---
title: Hybrid Data-Driven Predictive Control (HDDPC)
url: https://www.emergentmind.com/topics/hybrid-data-driven-predictive-control-hddpc
type: topic
---

# Hybrid Data-Driven Predictive Control (HDDPC)

Searching arXiv for the cited HDDPC and closely related papers to ground the article in current literature.
Hybrid Data-Driven Predictive Control (HDDPC) denotes a family of predictive-control methodologies that combine data-driven prediction with additional structural ingredients drawn from mechanistic modeling, state-space MPC, hybrid-system representations, or safety and robustness layers. Across the recent literature, the term does not refer to a single canonical algorithm. Instead, it covers several related constructions: hybrid mechanistic/data-driven process models embedded in MPC [2506.18344], partial-model extensions of data-enabled predictive control that bridge DeePC and MPC [2502.12467], trajectory-predictor formulations that recover classical linear MPC from data-driven predictors [2602.10936], and explicitly hybrid locomotion planners that jointly optimize contact schedules and continuous trajectories [2508.10269]. A consistent theme is that prediction is learned from data, but the controller is not purely black-box: it retains structure needed for constraints, interpretability, robustness, or computational tractability.

## 1. Terminological scope and conceptual boundaries

The recent literature uses HDDPC in both a narrow and a broad sense. In the narrow sense, it denotes a specific framework for exoskeleton locomotion that extends DeePC to hybrid walking by simultaneously planning foot contact schedules and continuous domain trajectories through a Hankel matrix-based representation with step-to-step transitions [2508.10269]. In a broader sense, the term is closely related to methods that bridge data-driven prediction and model-based predictive control without committing to a single formulation [2502.12467], or to dynamic hybrid modeling approaches that identify mechanistic/data-driven predictors later embedded in NMPC [2506.18344].

This non-uniform usage is central to the subject. One line of work treats HDDPC as a DeePC extension for hybrid systems; another treats it as a middle ground between DeePC and MPC when partial model knowledge is available; another uses “hybrid” to describe the combination of offline and online learned predictors inside NMPC [2411.13859]. This suggests that HDDPC is best understood as a research umbrella organized around structured data-driven prediction rather than as a fixed controller architecture.

A common misconception is that HDDPC is simply another name for DeePC. The literature does not support that reduction. DeePC uses measured trajectory data directly instead of an explicit model, whereas HDDPC-style formulations incorporate additional structure such as partial state-space models [2502.12467], causal predictor constraints [2311.09545], mechanistic conservation laws [2506.18344], or hybrid contact scheduling [2508.10269]. Another misconception is that HDDPC necessarily introduces a new predictive-control optimizer. In the dynamic hybrid modeling literature, the primary contribution may instead be the identification of a hybrid prediction model that is then embedded in a standard NMPC formulation [2506.18344].

## 2. Core architectural patterns

The most common HDDPC architectures in the recent literature fall into four recurring patterns.

**Mechanistic/data-driven dynamic predictors** combine a mechanistic state evolution with learned surrogates for unknown or hard-to-model quantities. In dynamic hybrid modeling, the plant is written as an index-1 DAE,
$$
\frac{\mathrm{d}\boldsymbol{x}}{\mathrm{d}t}(t)=\boldsymbol{f}(\boldsymbol{x}(t),\boldsymbol{y}(t),\boldsymbol{u}(t),\boldsymbol{p}(t)), \qquad \boldsymbol{0}=\boldsymbol{g}(\boldsymbol{x}(t),\boldsymbol{y}(t),\boldsymbol{u}(t),\boldsymbol{p}(t)),
$$
where the unknown quantities $\boldsymbol{p}(t)$ are learned from data and then reinserted into the mechanistic DAE as $\boldsymbol{ML}(\bar{\boldsymbol{x}},\bar{\boldsymbol{y}},\bar{\boldsymbol{u}})$ [2506.18344]. The resulting predictor is hybrid in the literal sense: mechanistic balances remain explicit, while difficult terms are supplied by ML surrogates.

**Partial-model DeePC/MPC bridges** split the plant into known and unknown subsystems. In HDeePC, the data-driven Hankel constraint is kept only for the unknown output component,
$$
\begin{bmatrix} U_P & Y_{U,P} & U_F & Y_{U,F} \end{bmatrix}g
=
\begin{bmatrix} u_{ini} \\ y_{u,ini} \\ u \\ y_u \end{bmatrix},
$$
while the known part is enforced through explicit model equations for $x_k$ and $y_k$ [2502.12467]. In the noiseless LTI case, this yields feasible-set equivalence and equivalent closed-loop behavior relative to DeePC and MPC under the stated assumptions [2502.12467].

