A particle swarm optimization with a reduced-subspace trust-region safeguard for contact-rich controller tuning
Abstract
Contact-rich robotic insertion is challenging because uncertainty in alignment, friction, and contact conditions can lead to unsuccessful assembly, excessive contact forces, and jamming. Designing a reliable controller therefore requires balancing insertion performance, robustness, and recovery from unexpected contact. In this paper, we propose PSO+TR, a derivative-free optimization (DFO) method that combines the exploratory search of particle swarm optimization (PSO) with a trust-region (TR) procedure for local refinement to improve the search process when progress stagnates. We apply the method to derivative-free policy optimization of an interpretable robotic insertion controller, jointly tuning its motion, feedback, and recovery parameters while preserving its predefined control structure. The proposed approach is evaluated on 93 eligible benchmark problems from the bound-constrained programs (BCP) collection and a synthetic contact-rich planar insertion task under uncertain operating conditions. Three random seeds per benchmark problem yield 279 matched problem--seed instances per method. PSO+TR reaches the prescribed target on 228 of these instances (81.72\%), the highest observed target-attainment rate among the five compared methods, which also include PSO, randomized black-box optimization (VRBBO), matrix adaptation evolution strategy (MAES), and differential evolution (DE). Across eight robotic optimizer seeds, the deployed controller-selection pipeline achieves 97.78\% completion under development conditions and 58.00\% under withheld stress conditions, compared with 91.22\% and 31.12\%, respectively, for the fixed staged controller. The stress violation rate is reduced from 20.69\% to 2.19\%. These findings support combining global and local search for DFO and structured contact-rich controller tuning. The synthetic planar results require validation on physical robots.
Related
- An Infeasible Method with Feasibility Safeguard for Nonsmooth Composite Optimization Over Manifolds
- Active Subspace-Guided Free-Form Deformation with Sinkhorn Autoencoders for Reduced-Order Modelling of Parametrised Shape Problems
- Sparse descent subspace-Newton thresholding algorithm for sparse optimization problems
- A note on the complexity of random subspace model-based methods for derivative-free optimization
- Forgetting matters: when subspace optimization accelerates without the strong convexity parameter
BibTeX
@misc{kimiaei2026particle,
title = {{A particle swarm optimization with a reduced-subspace trust-region safeguard for contact-rich controller tuning}},
author = {Morteza Kimiaei and Roya Khalili-Amirabadi and Mohsen Jalaeian-Farimani},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.20032},
eprint = {2610.20032},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.20032},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - A particle swarm optimization with a reduced-subspace trust-region safeguard for contact-rich controller tuning
AU - Morteza Kimiaei
AU - Roya Khalili-Amirabadi
AU - Mohsen Jalaeian-Farimani
PY - 2026
DA - 2026/10/14
PB - arXiv
DO - 10.48550/arxiv.2610.20032
UR - https://arxiv.org/abs/2610.20032
AB - Contact-rich robotic insertion is challenging because uncertainty in alignment, friction, and contact conditions can lead to unsuccessful assembly, excessive contact forces, and jamming. Designing a reliable controller therefore requires balancing insertion performance, robustness, and recovery from unexpected contact. In this paper, we propose PSO+TR, a derivative-free optimization (DFO) method that combines the exploratory search of particle swarm optimization (PSO) with a trust-region (TR) procedure for local refinement to improve the search process when progress stagnates. We apply the method to derivative-free policy optimization of an interpretable robotic insertion controller, jointly tuning its motion, feedback, and recovery parameters while preserving its predefined control structure. The proposed approach is evaluated on 93 eligible benchmark problems from the bound-constrained programs (BCP) collection and a synthetic contact-rich planar insertion task under uncertain operating conditions. Three random seeds per benchmark problem yield 279 matched problem--seed instances per method. PSO+TR reaches the prescribed target on 228 of these instances (81.72\%), the highest observed target-attainment rate among the five compared methods, which also include PSO, randomized black-box optimization (VRBBO), matrix adaptation evolution strategy (MAES), and differential evolution (DE). Across eight robotic optimizer seeds, the deployed controller-selection pipeline achieves 97.78\% completion under development conditions and 58.00\% under withheld stress conditions, compared with 91.22\% and 31.12\%, respectively, for the fixed staged controller. The stress violation rate is reduced from 20.69\% to 2.19\%. These findings support combining global and local search for DFO and structured contact-rich controller tuning. The synthetic planar results require validation on physical robots.
ER -