Here is an interview of Dennis Hong by Sander Olson. Dr. Hong is a Professor of mechanical engineering at Virginia Tech who specializes in robotics. He directs the Robotics and Mechanisms Laboratory (ROMELA) at Virginia Tech, which has developed a number of innovative, mobile, and versatile robots, as well as robotic components such as hands. Hong and his team are currently designing a large, sophisticated humanoid robot called Charlie Heavy. The pace of robotics development is now so rapid that the ROMELA lab is introducing new versions of its robots every year.
Question: Tell us about the Robotics and Mechanisms Laboratory (RoMeLa) at Virginia Tech.
Answer: I founded RoMeLa seven years ago here at Virginia Tech as a graduate-level research laboratory. However, now RoMeLa also emphasizes undergraduate research. We currently have nine PhD students, nine masters students, two visiting professors, one post-Doc, and 30 undergraduate researchers. We initially focused on the mechanical side of robotics, but now we cover almost all aspects of robotics including dynamics, control, kinematics, design, autonomous behaviors, embedded systems, sensor development, etc.
TED Talk video Dennis Hong: My 7 species of robot
Question: Who funds RoMeLa?
Answer: Funding varies year to year, but some examples of funding agencies we have been working with include NSF, DARPA, ONR, NASA, and companies such as SAIC, NFB, Lockheed Martin, Boeing, and a number of other organizations. We anticipate a substantial increase in our funding starting next year, especially in the area of humanoid robots.
Question: Tell us about the Self-Excited Tripedal Dynamic Experimental Robot (STriDER) 2 robot.
Answer: STriDER is a 3 legged walking robot which walks using a technique called actuated passive dynamic locomotion in order to walk. It is stable, can move efficiently, can change direction, and is really cool. We think that this technique has practical potential for walking robots.
Question: Your Multi Appendage Robot System (MARS) would be well suited for space missions. What potential uses could it have on earth?
Answer: The Jet Propulsion Laboratory, which developed a number of martian landers, is also interested in legged robots. The MARS robot is based upon the JPLs Lemur II robot, which is designed to operate in space. The MARS robot can walk in a variety of different environments, such as dunes, so it could function either in earth or in space.
Question: There are a number of highly dexterous robotic hands on the market. What makes your Robotic Air Powered Hand with Elastic Ligaments (RAPHaEL) hand superior?
Answer: There are some fantastic robot hands on the market today, but these hands are quite expensive. We used compressed air with a novel accordion type actuator to create a low-cost, dexterous hand that is both fast and strong enough to crush a soda can, or delicate enough to handle a raw egg. It only cost us $200 to make the first prototype, so it clearly proves that inexpensive, dexterous robotic hands are feasible.
Question: Your team has recently created the CHARLIE robot. How does this robot compare with Honda’s ASIMO?
Answer: CHARLIE is a 1.5 meter tall robot that is the first American full-sized, free-walking, untethered robot. Honda’s ASIMO is currently the world’s most advanced humanoid robot and is the pride of Japan. ASIMO can walk or run, dance, can recognize faces and moving objects, can hear sounds, and is much more capable than CHARLIE. But CHARLIE was designed by a handful of undergraduates on a shoestring budget, so those comparisons aren’t fair. However, CHARLI is fully autonomous and can see and recognize certain objects using its two camera eyes. CHARLI is evolving and you will be able to see some very impressive things in the near future.
Question: How many different CHARLIE models are there?
Answer: There are currently two different models, the CHARLIE Light (L) and CHARLIE Heavy (H). CHARLIE L will be a low-cost model with rudimentary capabilities. CHARLIE H will be larger, stronger, and more capable than CHARLIE L. We currently have only one leg prototype for CHARLIE H, but we are very excited by its considerable potential.
Question: Your Dynamic Adaptive Robot With Intelligence (DARwIn) is designed to play soccer. What else can it do?
Answer: DARwIn started as an experimentation into human locomotion. The first DARwIn prototype was created in 2004, and we have made progressively more advanced DARwIns. We currently have DARwIn 4, and we are now working on DARwIn High Performance (HP) and DARwIn Low Cost (LC). The LC version will be under $8,000, and the HP substantially more. The HP will mostly be used in research laboratories, and we will distribute these robots to 11 partner Universities.
Question: How long before your robots can talk, and respond to verbal commands?
Answer: That is not currently our research focus, but CHARLI can speak. Responding to natural language is harder, but that capability could be added to our robots if desired. But to have a meaningful conversation the robot would need to possess common knowledge about things, and that would be difficult.
Question: What about pattern recognition?
Answer: Vision systems using cameras currently have rudimentary image recognition devices, and Asimo can already recognize different faces. As robots become more sophisticated they will increasingly gain the capability to recognize humans and most objects in the real world.
Question: When do you think that the robotic equivalent of Google will emerge?
Answer: Although many robotics companies exist today, only a handful are making money. But I do see many business opportunities for robotic components, such as actuators and sensors. If a multi-billion dollar robotics company emerges within the next decade I hopefully will be involved!
Question: How much of RoMela’s research goes into Artificial General Intelligence?
Answer: We do not claim ourselves to be AI experts. We do use AI because we have practical needs, but that is not our main research area. Although AI advances would obviously benefit the field, robotics would equally benefit from more mundane advances such as better actuators and energy sources.
Question: If you were given $1 billion and five years to develop the most sophisticated robot possible, what could you build?
Answer: I would put that money into CHARLIE H. CHARLIE H is being designed for the “3-D” – Dirty, Dull, and Dangerous tasks. For such a robot to be useful in the real world, it will have to be of human size and human form. So I would pour money into making CHARLIE H smarter, more agile, more reliable, and more capable.
Question: Are any startups being formed to commercialize your research?
Answer: I have plans to establish a company, but I have a full plate because I am involved in so many projects right now. I have, however, already designed a logo for my startup and will definitely get it up and running within the next several years. I am constantly approached by companies asking for collaboration.
Question: A number of prizes have emerged to encourage robotics development. Are these prizes having the desired effect?
Answer: At RoMeLa we are prize magnets – we have one entire wall covered with plaques, floor to ceiling. Competitions are an effective way to motivate both individuals and research groups, and they encourage people to push the envelope.
Question: Is the robotics industry hitting an exponential growth phase?
Answer: Robotics is really more of a conglomeration of technologies rather than a single technology. In the 1970s, the big limiter was the lack of computing power. The robotics industry has clearly benefited from Moore’s law, but now we are impeded by inadequate actuators and robot intelligence. There are new types of actuators being developed, but we are still limited by inefficient power sources. But progress is being made in all of these areas. My dream for 2020 is to see the CHARLIE H robot being used in millions of households as a robot helper.
Brian Wang is a Futurist Thought Leader and a popular Science blogger with 1 million readers per month. His blog Nextbigfuture.com is ranked #1 Science News Blog. It covers many disruptive technology and trends including Space, Robotics, Artificial Intelligence, Medicine, Anti-aging Biotechnology, and Nanotechnology.
Known for identifying cutting edge technologies, he is currently a Co-Founder of a startup and fundraiser for high potential early-stage companies. He is the Head of Research for Allocations for deep technology investments and an Angel Investor at Space Angels.
A frequent speaker at corporations, he has been a TEDx speaker, a Singularity University speaker and guest at numerous interviews for radio and podcasts. He is open to public speaking and advising engagements.