Belief-Informed Hybrid Control with Almost-Sure Target-Set Convergence
Abstract
Controlling a hybrid system to a target set under parameter uncertainty can require informative actions that temporarily drive the system state away from the specified set. We propose a belief-informed dual-control algorithm that combines belief-space receding-horizon selection with an expected-decrease constraint on a nonnegative target-set progress function. To accommodate exploratory deviations, a scalar controller state bounds the constraint's cumulative slack. Our algorithm's two-step lookahead selection uses predicted observations to update the parameter belief before evaluating the subsequent action's admissibility. Under distance-comparison bounds, correct conditional prediction, and recursive feasibility, we prove almost-sure target-set convergence at decision times and bound both the sum of expected progress-function values and the expected neighborhood-entry time. Upper confidence bounds extend these convergence guarantees to bounded model samples with summable error probabilities. In planar regulation with an unknown control direction, we verify recursive feasibility: the proposed two-step selection reduces the Euclidean state norm below 0.01 within 11 decisions for either sign, whereas a myopic one-step selection loses admissibility immediately after zero input. In a simulated bimanual assembly task, our algorithm's one-step implementation uses clearance feedback to complete the assembly under nominal friction, yielding a 96.4% lower infinity-norm relative-position error than the reference-tracking baseline at the method's completion time. At lower friction, its posterior conditioning successfully detects an empty admissible set, whereas a fixed-prior alternative admits an action that violates the conditional decrease constraint. Project page: https://clintonenwerem.com/belief-hybrid-control/.
Related
- On the Convergence of Belief Propagation for Multipath Data Association in Target Tracking
- Blind Random Search with Noisy Measurements: Almost Sure Convergence and Convergence Rates
- Belief Propagation-Informed Tesseract Decoding of Quantum LDPC Codes
- Blind Random Search with Noisy Loss Measurements: Averaging, Thresholding, and Almost Sure Convergence
- Almost everywhere convergence of mock Fourier series for the middle-fourth Cantor measure
BibTeX
@misc{enwerem2026beliefinformed,
title = {{Belief-Informed Hybrid Control with Almost-Sure Target-Set Convergence}},
author = {Clinton Enwerem and Saleh Kemal and John S. Baras and Calin Belta},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.07674},
eprint = {2610.07674},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.07674},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Belief-Informed Hybrid Control with Almost-Sure Target-Set Convergence
AU - Clinton Enwerem
AU - Saleh Kemal
AU - John S. Baras
AU - Calin Belta
PY - 2026
DA - 2026/10/06
PB - arXiv
DO - 10.48550/arxiv.2610.07674
UR - https://arxiv.org/abs/2610.07674
AB - Controlling a hybrid system to a target set under parameter uncertainty can require informative actions that temporarily drive the system state away from the specified set. We propose a belief-informed dual-control algorithm that combines belief-space receding-horizon selection with an expected-decrease constraint on a nonnegative target-set progress function. To accommodate exploratory deviations, a scalar controller state bounds the constraint's cumulative slack. Our algorithm's two-step lookahead selection uses predicted observations to update the parameter belief before evaluating the subsequent action's admissibility. Under distance-comparison bounds, correct conditional prediction, and recursive feasibility, we prove almost-sure target-set convergence at decision times and bound both the sum of expected progress-function values and the expected neighborhood-entry time. Upper confidence bounds extend these convergence guarantees to bounded model samples with summable error probabilities. In planar regulation with an unknown control direction, we verify recursive feasibility: the proposed two-step selection reduces the Euclidean state norm below 0.01 within 11 decisions for either sign, whereas a myopic one-step selection loses admissibility immediately after zero input. In a simulated bimanual assembly task, our algorithm's one-step implementation uses clearance feedback to complete the assembly under nominal friction, yielding a 96.4% lower infinity-norm relative-position error than the reference-tracking baseline at the method's completion time. At lower friction, its posterior conditioning successfully detects an empty admissible set, whereas a fixed-prior alternative admits an action that violates the conditional decrease constraint. Project page: https://clintonenwerem.com/belief-hybrid-control/.
ER -