Boston Dynamics has joined forces with the research organisation Robotics & AI Institute (RAII) to bring enhanced reinforcement learning to humanoid robots.
This collaboration aims to develop dynamic and generalisable mobile manipulation capabilities for the Boston Dynamics’ new electric Atlas robot.
Go deeper with GlobalData
The partnership builds on their previous joint efforts, including the creation of Spot’s Reinforcement Learning Researcher Kit.
One of the primary objectives of this collaboration is to develop a more effective simulation-to-reality transfer for mobility.
The research teams will work together to train policies that enable agile and adaptable movements in physical environments.
Another key goal is to enhance the ability of humanoid robots to manipulate objects while in motion.
How well do you really know your competitors?
Access the most comprehensive Company Profiles on the market, powered by GlobalData. Save hours of research. Gain competitive edge.
Thank you!
Your download email will arrive shortly
Not ready to buy yet? Download a free sample
We are confident about the unique quality of our Company Profiles. However, we want you to make the most beneficial decision for your business, so we offer a free sample that you can download by submitting the below form
By GlobalDataAdditionally, the project will explore full-body contact strategies to advance high-performance locomotion and tasks that require coordinated body movements.
By using reinforcement learning, the team will develop these behaviours without the need for predefined control mechanisms.
The latest generation of Atlas, known for its physical capability and software interfaces, serves as an ideal platform for this research, Boston said.
The Atlas robot features advanced hardware and software for improved AI-driven manipulation.
For the RAII, the collaboration with Boston Dynamics will further its research into AI and machine learning, with the potential to apply the advancements to a broader range of robotic platforms.
RAII executive director Marc Raibert said: “Our aim at RAI is to develop technology that enables future generations of intelligent machines.
“Working on Atlas with Boston Dynamics enables us to make advances in reinforcement learning on arguably the most sophisticated humanoid robot available.
“This work will play a crucial role in advancing the capabilities of humanoids not only by expanding its skillset, but also streamlining the process to achieve new skills.”
