Boston Dynamics and Toyota Research Institute (TRI) announced on Tuesday that they are partnering to develop general-purpose humanoid robots. Boston Dynamics will contribute its new electric Atlas robot to the task, while TRI will utilize its industry-leading Large Behavior Models.

Boston Dynamics, which launched in 1992 as an offshoot from the Massachusetts Institute of Technology (MIT), has been at the forefront of robotics development for more than 30 years. It burst into the mainstream in 2009 with the BigDog and LittleDog quadrupedal systems and debuted the first iteration of its bipedal Atlas platform in 2013. Atlas’ capabilities have undergone a steady evolution in the past decade, enabling the robot to perform increasingly difficult acrobatics and dexterity tasks, from dancing and doing back flips to to conquering parkour courses and navigating simulated construction sites.

In April 2024, the company retired its long-standing, hydraulic Atlas platform in favor of a new generation driven by electric servos. The company describes the electric Atlas as “one of the most advanced humanoid robots ever built,” one that is “able to move in ways that exceed human capabilities.”

TRI, on the other hand, stands at the forefront of Large Behavior Model (LBM) development. LBMs are to robotics as LLMs are to chatbots. Just as LLM’s are trained on massive multimodal datasets to respond to a human like a human would, LBMs are trained on enormous corpora of human behaviors, enabling robots to move and act in a humanlike manner. They also help robots learn new behaviors and generalize across tasks. Per the announcement blog, “TRI’s work on LBMs aims to achieve multitask, vision-and-language-conditioned foundation models for dexterous manipulation.”

“Recent advances in AI and machine learning hold tremendous potential for advancing physical intelligence,” Gill Pratt, chief scientist for Toyota and CEO of TRI, said in a statement. “The opportunity to implement TRI’s state-of-the-art AI technology on Boston Dynamics’ hardware is game-changing for each of our organizations as we work to amplify people and improve quality of life.”

This news comes amid an increasingly crowded field of companies looking to incorporate robots into the future workforce. Agility Robotics’ Digit and Figure’s 01 and 02 models, for example, are already being tested in industrial settings such as BMW’s Spartanburg plant in South Carolina and a Spanx production facility in Flowery Branch, Georgia. Tesla’s Optimus is ostensibly also in the running, though even the most recent models still need to be remotely operated when performing more than the most basic tasks.

Related Posts

New study shows AI isn’t ready for office work

A reality check for the "replacement" theory

Google Research suggests AI models like DeepSeek exhibit collective intelligence patterns

The paper, published on arXiv with the evocative title Reasoning Models Generate Societies of Thought, posits that these models don't merely compute; they implicitly simulate a "multi-agent" interaction. Imagine a boardroom full of experts tossing ideas around, challenging each other's assumptions, and looking at a problem from different angles before finally agreeing on the best answer. That is essentially what is happening inside the code. The researchers found that these models exhibit "perspective diversity," meaning they generate conflicting viewpoints and work to resolve them internally, much like a team of colleagues debating a strategy to find the best path forward.

Microsoft tells you to uninstall the latest Windows 11 update

https://twitter.com/hapico0109/status/2013480169840001437?s=20