Working with Humanoid Robots to Walk More Naturally, to Help Humans

For robots, walking with a natural stride is a major challenge. Researchers at EPFL's Biorobotics Laboratory  are testing novel systems to improve humanoids' ability to walk and interact with humans. Specifically, they are testing new walking algorithms on a 95-cm-tall, headless platform called COMAN - short for COmpliant HuMANoid. "Whether for manufacturing or natural disasters, we need robots that can interact with humans and help us carry heavy objects," says Jessica Lanini, an engineer in the lab. "But such robots don't exist. That's because, in order to operate safely and effectively, the robots would need to be able to make decisions and respond to unexpected circumstances." COMAN's joints are integrated with elastic elements that give it greater flexibility when performing different tasks. The EPFL team came up with a novel control algorithm for the robot, based on the existing symmetries in the structure and dynamics of the robot, as well as the mathematical equations representing the robot dynamics.



Transcript

00:00:01 a k is a humanoid robot humanoid means that it's like a human two legs arms what we study here is U the walking so we want to achieve a stable walking with this robot so this robot has to go from point A to point B while keeping balance uh there are many humanoids out there but what is a specific to kman uh whose name by the way comes from compliant humanoid is that its actuators

00:00:31 are integrated with the springs that can absorb shocks while walking can save energy and can provide the robot with the ability to walk more naturally there are a few applications that I can think of the first one is the search and rescue mission in disasterous scenarios where you have stairs you have doors to open then the humanoid design makes sense the second application is the

00:00:58 assistive scenarios where this robot uh helps human in Cooperative tasks for example when carrying an object again you have a a human environment right and again humano design would make sense and uh the last application which could be an outcome of our research is a application to excess cleton and powered prosthesis for people who are paralyzed