Candidate:
Matthew
Pitropov
Title:
LiDAR-MIMO:
Efficient
Uncertainty
Estimation
for
LiDAR-based
3D
Object
Detection
Date:
January
24,
2022
Time:
15:00
Place:
online
Supervisor(s):
Czarnecki,
Krzysztof
-
Waslander,
Steven
(ME)
Abstract:
The
estimation
of
uncertainty
in
robotic
vision,
such
as
3D
object
detection,
is
an
essential
component
in
developing
safe
autonomous
systems
aware
of
their
own
perfor-
mance.
However,
the
deployment
of
current
uncertainty
estimation
methods
in
3D
object
detection
remains
challenging
due
to
timing
and
computational
constraints.
To
tackle
this
issue,
we
propose
LiDAR-MIMO,
an
adaptation
of
the
multi-input
multi-output
(MIMO)
uncertainty
estimation
method
to
the
LiDAR-based
3D
object
detection
task.
Our
method
modifies
the
original
MIMO
by
performing
multi-input
at
the
feature
level
to
ensure
the
detection,
uncertainty
estimation,
and
runtime
performance
benefits
are
retained
despite
the
limited
capcity
of
the
underlying
detector
and
the
large
computational
costs
of
point
cloud
processing.
We
compare
LiDAR-MIMO
with
MC
dropout
and
ensembles
as
baselines
and
show
comparable
uncertainty
estimation
results
with
only
a
small
number
of
output
heads.
Further,
LiDAR-MIMO
can
be
configured
to
be
twice
as
fast
as
MC
dropout
and
ensembles,
while
achieving
higher
mAP
than
MC
dropout
and
approaching
that
of
ensem-
bles.