Dennis Hong, robotics professor and founding director at Virginia Tech, explains why humanoid robots suit human environments and how his lab developed soccer-playing robots and firefighting prototypes.
Hong argues that a robot’s shape should match its job: a hospital delivery robot need not resemble a nurse, and a floor vacuum can be a low-profile puck. Human-sized robots could move through homes built for people and use familiar tools. Studying bipedal robots may also deepen understanding of human walking and inform prosthetic design.
Hong traces DARwIn from an early 2004 prototype without sensors or feedback control to later versions with onboard computing, cameras, force sensors, and batteries. By 2006, it could search for a ball and kick toward a goal without remote control or a tether. The team qualified for RoboCup, where autonomous robots tackle challenges in vision, movement, and decision-making.
Researchers wanted to use DARwIn, so Hong’s team worked with the University of Pennsylvania and Robotis to develop DARwIn-OP as an open platform. Its software, fabrication instructions, and design files were made freely available, while the robot could also be purchased. Other groups used it to study balance after a push, coordinated object carrying, and machine learning.
Hong describes CHARLI, a full-sized humanoid that learned to walk, balance using inertial sensors, and play autonomous soccer. His teams won both adult-size and kid-size RoboCup divisions, bringing the competition’s trophies to the United States. He presents SAFFiR, a Navy-funded firefighting robot, as an application of the same robotics challenges: its legs can handle ship corridors and raised thresholds, while a protective suit helps shield it from heat.
Hong says bipedal robots require expertise spanning mechanical design and artificial intelligence. His lab uses zero-moment-point control for stable walking on smooth, hard surfaces, while more varied terrain calls for different approaches. Battery life remains a constraint: he estimates CHARLI can run for about 15 to 20 minutes, and points to better actuators, compliance, and force control as needs for future robots.
Briefs summarise talks and interviews; timestamps open the video at that moment. Claims in a talk are the speaker's own.
Dr. Dennis Hong of Virginia Tech presents the DARwIn-OP humanoid robot, its development and research goals, alongside collaborators at Purdue, the University of Pennsylvania, and ROBOTIS.
Dennis Hong, director of RoMeLa at Virginia Tech, presents TEDxNASA on mobile robots, their design principles, and how his lab develops ideas.
Michael Chang, a PhD researcher at the University of California, Berkeley, presents his work at the GRASP Lab Spring 2023 SFI on neural abstractions for modeling and controlling systems, and discusses future human-computer interfaces at DeepMind.
Karen Liu, an associate professor of computer science at Stanford University, discusses physics-based human motion simulation and its use in robotics at an MIT Robotics talk.
A ROBOTIS presenter discusses a Darwin humanoid robot that plays Dance Dance Revolution and the vision-processing and motion constraints behind the demonstration.
Alex, role and affiliation unknown, presents the Darwin Drives project with King at an ICRA 2012 challenge; they show a humanoid robot operating an iRobot Create and discuss possible uses for humanoid-driven vehicles.
