, reducing data needs and accelerating development; the method is demonstrated on a real robot and deployed in warehouse logistics.
Source: Robotics — Robot learning news discovery · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
packages sorted annually per robot
>15,000
View original evidence
s earlier this year to analyze parcel-sorting data and test updates to robot behavior. Tests showed an increased capacity of over 15,000 packages sorted annually per robot; the change is now deployed across 30% of the company's U.S. fleet. "AI-powered industrial robots must continuously improve reliability and performance," said Jeff Mahler, Ambi Robotics' co-founder and chief technology officer. "Agentic Robotics co
Open source S15robots in fleet
30
View original evidence
s earlier this year to analyze parcel-sorting data and test updates to robot behavior. Tests showed an increased capacity of over 15,000 packages sorted annually per robot; the change is now deployed across 30% of the company's U.S. fleet. "AI-powered industrial robots must continuously improve reliability and performance," said Jeff Mahler, Ambi Robotics' co-founder and chief technology officer. "Agentic Robotics co
Open source S15Reported trials
1 trials
Reported trials
View original evidence
ons of the sponge. The researchers then gave the AI that simulation and their Graph-as-Policy framework. The AI generated a robot-control program and repeatedly tested and improved it in simulation. When the researchers ran the resulting code on a real robot, it worked. In one trial, Goldberg said, the robot pushed over the metal bar because it did not reliably infer its mass. The misstep created new evidence for the
Open source S13robots deployed
30
View original evidence
s earlier this year to analyze parcel-sorting data and test updates to robot behavior. Tests showed an increased capacity of over 15,000 packages sorted annually per robot; the change is now deployed across 30% of the company's U.S. fleet. "AI-powered industrial robots must continuously improve reliability and performance," said Jeff Mahler, Ambi Robotics' co-founder and chief technology officer. "Agentic Robotics co
Open source S15
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
AI agents test and improve robot code in virtual worlds before deployment
Open source S1
s earlier this year to analyze parcel-sorting data and test updates to robot behavior. Tests showed an increased capacity of over 15,000 packages sorted annually per robot; the change is now deployed across 30% of the company's U.S. fleet. "AI-powered industrial robots must continuously improve reliability and performance," said Jeff Mahler, Ambi Robotics' co-founder and chief technology officer. "Agentic Robotics co
Open source S15
ra model made the process even more promising, Goldberg said. His postdoctoral students Eric Kaiyuan Chen and Shuangyu Xie gave Astra access to their simulation interface and a short video of a real robot whose assignment was using a sponge to wipe ink off a metal bar. In less than an hour, the AI tool created and fine-tuned a physics simulation that accurately reproduced the video, including very realistic deformati
Open source S12
ons of the sponge. The researchers then gave the AI that simulation and their Graph-as-Policy framework. The AI generated a robot-control program and repeatedly tested and improved it in simulation. When the researchers ran the resulting code on a real robot, it worked. In one trial, Goldberg said, the robot pushed over the metal bar because it did not reliably infer its mass. The misstep created new evidence for the
Open source S13
Source：Robotics — Robot learning news discovery · msn.com