
Princeton researchers have found that human-language descriptions of tools can accelerate the learning of a simulated robotic arm lifting and using a variety of tools. Animation by the researchers;
GIF by Neil Adelantar
Exploring a new way to teach robots, Princeton researchers have found that human-language descriptions of tools can accelerate the learning of a simulated robotic arm lifting and using a variety of tools.
The results build on evidence that providing richer information during artificial intelligence (AI) training can make autonomous robots more adaptive to new situations, improving their safety and effectiveness.
Adding descriptions of a tool’s form and function to the training process for the robot improved the robot’s ability to manipulate newly encountered tools that were not in the original training set. A team of mechanical engineers and computer scientists presented the new method, Accelerated Learning of Tool Manipulation with LAnguage, or ATLA, at the Conference on Robot Learning on Dec. 14.
Robotic arms have great potential to help with repetitive or challenging tasks, but training robots to manipulate tools effectively is difficult: Tools have a wide variety of shapes, and a robot’s dexterity and vision are no match for a human’s.
“Extra information in the form of language can help a robot learn to use the tools more quickly,” said study coauthor Anirudha Majumdar, an assistant professor of mechanical and aerospace engineering at Princeton who leads the Intelligent Robot Motion Lab.
The team obtained tool descriptions by querying GPT-3, a large language model released by OpenAI in 2020 that uses a form of AI called deep learning to generate text in response to a prompt. After experimenting with various prompts, they settled on using “Describe the [feature] of [tool] in a detailed and scientific response,” where the feature was the shape or purpose of the tool.
“Because these language models have been trained on the internet, in some sense you can think of this as a different way of retrieving that information,” more efficiently and comprehensively than using crowdsourcing or scraping specific websites for tool descriptions, said Karthik Narasimhan, an assistant professor of computer science and coauthor of the study. Narasimhan is a lead faculty member in Princeton’s natural language processing (NLP) group, and contributed to the original GPT language model as a visiting research scientist at OpenAI.
This work is the first collaboration between Narasimhan’s and Majumdar’s research groups. Majumdar focuses on developing AI-based policies to help robots — including flying and walking robots — generalize their functions to new settings, and he was curious about the potential of recent “massive progress in natural language processing” to benefit robot learning, he said.
For their simulated robot learning experiments, the team selected a training set of 27 tools, ranging from an axe to a squeegee. They gave the robotic arm four different tasks: push the tool, lift the tool, use it to sweep a cylinder along a table, or hammer a peg into a hole. The researchers developed a suite of policies using machine learning training approaches with and without language information, and then compared the policies’ performance on a separate test set of nine tools with paired descriptions.
This approach is known as meta-learning, since the robot improves its ability to learn with each successive task. It’s not only learning to use each tool, but also “trying to learn to understand the descriptions of each of these hundred different tools, so when it sees the 101st tool it’s faster in learning to use the new tool,” said Narasimhan. “We’re doing two things: We’re teaching the robot how to use the tools, but we’re also teaching it English.”
The researchers measured the success of the robot in pushing, lifting, sweeping and hammering with the nine test tools, comparing the results achieved with the policies that used language in the machine learning process to those that did not use language information. In most cases, the language information offered significant advantages for the robot’s ability to use new tools.
One task that showed notable differences between the policies was using a crowbar to sweep a cylinder, or bottle, along a table, said Allen Z. Ren, a Ph.D. student in Majumdar’s group and lead author of the research paper.
“With the language training, it learns to grasp at the long end of the crowbar and use the curved surface to better constrain the movement of the bottle,” said Ren. “Without the language, it grasped the crowbar close to the curved surface and it was harder to control.”
The research was supported in part by the Toyota Research Institute (TRI), and is part of a larger TRI-funded project in Majumdar’s research group aimed at improving robots’ ability to function in novel situations that differ from their training environments.
“The broad goal is to get robotic systems — specifically, ones that are trained using machine learning — to generalize to new environments,” said Majumdar. Other TRI-supported work by his group has addressed failure prediction for vision-based robot control, and used an “adversarial environment generation” approach to help robot policies function better in conditions outside their initial training.
Original Article: Words prove their worth as teaching tools for robots
More from: Princeton University School of Engineering and Applied Science | Princeton University
The Latest Updates from Bing News
Go deeper with Bing News on:
Robot learning
- Preschoolers prefer to learn from a competent robot than an incompetent human
Researchers found that preschoolers prefer learning from what they perceive as a competent robot over an incompetent human. This study is the first to use both a human speaker and a robot to see if ...
- Kids would rather learn from smart robots than less-smart humans: new study
The impacts of virtual learning on school-age kids is one area researchers have examined in recent years, but now, new research goes a step further, suggesting kids may be more susceptible to the ...
- Northcentral Technical College dawns a new day with new manufacturing robot
WAUSAU, Wis. (WSAW) - At Northcentral Technical College, students are always learning what’s new in the world of automation. It took all summer to build and creat and now, their new manufacturing ...
- Covariant’s CEO on building AI that helps robots learn
We had no mechanical engineers, no one in robotics. That allowed us to go much deeper into ... A lot of researchers are taking a lot of different approaches to learning. What’s different about yours?
- Preschoolers prefer to learn from a competent robot than an incompetent human, study shows
Who do children prefer to learn from? Previous research has shown that even infants can identify the best informant. But would preschoolers prefer learning from a competent robot over an incompetent ...
Go deeper with Bing News on:
Robotic systems
- Plan for the Future with Our Robotic Vision Systems Market Analysis Report Covering Top Countries Data [2030]
The MarketWatch News Department was not involved in the creation of this content. Mar 28, 2023 (The Expresswire) -- [133 Pages Report] Global “Robotic Vision Systems Market” [2023-2030] is expected to ...
- Industrial Robot Vision Systems Market Top Players By 2031
The MarketWatch News Department was not involved in the creation of this content. Mar 28, 2023 (The Expresswire) -- The "Industrial Robot Vision Systems Market" study describes how the technology ...
- Amicare Hospital Sets up Robotic Knee Replacement System
March 28, 2023: Amicare has introduced the first fully automated Robotic Knee Replacement Surgery system in western UP to assist in complex knee surgery procedures. This entirely automated Robotic ...
- Garden City Community College offers Robotics program
The Associate in Applied Science degree in Robotics and Mechatronics is a cross-disciplinary program that focuses on automation and control of mechanical systems, and students will be prepared to earn ...
- Northcentral Technical College dawns a new day with new manufacturing robot
NTC has other small robots but this is the first robot of its kind. “Here we have our smart manufacturing system here at NTC. The system is designed to train students on the industry of 4.0. Industry ...