This brief presents a suite of computationally efficient methods for
bounding trajectories of dynamical systems with multi-dimensional
intervals, or 'boxes'. It explains the importance of bounding
trajectories for evaluating the robustness of systems in the face of
parametric uncertainty, and for verification or control synthesis
problems with respect to safety and reachability properties. The methods
presented make use of:
- interval analysis;
- monotonicity theory;
- contraction theory; and
- data-driven techniques that sample trajectories.
The methods are implemented in an accompanying open-source Toolbox for
Interval Reachability Analysis.
This brief provides a tutorial description of each method, focusing on
the requirements and trade-offs relevant to the user, requiring only
basic background on dynamical systems. The second part of the brief
describes applications of interval reachability analysis. This makes the
brief of interest to a wide range of academic researchers, graduate
students, and practising engineers in the field of control and
verification.