Convex Chance-Constrained Stochastic Control under Uncertain Specifications with Application to Learning-Based Hybrid Powertrain Control

2026-01-26

AI Summary

This work addresses the challenge of stochastic control under non-Gaussian uncertainties in reference trajectories and operational constraints, where conventional approaches struggle to simultaneously satisfy probabilistic constraints and preserve favorable optimization properties. The authors propose a strictly convex chance-constrained stochastic control framework that jointly optimizes control inputs and risk allocation. Notably, this is the first method to guarantee strict convexity of the chance-constrained problem under general non-Gaussian uncertainty, thereby ensuring solution uniqueness and continuity. By integrating machine learning to identify nonlinear dynamics amenable to exact linearization, the framework yields an end-to-end deployable model predictive control scheme. Experimental validation on a hybrid powertrain demonstrates that the approach maintains computational efficiency and solution stability while achieving high satisfaction rates of probabilistic constraints.

Technology Category

• Reasoning under Uncertainty: Stochastic Optimization
• Search and Optimization: Non-convex Optimization
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This paper presents a strictly convex chance-constrained stochastic control framework that accounts for uncertainty in control specifications such as reference trajectories and operational constraints. By jointly optimizing control inputs and risk allocation under general (possibly non-Gaussian) uncertainties, the proposed method guarantees probabilistic constraint satisfaction while ensuring strict convexity, leading to uniqueness and continuity of the optimal solution. The formulation is further extended to nonlinear model-based control using exactly linearizable models identified through machine learning. The effectiveness of the proposed approach is demonstrated through model predictive control applied to a hybrid powertrain system.

Problem

• chance-constrained
• stochastic control
• uncertain specifications
• convex optimization
• hybrid powertrain

Innovation

• convex chance-constrained control
• stochastic control
• risk allocation
• machine learning-based modeling
• hybrid powertrain control