UC버클리, 5천달러대 인공지능 로봇 '블루' 개발 VIDEO: Meet Blue, the low-cost, human-friendly robot designed for AI
Meet Blue, the low-cost, human-friendly robot designed for AI
By Kara Manke| APRIL 9, 2019
Robots may have a knack for super-human strength and precision, but they still struggle with some basic human tasks — like folding laundry or making a cup of coffee.
Blue’s creators, Pieter Abbeel, David Gealy and Stephen McKinley. (Philip Downey photo)
UC버클리, 사람 처럼 유연한 인공지능 로봇 '블루' 개발 5천 달러대 * 상단 사진 설명: 피터 애빌 교수(좌측) 'MIT 테크놀로지 리뷰' 등 매체에 따르면 UC 버클리 '피터 애빌(Pieter Abbeel)' 교수 등 과학자들은 심층 강화학습 방식의 인공지능 알고리즘을 이용해 빨래를 개거나 커피를 내리는 등 복잡한 작업을 수행할 수 있는 로봇인 ‘블루(Blue)’를 개발했다. 일종의 범용 로봇이다. 이 로봇은 일부 3D프린팅 부품을 사용했으며, 부드러운 성질의 타이밍 벨트 등 부품을 활용한 'QDD(quasi-direct drive)' 액추에이터를 채택, 사람과 충돌하더라도 안전하도록 설계됐다. VR헤드마운트 장비와 핸드헬드 컨트롤러를 이용해 로봇을 제어할 수 있다. 조작자가 VR헤드 마운트를 쓰고 팔을 움직이면 로봇이 같이 움직인다. VR장비 없이 손에 컨트롤러를 잡고 조작하는 것도 가능하다. 인공지능 기술을 이용해 로봇 팔에 부착된 집게를 조작, 물건을 다루는 방법을 훈련시켰다. 이 로봇은 5천 달러 미만의 가격으로 제작할 수 있는 게 특징이다. 기존에 나와있는 다른 로봇들과 비교할 때 파격적이다. 박스터 로봇은 블루보다 5배 이상 비싸고 쿠카 LBR은 7만 달러, 프랑카 에미카는 3만 달러에 달한다. 연구자들에게 오랫동안 사랑을 받아왔던 윌로우 개러지(Willow Garrage)가 개발한 PR2는 높은 가격에도 볼구하고 더 이상 구입하거나 서비스를 받을 수 없다. 5천 달러 가격대의 로봇은 로봇 연구자들이나 개발자들에게 매력적인 가격이다. 연구팀은 이 로봇을 개인용 컴퓨터인 ‘애플 II(Apple II)’에 비유했다. 1970년대와 1980년대에 아마추어 동호인들과 해커들이 애플 II를 이용해 컴퓨터의 세계에 빠지면서 기술 혁명을 이끌었던 것처럼 블루 로봇을 이용해 로봇 혁명 시대를 앞당겨야 한다는 바램을 담고 있다. 블루 로봇은 사람의 상체와 비슷한 크기이며, 7자유도의 로봇팔을 갖추고 있다. 페이로드는 2kg이다. 낮은 레벨의 로봇 제어 소프트웨어와 VR 시스템을 활용하고 있으며 기존의 AI 운용 컴퓨터와 호환성을 갖추고 있다는 설명이다. 이 로봇 개발 프로젝트는 피터 애빌 교수가 운영하고 있는 로봇 연구실에서 시작됐다. 피터 애빌 교수는 오랫동안 로봇 기술에 인공지능을 접목하려는 노력을 해왔다. 블루 로봇 연구팀은 이 프로젝트를 위한 지적 재산권(IP)을 신설 기업인 ‘버클리 오픈 암(Berkeley Open Arms)’을 통해 UC버클리로부터 라이센스 받았다. 연구팀은 가상세계의 머신러닝을 로봇 하드웨어에 이전하는 데 많은 어려움이 있었지만 큰 진전을 이룩했다고 설명했다. 연구팀이 블루 로봇을 5천 달러 이하 가격에 내놓는다면 많은 로봇 연구자들과 개발자들이 낮은 예산으로 로봇 연구를 할수 있을 것으로 기대된다. 장길수 ksjang@irobotnews.com 로봇신문사 |
edited by kcontents
Enter Blue, a new low-cost, human-friendly robot conceived and built by a team of researchers at the University of California, Berkeley. Blue was designed to use recent advances in artificial intelligence (AI) and deep reinforcement learning to master intricate human tasks, all while remaining affordable and safe enough that every artificial intelligence researcher — and eventually every home — could have one.
