Robotics  

ATLAS, the humanoid robot built for the DARPA Robotics Challenge is cutting the cord.  In new demo videos, the robot is seen walking unattached and carrying heavy loads across a warehouse floor.

Since the initial stages of the DARPA Robotics Challenge (DRC), the Boston Dynamics-built ATLAS robot has been progressing well as the various teams continue to develop it. Where we used to see ATLAS secured to gantries and cranes to save it from unwanted falls, the humanoid robot is now roaming unteatherd (apart from hydraulic and power lines).

The demo above, which was presented at the International Conference on Robotics and Automation (ICRA) in Hong Kong, shows ATLAS dragging a huge piece of metal around an open space. The project is part of DRC work and was produced by Scott Kuindersma, Frank Permenter, and Russ Tedrake.

The video is significant as it shows that ATLAS can now walk while off-balance. This means the robot could carry various objects. It is beginning to look like a humanoid robot that can do actual work.

In a second video (below), a stereo depth fusion visualization of what ATLAS "sees" is shown.

Related articles Dennis Hong On Robot Evolution and The DARPA Robotics Challenge  Robot Revolution - Will Machines Surpass Humans?  Meet DARPA's ATLAS Humanoid Robot

This video demonstrates the simultaneous location and mapping (SLAM) systems used by the robot. The use of stereo depth fusion using Kintinuous (originally used to build large maps with Kinect data) to a quality which matches LIDAR data. The heightmap shown was used to place the required footsteps a priori while stationary. It also demonstrates the state estimation is provided by a highly tuned estimator developed by MIT. In this case it is running open loop (and not using any laser info). In open loop mode it drifts about 4cm in this total walking motion.




SOURCE  IEEE Spectrum

By 33rd Square

Embed

 Robotics  

Researchers at the University of Pennsylvania have successfully demonstrated autonomous flight using an off-the-shelf Google Tango smart phone attached to a quadrotor.

Earlier this year, Google unveiled its Project Tango smartphone, a mobile device equipped with a depth sensor, a motion tracking camera, and two vision sensors that let the phone track its position in space and create 3D maps in real time, a process known as SLAM (Simultaneous Localization and Mapping).

This set-up has great implications for robots, which have to navigate and locate themselves in the world. As such, a video showed how Google and its partners were putting the smartphone on different kinds of robots, including mobile platforms and manipulator arms.

The Google device is remarkable because it lets you "literally velcro it to a robot and have it be autonomous."

Now researchers at the University of Pennsylvania led by Professor Vijay Kumar, where quadrotor swarms have already demonstrated amazing abilities, are moving on to the next logical phase of the work: attaching a Tango device from Google onto one of their quadrotors.

Related articles NOVA's 'Rise Of The Drones' Opens The Shutters On Lethal Airborne Robotics Technology  Circus Performers - Get Ready To Lose Your Job To Robots Too  Cloud-Computing Internet For Robots Developed

Kumar says that a big challenge for researchers working with flying robots is not building them but rather developing hardware and software capable of making them autonomous. Many robots use GPS for guiding themselves, or, when flying indoors, they rely on motion tracking systems which offer great accuracy but requires that you install sensors on walls and ceilings.

The Tango phone does, opens new possibilities for flying robots. Kumar says that the Google device is remarkable because it lets you "literally velcro it to a robot and have it be autonomous."

Next, the researchers now plan to study Tango's accuracy of localization (and compare it to external motion tracking systems), but from their initial tests they estimate the accuracy to be within a centimeter. If that proves to be the case (and if Tango can be made cheap enough), it will be an impressive capability for the Google device, which could revolutionize how mobile robots and drones navigate indoor spaces.

Kumar says that the convergence of computation, communication, and consumers has a huge potential for the robotics industry, and a device like Tango is a key advance because it's "lowering the barrier to entry for autonomous robots."

The team has made a video of their results. In the first part of the video (below), Giuseppe Loianno, a PhD student in Kumar's group sets the quadrotor to hover at a fixed position and then disturbs it by moving it around, but the drone promptly returns to the starting point. Next he commands the drone to go to different places in the room and, even if disturbed, the drone recovers and stays on its programmed path.




SOURCE  IEEE Spectrum

By 33rd Square

Embed