IEEE Spectrum January, 2017 - 10

Motion-planning software has been a huge
limiter to the adoption of robotics. Real-time
motion planning would let robots operate in
dynamic, unstructured environments
tion. If there's a collision, the chip removes
that edge from the PRM. Once the chip
has run through all of the pixels in the
image, what's left is a PRM consisting only
of collision-free paths. The robot then just
picks the shortest one.
The speedup is substantial. No matter
how many edges you start with, the FPGA
will take just 50 nanoseconds per pixel to
determine all the potential collisions. In
one particularly complex example, the
FPGA took a little over 0.6 millisecond
to come up with a plan, and a softwarebased planner running on a quad-core
Intel Xeon processor clocked at 3.5 gigahertz took 2,738 ms-nearly 3 seconds.

Dinesh Manocha, a professor at
the University of North Carolina at
Chapel Hill who has been working on
real-time motion planning with GPUs,
agrees that FPGAs have the potential
to be much more efficient at motionplanning tasks. "Currently, industrial
robots do not use motion planners,"
Manocha explains. "As robots are
increasingly used in new, uncertain
environments, the role of motion planning will increase. I feel that this work
is very exciting and provides a very
practical solution."
The researchers at Duke, including
professors George Konidaris and Daniel

J. Sorin with grad students Sean Murray,
William Floyd-Jones, and Ying Qi, are
now exploring ways of applying similar
techniques to the next bottleneck: finding the shortest path through the PRM.
A startup called Realtime Robotics will be commercializing the Duke
technology. That will involve moving
from FPGAs to application-specific
integrated circuits (ASICs) that contain much larger PRMs (100,000 edges
or more), allowing robots to handle a
variety of different environments.
"We've been talking with many companies in the robotics space," Sorin
says. "There's great interest in this.
Motion-planning software has been a
huge limiter to the adoption of robotics, and if you can do real-time motion
planning, suddenly robots can now
operate in dynamic, unstructured environments. That's what we're hoping to
enable." -eva n ack er m a n

ROBOTIC END - EFFECTORS

Measure all six components of
force and torque in a compact,
rugged sensor.
Interface Structure-high-strength
alloy provides IP60, IP65, and IP68
environmental protection as needed
Low-noise Electronics-interfaces for
Ethernet, PCI, USB, EtherNet/IP, PROFINET,
CAN, EtherCAT, Wireless, and more
Sensing Beams and Flexures-designed
for high stiffness and overload protection

The F/T Sensor outperforms traditional load cells, instantly providing
all loading data in every axis. Engineered for high overload protection
and low noise, it's the ultimate force/torque sensor. Only from ATI.

www.ati-ia.com/ift
919.772.0115

10

|

jAN 2017

|

NORTh AMERICAN

|

SPECTRUM.IEEE.ORG
http://www.ati-ia.com/ift http://SPECTRUM.IEEE.ORG
Table of Contents for the Digital Edition of IEEE Spectrum January, 2017
