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.
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.
The AIRarm is a robot arm developed by iRobot with funding from DARPA. It is inexpensive as compared with an arm of similar size and lightweight as well. It weighs around 1/10th of the weight of the PackBot 3’s arm. The best part is that it can be easily deflated and kept. A pump is located onboard that allows it to inflated and deflated. Despite its light weight, AIRarm is still pretty stiff once inf, and can lift up to five pounds, or possibly more depending on how much its inflated. By varying the level of inflation, it’s also possible to vary the level of compliance of the arm: this makes the arm a little bit flexible when you need it to be, which in turn makes it safer and more durable. The same construct is used to develop a six legged robot as well.
Sandia, in partnership with Stanford, has created a dexterous robot hand for the DARPA’s ARM program. It’s addresses issues that have plagued previously developed arms, such as cost, durability, dexterity and modularity. It’s amazing how you can just snap on the fingers to form the hand and it has a skin that is able to mimic human tissue allowing for a better grip on objects.
Since the hand is modular and fingers can be attached magnetically according to the use of the robot, it would give us the opportunity to expand the use of the hand by looking at different configurations of the hand. Given the way the fingers are attached, it’s possible for the hand to pick up fingers and attach them as well. This gives the robot the flexibility to easily change the configuration of the hand during operation.
The fingers are costed around $800 per degree of freedom for low-volume productions and hence the 12 degrees of freedom hand would cost around $10,000. Sandia claim this to be cheaper than similar industrial hand with identical degrees of freedom.
Have a look at the video to see how dexterous the hand can be.
Hainanese chicken rice is a national delight here on the little red dot. There could be thousands of stalls selling chicken rice here and each stall selling up to 100 or more chickens a day. Each chicken is cut up into pieces before it is place on a plate of rice to be serve. This challenge of deboning the chicken (after it has been cooked) has been posed to engineers on the item without much result. It’s possible technically but it’s not easy to beat the chef with his mega chopper.
Gary McMurray, chief of the Georgia Tech, is getting robots to debone uncooked chicken. It’s not an easy task. “Each bird is unique in its size and shape, so we have developed the sensing and actuation needed to allow an automated deboning system to adapt to the individual bird, as opposed to forcing the bird to conform to the machine.” The team revealed a prototype version of the robot last year, but has since improved the speed and, in a recent demonstration, was able to debone a bird in seconds. Impressive!!
Festo has been developing beautiful robots of late and it’s still amazing me the way that the develop robots with an understanding of biological systems. It not only gives robots the ability to mimic biological systems but gives us an understanding of how our anatomy works.
The Exohand won second place during the Hermes Award at this year’s Hannover Messe industrial fair. It’s a fair that showcases the latest and most innovative products.
The ExoHand has eight double-acting pneumatic actuators that act as the muscles of the hand, with eight linear potentiometers acting as displacement sensors, and 16 pressure sensors provide feedback about the positions, angles, and forces of fingers. This provides a means for haptic force feedback for the human operator while remotely manipulating the arm.
Festo has developed other systems worth looking at, e.g. the PowerGripper that models after a bird’s beak and a robotic arm that is inspired by the elephant trunk. They also have a flying robot that look at the flight of bird with the Robotino XT, their mobile platform used for education and research. I am sure there will be many more interesting projects in the pipeline.
Kinova has created a 6 DOF arm (JACO Arm) weighing at 5kg and has a payload of 1.5kg (30% of it’s weight) with a maximum reach of 90cm. The arm is made from carbon fibre and uses harmonic gears motors thus making it a very quiet arm. It has claimed that it consumes less energy than a light bulb.
This arm cost around USD 50,000 but it’s considered low cost among robotic arms in it’s class.