A computational study of the use of an optimization-based method for simulating large multibody systems.
The present work aims at comparing the performance of several quadratic programming (QP) solvers for simulating large-scale frictional rigid-body systems. Traditional time-stepping schemes for simulation of multibody systems are formulated as linear complementarity problems (LCPs) with copositive matrices. Such LCPs are generally solved by means of Lemke-type algorithms and solvers such as the PATH solver proved to be robust. However, for large systems, the PATH solver or any other pivotal algorithm becomes unpractical from a computational point of view. The convex relaxation proposed by one of the authors allows the formulation of the integration step as a QPD, for which a wide variety of state-of-the-art solvers are available. In what follows we report the results obtained solving that subproblem when using the QP solvers MOSEK, OOQP, TRON, and BLMVM. OOQP is presented with both the symmetric indefinite solver MA27 and our Cholesky reformulation using the CHOLMOD package. We investigate computational performance and address the correctness of the results from a modeling point of view. We conclude that the OOQP solver, particularly with the CHOLMOD linear algebra solver, has predictable performance and memory use patterns and is far more competitive for these problems than are the other solvers.
- Research Organization:
- Argonne National Laboratory (ANL)
- Sponsoring Organization:
- SC; NSF
- DOE Contract Number:
- AC02-06CH11357
- OSTI ID:
- 966335
- Report Number(s):
- ANL/MCS/JA-62301
- Journal Information:
- Optimization Methods and Software, Journal Name: Optimization Methods and Software Journal Issue: 6 ; 2009 Vol. 24
- Country of Publication:
- United States
- Language:
- ENGLISH
Similar Records
Parallel and serial solution of large-scale linear complementarity problems
A linear complementarity approach to the frictionless gripper problem