Servo - April 2012

WE BE JAMMIN’

The jamming robot gripper has learned a new trick! Roboticists at Cornell and the University of Chicago have taught it to throw stuff.

A quick refresher: The gripper is simply a latex balloon filled with coffee grounds. The grounds move around each other like grains of sand and can conform to objects and complex surfaces, but when air is pumped out of the balloon, the grounds all "jam" together into a solid mass, yielding a strong hold on whatever the gripper is in contact with.

It's simple, cheap, and you can pick up just about anything without having to calculate optimal grasping points (or anything in the way of sensing or computation). You really just stuff the gripper against an object, pump the air out, and off you go.

This new "shooting" trick (or "fast ejection," if you prefer) comes from rapidly re-inflating the gripper with air. It sounds simple enough, but what you don't expect is the repeatable long-range accuracy — good enough to shoot baskets, sort hardware, and play a mean game of darts. Researchers say the precision they can achieve is ± 60 mm with 95 percent confidence in the direction perpendicular to flight, which "is certainly too coarse for high-precision manufacturing tasks, but could be useful for tasks like sorting objects into bins in a factory or throwing away trash in a home."

It's obviously good enough for winning games of mini-basketball and playing horizontal darts, so it's kinda fun to imagine what other tasks a talented throwing robot might do around the house ... like making a sandwich or unloading the dishwasher.

EYES ON OPTI-TRACK

In autonomous robotics, the right inputs reveal the right path. Each day, the University of Waterloo's WAVELab Research Group navigates these waters as they work out the best ways to help robot commanders get their flying mecha-assistants from point A to point B without the use of manual controls. For them, the most precise way to achieve this is with the help of an Opti Track™ motion capture system.

Professor Steven Waslander began WAVELab's autonomous vehicle program with the traditional measurement tools of the field: IMU sensors, gyroscopes, and onboard GPS. These devices gave real time estimates that stabilized his squadron of aerial and ground rovers, but failed to deliver the control needed to prevent those same vehicles from veering off into hazardous areas (like walls). To address this problem, Waslander increased his state estimation system's scope by enlisting the input of an 18 camera OptiTrack tracking system.

The addition of the cameras enabled the team to estimate in real time if the onboard sensors were working and if the robots had stayed locked to their predetermined route. Quick adjustments to the onboard control algorithms could be made from this data which significantly reduced its development time. Now, each time the WAVELab's robots go for a spin on the ground or in the air, they can sense unknown surroundings, develop accurate 3D maps, and navigate through their environment with the assistance of Opti Track's sub-millimeter data. As Opti Track's system helps the algorithm increase in potency, new opportunities for robot crossover could start to materialize in our lives, as well. In time, you may see WAVELab's robots out in the world as sample collectors for scientists exploring hard-to-reach crevasses in Antarctica, or as scouts that keep soldiers safe. Maybe someday they could even be the pilot that flies you home from a well deserved vacation.

SOCCER IT TO US

This is the official goal of the RoboCup soccer competition: "By mid-21st century, a team of fully autonomous humanoid robot soccer players shall win the soccer game, complying with the official rule[s] of the FIFA [Fédération Internationale de Football Association], against the winner of the most recent World Cup." There’s been a lot of improvement over the last few years, but nothing that compares to the skills that the new version of ASIMO recently displayed (and RoboCup itself isn't far behind). ASIMO, of course, costs a ton of money and has the corporate support of Honda. However, watching RoboCup competitions themselves, you can see improvement that's almost as dramatic, albeit with a delay commensurate with the amount of time and money that can be invested in what's ultimately a hobby/research for most of the teams involved.