Tech Briefs Magazine - June 2024 - MD18

Using Machine Learning to Teach New Tricks to
ANYMal Robot
The quadrupedal robot ANYmal can now climb over obstacles and successfully negotiate pitfalls.
ETH Zurich, Switzerland
A
NYmal has for some time had no
problem coping with the stony terrain
of Swiss hiking trails. Now researchers at
ETH Zurich have taught this quadrupedal
robot some new skills: it is proving rather
adept at parkour, a sport based on using
athletic maneuvers to smoothly negotiate
obstacles in an urban environment, which
has become very popular. ANYmal is also
proficient at dealing with the tricky terrain
commonly found on building sites or in
disaster areas.
To teach ANYmal these new skills,
two teams, both from the group led
by ETH Professor Marco Hutter of
the Department of Mechanical and
Process Engineering, followed different
approaches.
Working in one of the teams is ETH
doctoral student Nikita Rudin, who does
parkour in his free time. " Before the
project started, several of my researcher
colleagues thought that legged robots
had already reached the limits of their
development potential, " he said, " but I
had a different opinion. In fact, I was
sure that a lot more could be done with
the mechanics of legged robots. "
With his own parkour experience in
mind, Rudin set out to further push the
boundaries of what ANYmal could do.
And he succeeded, by using machine
learning to teach the quadrupedal robot
new skills. ANYmal can now scale obstacles
and perform dynamic maneuvers to jump
back down from them.
In the process, ANYmal learned like
a child would - through trial and error.
Now, when presented with an obstacle,
ANYmal uses its camera and artificial neural
network to determine what kind of
impediment it's dealing with. It then performs
movements that seem likely to succeed
based on its previous training.
Is that the full extent of what's techniThe
quadrupedal robot ANYmal practices parkour in a hall at ETH Zurich. (Image: Nikita Rudin/ETH Zurich)
ANYmal on a civil defense training ground. (Image: Fabian Jenelten/ETH Zurich)
18
cally possible? Rudin suggested that this
is largely the case for each individual new
skill. But he added that this still leaves
plenty of potential improvements. These
include allowing the robot to move beyond
solving predefined problems and instead
asking it to negotiate difficult terrain
like rubble-strewn disaster areas.
Getting ANYmal ready for precisely
that kind of application was the goal of
the other project, conducted by Rudin's
colleague and fellow ETH doctoral student
Fabian Jenelten. But rather than
relying on machine learning alone,
Jenelten combined it with a tried-andtested
approach used in control engineering
known as model-based control.
This provides an easier way of teaching
the robot accurate maneuvers, such as
how to recognize and get past gaps and
recesses in piles of rubble. In turn, machine
learning helps the robot master
movement patterns that it can then
flexibly apply in unexpected situations.
" Combining both approaches lets us get
the most out of ANYmal, " Jenelten said.
As a result, the quadrupedal robot is
now better at gaining a sure footing on
slippery surfaces or unstable boulders.
ANYmal is soon also to be deployed on
building sites or anywhere that is too
dangerous for people - for instance to inspect
a collapsed house in a disaster area.
For more information, contact Media
Relations at mediarelations@hk.ethz.ch;
+41 44-632-41-41.
Motion Design, June 2024

Tech Briefs Magazine - June 2024

Table of Contents for the Digital Edition of Tech Briefs Magazine - June 2024