Learning by Demonstration

It’s never easy to program a robot to perform a useful task. A person has to first attend a course or pick up some skills from a robotics manufacturer. There’s always a designated person in the factory that is able to program the robot and no one else. This is not true for a human operator as all we have to do is instruct the person to perform the task, and this is possible if you know the task to be accomplished.

Many researchers have worked on Learning by Demonstration and the following video is the work done at Willow Garage where they run trials on normal end-users. The end-users are able to physical move the PR2 to show it how to perform a particular task engaging the robot using speech recognition. This is one of the key things that will bring robots closer to a human centric environment.

Velo 2G – Willow Garage has a New Gripper

Grippers that conform to objects surfaces are really useful. Some have looked at hand designs as all manmade should be made for grasp of the human hand. but it’s not easy to teach human grasp to a robot as we do grasp objects differently, e.g. how one holds a pair of chopsticks. I have seen different people holding a pair of chopsticks differently but yet able to finish a meal with the grasp. Secondly, it’s easy for humans to know how we are holding an object but it’s difficult to determine the orientation of the object if we use a robotic hand to hold the object.

The 2/3 finger design is simple and it can work really well maybe 90% of the time, which is good enough. Velco 2G is a passively adaptive gripper. It’s gripper is able to conform to any object it grasp. This is similar to the Robotiq grippers as well. BarrettHand is another gripper that’s falls in this category but it’s better because 2 of the 3 fingers of the BarrettHand can rotate  2 of the fingers around the palm axis and that allows changing the grasping style of the gripper. I find this useful for some applications.

Having the Velo 2G on the PR2 is great. It’s improves the grasp of the PR2 and i hope to see some innovation outside of software that can reduce the computation power requirements of the robot. My belief is that we need to produce robo-humancentric objects to improve the way the robots is able to perform task in a human-centric environment.


Related Articles:

 

Bring Manufacturing Back to the US

Robotics and perception technology is getting cheaper and more robust. It will indeed help bring manufacturing back to 1st world countries. This is an issue in America as well as in Europe. China’s cost of manufacturing is also increasing. With a push and a pull, there’s an incentive now for 1st world countries to rethink manufacturing. China is not the only option now, since the cost of manufacturing now is much higher there. Foxconn is feeling it and they have plans to replace the current workforce with robots (1 million of them) in 3 years.

Are we going to see a shift in manufacturing towards the west? Are we going to see innovation in robotics and manufacturing? The landscape of automation is going to change. We are going to rely on software and cheaper hardware to get things done. Willow Garage, Redwood robotics and Rethink robotics are geared for this shift.

Article

RedWood Robotics

Meka Robotics, Willow Garage and SRI announced a new startup — Redwood Robotics.

Meka has developed very sophisticated force controlled arms but it’s expensive and only affordable to researcher. With Redwood Robotics, Meka will be codeveloping a new generation of robot arms that are simple to program, inexpensive, and safe to operate alongside people.

Those three partners bring a lot of robotic talent to the table and a formidable competitor for Heartland.

Read this article.

Open Source – Is it good for Business?

The debate published in ieee spectrum between Colin Angle (iRobot) and Robert Bauer (Willow Garage) is interesting. Willow garage has benefited the community greatly and it’s pretty easy to get a robot to grasp a cup using the ROS platform (given you can purchase the robot). This approach of crowdsourcing does speed up the development but it’s not easy to build a hardware business out of this model. Do write your thought in the article. It will be interesting to see where this goes.