Boston Dynamics has partnered with its former CEO, Marc Raibert, to develop a next-generation humanoid robot through the Robotics & AI Institute. This collaboration aims to improve reinforcement learning on the electric Atlas humanoid robot.
Boston Dynamics Partners with Its Former CEO to Build a Humanoid Robot
Boston Dynamics has announced a partnership designed to bring improved reinforcement learning to its electric Atlas humanoid robot. The tie-up is with the Robotics & AI Institute (RAI Institute), earlier known as The Boston Dynamics AI Institute, which was founded by Marc Raibert, a former MIT professor and Boston Dynamics’ CEO for 30 years.
Boston Dynamics is a leading robotics company that specializes in designing and manufacturing advanced robots for various industries.
Founded in 1992 by Marc Raibert, the company has made significant contributions to the field of robotics, particularly in areas such as mobility, dexterity, and autonomy.
Boston Dynamics' robots are designed to navigate complex environments with ease, making them suitable for applications like search and rescue, logistics, and healthcare.
The company's most notable creations include Atlas, a humanoid robot capable of walking and climbing stairs, and Spot, a quadruped robot used for inspection and exploration.
A Partnership Born from Shared Roots
Both organizations have ties to Hyundai, the Korean carmaker that acquired Boston Dynamics in 2021. ‘Hyundai also funds the RAI Institute, giving Raibert free rein to explore more experimental and bleeding-edge technologies than is possible in a commercial company.’ This mirrors Toyota’s creation of TRI (Toyota Research Institute), which announced its own partnership with Boston Dynamics in October, focused on the use of large behavior models (LBMs).
Improving Reinforcement Learning
The twin partnerships are designed to improve the way Boston Dynamics’ electric Atlas humanoid learns new tasks. The RAI Institute deal is specifically focused on reinforcement learning, a method that operates through trial and error, similar to the way humans and animals learn. ‘This approach has traditionally been extremely time-intensive, though the creation of effective simulation has allowed many processes to be carried out at once in a virtual setting.’
Transferring Simulation-Based Learning
The Boston Dynamics/RAI Institute union kicked off earlier this month in Massachusetts. It’s the latest in a number of collaborations between the pair, including a joint effort to develop a reinforcement learning research kit for the quadrupedal Spot robot by Boston Dynamics. ‘The new work focuses on transferring simulation-based learning to real-world settings and improving how the company’s humanoid Atlas moves through and interacts with physical environments.’
Challenges and Opportunities
Pertaining to the latter, Boston Dynamics points to ‘dynamic running and full-body manipulation of heavy objects.‘ Both are examples of actions that require synchronization of the legs and arms. The humanoid’s bipedal form factor presents a number of unique challenges — and opportunities — when compared with Spot. Every activity is also subject to a broad range of forces, including balance, force, resistance, and motion.
Advancing Humanoid Capabilities
Bigger picture, Raibert notes in a statement, ‘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.’
Raibert's bipedal robot is a robotic system developed by Marc Raibert in the 1980s.
The robot uses a feedback control approach to balance and move on two legs.
It has no external support or balance aids, relying solely on its own sensors and algorithms.
Raibert's work on bipedal robots paved the way for future research in robotics and human-like motion.
The system's ability to adapt to changing environments and terrain was a significant breakthrough.
Industry Developments
News of the partnership arrives a day after Figure AI founder and CEO Brett Adcock announced that the Bay Area company is abandoning a partnership with OpenAI in favor of developing its own in-house models. ‘We found that to solve embodied AI at scale in the real world, you have to vertically integrate robot AI,’ the executive told TechCrunch. Most companies involved in humanoid space are working on their own bespoke AI models, including Boston Dynamics, which has decades of experience developing software to run on its unique robotics systems.