Blue is the brainchild of Pieter Abbeel, professor of electrical engineering and computer sciences at UC Berkeley, postdoctoral research fellow Stephen McKinley and graduate student David Gealy. The team hopes Blue will accelerate the development of robotics for the home.
“AI has done a lot for existing robots, but we wanted to design a robot that is right for AI,” Abbeel said. “Existing robots are too expensive, not safe around humans and similarly not safe around themselves – if they learn through trial and error, they will easily break themselves. We wanted to create a new robot that is right for the AI age rather than for the high-precision, sub-millimeter, factory automation age.”
Over the past 10 years, Abbeel has pioneered deep reinforcement learning algorithms that help robots learn by trial and error or by being guided by a human like a puppet. He developed these algorithms using robots built by outside companies, which market them for tens of thousands of dollars.
Blue’s durable, plastic parts and high-performance motors total less than $5,000 to manufacture and assemble. Its arms, each about the size of the average bodybuilder’s, are sensitive to outside forces — like a hand pushing it away — and has rounded edges and minimal pinch points to avoid catching stray fingers. Blue’s arms can be very stiff, like a human flexing, or very flexible, like a human relaxing, or anything in between.
Currently, the team is building 10 arms in-house to distribute to select early adopters. They are continuing to investigate Blue’s durability and to tackle the formidable challenge of manufacturing the robot on a larger scale, which will happen through the UC Berkeley spinoff Berkeley Open Arms. Sign-ups for expressing interest in priority access start today on that site,
“With a lower-cost robot, every researcher could have their own robot, and that vision is one of the main driving forces behind this project — getting more research done by having more robots in the world,” McKinley said.
From moving statue to lithe as a cat
Robotics has traditionally focused on industrial applications, where robots need strength and precision to carry out repetitive tasks perfectly every time. These robots flourish in highly structured, predictable environments — a far cry from the traditional American home, where you might find children, pets and dirty laundry on the floor.
“We’ve often described these industrial robots as moving statues,” Gealy said. “They are very rigid, meant to go from point A to point B and back to point A perfectly. But if you command them to go a centimeter past a table or a wall, they are going to smash into the wall and lock up, break themselves or break the wall. Nothing good.”
If an AI is going to make mistakes and learn by doing in unstructured environments, these rigid robots just won’t work. To make experimentation safer, Blue was designed to be force-controlled — highly sensitive to outside forces, always modulating the amount of force it exerts at any given time.
Blue’s grippers holding a planetary gear set. (Philip Downey photo)
edited by kcontents
“One of the things that’s really cool about the design of this robot is that we can make it force-sensitive, nice and reactive, or we can choose to have it be very strong and very rigid,” Gealy said. “Researchers can adjust how stiff the robot is, and what kind of stiffness — do you want it to feel like molasses? Do you want it to feel like a spring? A combination of those? If we want robots to move toward the home and perform in these increasingly unstructured environments, they are going to need that capability.”
To achieve these capabilities at low cost, the team considered what features Blue needed to complete human-centered tasks, and what it could go without. For example, the researchers gave Blue a wide range of motion — it has joints that can move in the same directions as a human shoulder, elbow and wrist — to enable humans to more easily teach it how to complete tricky maneuvers using virtual reality. But the agile robot arms lack some of the strength and precision of a typical robot.
Blue is able to continually hold up 2 kilograms of weight with arms fully extended. But unlike traditional robot designs that are characterized by one consistent “force/current limit,” Blue is designed to be “thermally-limited,” McKinley said. That means that, similar to a human being, it can exert a force well beyond 2 kilograms in a quick burst, until its thermal limits are reached and it needs time to rest or cool down. This is just like how a human can pick up a laundry basket and easily carry it across a room, but might not be able to carry the same laundry basket over a mile without frequent breaks.
“Essentially, we can get more out of a weaker robot.” Gealy said. “And a weaker robot is just safer. The strongest robot is most dangerous. We wanted to design the weakest robot that could still do really useful stuff.”
“Researchers had been developing AI for existing hardware and, about three years ago, we began thinking, ‘Maybe we could do something the other way around. Maybe we could think about what hardware we could build to augment AI and work on those two paths together, at the same time,’” McKinley said. “And I think that is a really dramatic shift from the way a lot of research has taken place.”
https://news.berkeley.edu/2019/04/09/meet-blue-the-low-cost-human-friendly-robot-designed-for-ai/
kcontents
