Lead researcher Nikos Tsagarakis believes the world won't need to be adapted to accommodate Walk-Man, meaning it could eventually operate in damaged buildings; turning a heavy valve of lifting collapsed masonry, for example.
"There's one factor that everyone agrees, that actually our world, our environment it was designed for our body basically. So, we have tools that are designed to be grasped by humanoid, human hands. You have also areas or access paths that are actually appropriate for our body forms. So it means that if you build a robot that has a very similar form, you need to adapt less the environment in order to have this robot operational within such a space," Tsagarakis told Reuters.
To effectively navigate through tricky environments, Walk-Man uses all its limbs to demonstrate whole-body motion dynamics. Using its hands, arms, legs and feet, Walk-Man can maintain a more stable and balanced motion by reaching out to support itself while overcoming obstacles.
Tsagarakis says their aim is to make the Walk-Man robot demonstrate human type locomotion, balance and manipulation capabilities.
"We believe that - as humans also do - that legs are not only enough. You have to use also the arms, you have to be able to grasp the environment and actually assist your locomotion by creating additional contacts with the environmental balance," he said.
"This will make a big difference in humanoids where currently the technology is limited to the solutions that provide the balance basically only using the lower body. Upper body is also important; especially if you want to pass through cluttered spaces and structural grounds and so on."
Walk-Man stands more than six feet tall (1.85 metres), with an arm span of two metres and a weight of 118 kilograms. Its head module is equipped with a stereo vision system and a rotating 3D laser scanner to help it make sense of its environment.
The researchers are working towards algorithms that will allow more rapid manipulation skills, combined with reflexive behaviours that will allow the robot to cope with uneven terrain and rapid start and stop gait transitions.
Eventually they want the robot to have sufficient perception and cognitive ability to permit it to operate autonomously. However, the plan is for a human operator to remotely take control of it when more advanced problem solving is needed.
"The idea with this robot is that will always be some pilots at the back, that will be remotely placed and actually guide the robot in any case that a decision needs to be made. The robot will transfer data, like perception data, back to the operator, and the operator will take the actions and decide what is the next movement for the robot," said Tsagarakis.
Their aim is not necessarily to make the robot faster because that increases the likelihood of accidents, he said.
"When the robot is going slow it is actually easier than when trying to be more aggressive and go fast. In structural environments like those after physical disasters, you have also the possibility that these robots would collide accidentally with the environment. And the faster you move, the harder will be the impact forces. Which means again that you may have issues that you could face with actual hardware robustness," said Tsagarakis, adding that they are focused on making Walk-Man even more dextrous and improving its robust balanced locomotion.
The first prototype of the Walk-Man robot took part in the DARPA Robotics Challenge finals in June, where teams from around the world showcased robots capable of assisting humans in responding to natural and man-made disasters.
No comments:
Post a Comment
comment