A machine learning model figured out how to keep the robot stable on three legs while opening a door with one leg.
Philip Arm, Mayank Mittal, Hendrik Kolvenbach, Marco Hutter/Robot Systems Laboratory
The robot dog can open doors, press buttons, and pick up backpacks with one leg while balancing on its other three legs.
Quadruped robots like Spot, the star of Boston Dynamics' viral video, typically require arms attached to their bodies to open doors or lift objects, which adds significantly to their weight. This can make it difficult for the robot to maneuver through tight spaces. .
philip arm Researchers at ETH Zurich in Switzerland used a machine learning model to teach an off-the-shelf robotic dog to perform tasks using one of its legs while remaining stationary or moving with the other three. I taught you to do it.
“We can't do everything with our legs that we can do with our arms. We're much more dexterous with our hands at the moment. But what's really important is making this work in applications where there are mass constraints, or in robots. “The idea is to make this work in applications where you don’t want the added complexity, such as space exploration, where every kilogram counts,” Arm says.
To train the dog, the ANYmal robot from ANYbotics, Arm and his team gave the machine learning model the goal of finding a specific point in space on one of the robot's legs. The model then took control of his remaining three legs and independently worked out how to keep the robot balanced when standing and walking.
Arm and his team can now remotely control the robot to perform actions such as picking up backpacks and putting them in boxes, or collecting rocks. Currently, the robot can only perform these tasks when controlled by a human, but Arm hopes future improvements will allow the dog to autonomously manipulate objects with its paws.
A wheeled robot released on a college campus has discovered how to roll around the real world and open all kinds of doors and drawers.
Robots have adapted themselves to new challenges, paving the way for machines that can independently interact with physical objects. “We want the robots to be able to operate autonomously, without having to rely on humans to keep giving them examples of all new kinds of scenarios during testing,” he says. Deepak Pathak at Carnegie Mellon University (CMU) in Pennsylvania.
Pathak and his colleagues initially trained the robot through imitation learning, which provided visual examples of how to open objects such as doors, cabinets, drawers, and refrigerators. They then unleashed it around CMU's campus, opening doors and cabinets they had never encountered before. This required the robot to adapt to each new object using artificial intelligence that rewards the robot for understanding things.
The robot typically spent 30 minutes to an hour learning how to open each object consistently. Haoyu Shion CMU Ph.D. built a robot to scout various testing locations on campus. The team included his 12 training objects for practice, and then he included eight additional objects to test the robot's abilities.
Initial success rates averaged about 50%, but the robot sometimes completely failed to open new objects when first started. Eventually, that success rate increased to about 95%.
In addition to learning on the fly, he said he had to be able to physically handle heavy doors. Russell Mendonca At C.M.U. Achieving both goals will cost him $25,000, which he says is much cheaper than other robotic systems with adaptive learning capabilities.
Demonstrating the robot outside the lab “represents a concrete step towards more general robotic manipulation systems,” he said. Yunju Lee At the University of Illinois at Urbana-Champaign. “Opening a door or a drawer is a seemingly simple task for humans, but it's actually surprisingly difficult for robots,” he says.
After many years and many attempts, a healthy rhesus monkey was finally created by cloning. The clone was born in China on July 16, 2020, but its existence has only now been revealed.
“The cloned rhesus macaque is now 3 years old,” team members say Fallon Lu at the Chinese Academy of Sciences in Beijing. “So far, no health problems have been found during routine medical examinations.”
However, because the monkeys were cloned from fetal cells rather than adult cells, the embryos had to be provided with a non-cloned placenta. Therefore, despite this progress, primate cloning remains extremely difficult. As a result, apart from ethical and legal issues, it may not yet be technically possible to clone an adult.
Cloning is the creation of an individual that is genetically identical to another individual. Cloning plants is easy, but for most animals it is much more difficult.
Dolly the sheep, the first mammal cloned from an adult cell, was born in 1996. Since then, researchers have attempted to clone many mammalian species, with mixed results.
In some cases, cloning works relatively well.A Korean team created a clone over 1500 dogs For example, so far, success rates remain low, with fewer than 4 percent of cloned embryos leading to live births. In many other mammalian species, cloning either fails completely or produces unhealthy animals.
The main problem is that as cells in the body develop and become specialized, various so-called epigenetic markers are added to the DNA in order to turn certain genes on or off. When adult cells are cloned into empty eggs, they usually contain the wrong epigenetic markers.
Primates (a group that includes apes such as monkeys and humans) have proven particularly difficult to treat. There have been several previous reports of monkey clones, but each case so far has come with major warnings.
For example, the rhesus macaque born in 1999 is sometimes described as the first primate clone, but this individual was created not by cloning adult cells like Dolly, but by creating identical twins. It was created by splitting the embryo, as is done.
The most successful attempt to date was the birth of two long-tailed macaques in 2017. The researchers behind this study used a chemical cocktail to help reset epigenetic markers, but they were still able to clone only fetal cells, not adult cells.
Lu's team tried applying the same cocktail to rhesus macaques, but the only clone produced this way did not survive. The researchers concluded that the abnormalities in the cloned placenta were partially to blame, and decided to transplant the part of the early embryo that turns into a fetus (the inner cell mass) into a non-cloned embryo, where the inner cell mass forms. Developed new technology. Cell clumps were removed.
This means that the cloned fetus develops within a non-cloned placenta that is genetically distinct from it. Theoretically, the resulting fetuses could be a mixture of clonal and non-clonal cells, but the researchers found no evidence of such chimerism.
But even with the help of this complex technique, the researchers have so far only cloned fetal cells and not adult cells. In other words, healthy primates have not yet been created by cloning adult cells.
This means that whether it is possible to clone adults remains an open question. Lu wouldn't speculate on whether his team's technique would help.
“The act of cloning humans is completely unacceptable. We don't think about this,” he says.
Shukrat Mitalipov A professor at Oregon Health & Science University, who also works on cloning but was not involved in the study, says it's unclear whether the technology will help create cloned humans. “Aside from ethical issues, it is unclear whether there is any humanity. [cloned] “The fetus has placental abnormalities,” Mitalipov said.
Lu says the purpose of primate cloning is to advance research. “Rhesus monkeys are important and commonly used non-human primate laboratory animals in cognitive and biomedical research,” he says.
Meanwhile, Mitalipov's aim is to use cloning to generate stem cells that are compatible with individual treatments. “In our case, one day doctors will be able to use non-rejection, genetically compatible embryonic stem cells to replace diseased nerve, muscle, blood and other cells, or to produce eggs for infertility treatment. I hope we can produce it,” he says.
This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.
Strictly Necessary Cookies
Strictly Necessary Cookie should be enabled at all times so that we can save your preferences for cookie settings.
