Smallest Ellipsoid Containing $p$-Sum of Ellipsoids with Application to Reachability Analysis
We study the problem of ellipsoidal bounding of convex set-valued data, where the convex set is obtained by the $p$-sum of finitely many ellipsoids, for any real $p\geq 1$. The notion of $p$-sum appears in the Brunn-Minkowski-Firey theory in convex analysis, and generalizes several well-known set-va...
Saved in:
Main Author | |
---|---|
Format | Journal Article |
Language | English |
Published |
20.06.2018
|
Subjects | |
Online Access | Get full text |
DOI | 10.48550/arxiv.1806.07621 |
Cover
Summary: | We study the problem of ellipsoidal bounding of convex set-valued data, where
the convex set is obtained by the $p$-sum of finitely many ellipsoids, for any
real $p\geq 1$. The notion of $p$-sum appears in the Brunn-Minkowski-Firey
theory in convex analysis, and generalizes several well-known set-valued
operations such as the Minkowski sum of the summand convex sets (here,
ellipsoids). We derive an outer ellipsoidal parameterization for the $p$-sum of
a given set of ellipsoids, and compute the tightest such parameterization for
two optimality criteria: minimum trace and minimum volume. For such optimal
parameterizations, several known results in the system-control literature are
recovered as special cases of our general formula. For the minimum volume
criterion, our analysis leads to a fixed point recursion over a scalar that
parameterizes the shape matrix of the outer ellipsoid. This recursion is proved
to be contractive, and found to converge fast in practice. We apply these
results to compute the forward reach sets for a linear control system subject
to different convex set-valued uncertainty models for the initial condition and
control, generated by varying $p\in[1,\infty]$. Our numerical results show that
the proposed fixed point algorithm offers more than two orders of magnitude
speed-up in computational time for $p=1$, compared to the existing semidefinite
programming approach without significant effect on the numerical accuracy. For
$p>1$, the reach set computation results reported here are novel. Our results
are expected to be useful in real-time safety critical applications such as
decision making for collision avoidance of autonomous vehicles, where the
computational time-scale for reach set calculation needs to be much smaller
than the vehicular dynamics time-scale. |
---|---|
DOI: | 10.48550/arxiv.1806.07621 |