Epsilon local rigidity and numerical algebraic geometry
Andrew Frohmader and Alexander Heaton
Contact the author: Please use for correspondence this email.
Submission date: 06. Nov. 2020
MSC-Numbers: 70B15, 65D17, 14Q99
Keywords and phrases: rigidity, kinematics, homotopy continuation
Download full preprint: PDF (1884 kB)
Link to arXiv: See the arXiv entry of this preprint.
DOI number (of the published article): 10.1142/S0219498822500098
A well-known combinatorial algorithm can decide generic rigidity in the plane by determining if the graph is of Pollaczek-Geiringer-Laman type. Methods from matroid theory have been used to prove other interesting results, again under the assumption of generic configurations. However, configurations arising in applications may not be generic. We present Theorem 5 and its corresponding Algorithm 1 which decide if a configuration is epsilon-locally rigid, a notion we define. A configuration which is epsilon-locally rigid may be locally rigid or flexible, but any continuous deformations remain within a sphere of radius epsilon in configuration space. Deciding epsilon-local rigidity is possible for configurations which are smooth or singular, generic or non-generic. We also present Algorithms 2 and 3 which use numerical algebraic geometry to compute a discrete-time sample of a continuous flex, providing useful visual information for the scientist.