Boston Dynamics Joins Forces With Its Former CEO (techcrunch.com) 4
An anonymous reader quotes a report from TechCrunch: Boston Dynamics Wednesday 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. Both organizations were founded by Marc Raibert, a former MIT professor who served as Boston Dynamics' CEO for 30 years. The Institute, founded in 2022, allows Raibert to continue the research that served as the foundation for Boston Dynamics.
Both have ties to Hyundai. The Korean carmaker acquired Boston Dynamics back in 2021; Hyundai also funds the Institute, giving Raibert free rein to explore more experimental and bleeding-edge technologies than is possible in a commercial company. The Institute mirrors Toyota's creation of TRI, or Toyota Research Institute, which announced its own partnership with Boston Dynamics in October, focused on the use of large behavior models. (LBMs). The twin partnerships are designed to improve the way Boston Dynamics' electric Atlas humanoid learns new tasks. The Robotics & AI Institute deal is specifically focused on reinforcement learning, a method that operates through trial and error, similar to the way both humans and animals learn. Reinforcement learning 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.
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 (which is its familiar robot "dog"). The new work focuses on both transferring simulation-based learning to real-world settings and improving how the company's humanoid Atlas moves through and interacts with physical environments. 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.
Both have ties to Hyundai. The Korean carmaker acquired Boston Dynamics back in 2021; Hyundai also funds the Institute, giving Raibert free rein to explore more experimental and bleeding-edge technologies than is possible in a commercial company. The Institute mirrors Toyota's creation of TRI, or Toyota Research Institute, which announced its own partnership with Boston Dynamics in October, focused on the use of large behavior models. (LBMs). The twin partnerships are designed to improve the way Boston Dynamics' electric Atlas humanoid learns new tasks. The Robotics & AI Institute deal is specifically focused on reinforcement learning, a method that operates through trial and error, similar to the way both humans and animals learn. Reinforcement learning 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.
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 (which is its familiar robot "dog"). The new work focuses on both transferring simulation-based learning to real-world settings and improving how the company's humanoid Atlas moves through and interacts with physical environments. 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.
They failed (Score:2)
Make no mistake, humanity has failed when it comes to robotics. We still can't mimic human muscle (motors are bulky and heavy in comparison) and human skeletal control systems. We are about 150 years from achieving a majority of the items on this list (some of which a 10 year old can do):
1. From a table on which there are about 20 screws of varying sizes strewn about confidently pick up only the eyeglass frame screw.
2. Place and screw the picked-up screw into an eyeglass frame
3. Pick up a single red m&m
Re: (Score:2)
Make no mistake, humanity has failed when it comes to robotics. We still can't mimic human muscle (motors are bulky and heavy in comparison) and human skeletal control systems. We are about 150 years from achieving a majority of the items on this list (some of which a 10 year old can do):
1. From a table on which there are about 20 screws of varying sizes strewn about confidently pick up only the eyeglass frame screw.
2. Place and screw the picked-up screw into an eyeglass frame
3. Pick up a single red m&m only from a table that has m&m strewn on it
4. Pick up a dry rice grain from a table.
These are all trivial, assuming a gripper of appropriately tiny size and properly designed hardware for orienting a screw via a hopper and inserting it. Basically, each piece has been done, though chaining them will require some slight additional hardware. No big deal, really.
5. From a small bag of various trinkets, feel around and pick out only the rubber band from it.
This one is hard, but only because any sort of touch sensitive skin is hard to pull off, and doing anything useful with the data doubly so.
6. Sculpt a recognizable face on a small piece of clay
7. Assemble a lego set
8. Assemble a motor, including wrapping of stator wires
9. Sculpt a face into granite like Michelangelo or Bernini.
And now we're back to trivial again. The programming for these things is insanely hard, but a
Re: (Score:2)
You don't seem to understand technological progress at all. A hundred and fifty years ago (1875) steam engines were the highest technology of the day, the telephone was still a year away from being invented, electric light bulbs three years after that, and the AC electric motor was still thirteen years in the future. Gallium had just been isolated as an element, milk chocolate was invented that year, and Nikola Tesla was still an engineering student.
Technology generally improves in an exponential manner,
Boston Dynamics vs China's Unitree (Score:2)