**Indirect data-driven predictors embedded in MPC** identify a predictor offline and then solve a standard MPC-like optimization online. Trajectory predictive control represents the future output trajectory as
$$
y_f(t)=Pz_p(t)+Fu_f(t)+e_f(t),
$$
and with a particular state-space predictor, the resulting TPC problem becomes a special case of linear MPC with the recent input/output history as the state [2602.10936]. A plausible implication is that some HDDPC variants are best interpreted as data-derived predictor constructions whose control layer is mathematically identical to conventional MPC.

**Hybrid planners over discrete and continuous decision variables** arise in exoskeleton locomotion, where HDDPC extends DeePC to hybrid systems by separating continuous domain evolution from step-to-step transitions and optimizing both contact schedules and continuous trajectories in a receding-horizon loop [2508.10269]. Here the hybrid character refers to hybrid dynamics in the classical sense: alternating contact modes, domain transitions, and impacts.

## 3. Identification and predictor construction

When HDDPC relies on a mechanistic/data-driven model, predictor construction is often incremental rather than simultaneous. A representative workflow comprises four key steps: regularized dynamic parameter estimation, correlation analysis, data-driven model identification, and hybrid model integration [2506.18344]. In the first stage, time-varying unknown quantities are inferred by solving a dynamic optimization with a regularization term
$$
R(\boldsymbol{p}(t))=
\sum_{k=1}^{N_{\mathrm{disc}}-1}
\big(\boldsymbol{p}(t_{k+1}^{\mathrm{disc}})-\boldsymbol{p}(t_k^{\mathrm{disc}})\big)^\mathsf{T}
\boldsymbol{W}^R_k
\big(\boldsymbol{p}(t_{k+1}^{\mathrm{disc}})-\boldsymbol{p}(t_k^{\mathrm{disc}})\big),
$$
designed to prevent unrealistic jumps in inferred parameter trajectories [2506.18344]. Pearson correlation analysis then selects candidate regressors according to the criterion $|c_{x,p}| \ge \tau$, and ANNs are trained outside the DAE optimization using standard ML tools [2506.18344].

When HDDPC is based on data-enabled or subspace prediction, predictor construction typically uses Hankel or related factorized data matrices. The exoskeleton formulation retains the DeePC relation
$$
\begin{bmatrix} Z_p \\ Z_f \end{bmatrix}g
=
\begin{bmatrix} z_{\mathrm{ini}} \\ z_f \end{bmatrix},
$$
but generalizes it to hybrid trajectories by coupling continuous-domain motions with step-to-step transitions [2508.10269]. In uncertainty-aware predictive control for hybrid power plants, subspace predictive control identifies a multistep map
$$
y_N = S^\* \begin{bmatrix} y_{T_{\mathrm{ini}}} \\ u_{T_{\mathrm{ini}}} \\ u_N \end{bmatrix},
$$
where $S^\* = Y_N M^\dagger$ is obtained from a least-squares fit on measured trajectories [2502.13333].

Predictor structure is a major research issue because implicit multistep predictors can be high variance under finite data. Causality-informed DDPC argues that lack of causality is a main cause for high variance of implicit prediction, and therefore constrains the multistep predictor so that the future-input block is lower-block triangular [2311.09545]. The corresponding causal predictor can be expressed in terms of LQ factors, and the resulting causal $\gamma$-DDPC preserves the computational advantages of factorized formulations while enforcing a causal prediction structure [2311.09545].

## 4. Relation to MPC, DeePC, and sequential decision structure

HDDPC occupies the interface between direct and indirect data-driven predictive control and classical MPC. Some variants remain close to DeePC, in the sense that future trajectories are constrained to lie in the span of recorded data through a behavioral coefficient vector. Others identify a reduced predictor offline and then use a standard MPC optimization online. This distinction is analytically important because it determines whether the controller can be interpreted as a sequential decision-making process.

The literature on predictive-control optimality states that closed-loop optimality is not guaranteed by prediction accuracy alone. What matters is whether the predictive controller is self-consistent in the Bellman sense, namely whether its value function satisfies
$$
V^{\mathrm{PC}}(s)=\min_a \,\ell(s,a)+\gamma V^{\mathrm{PC}}(f(s,a)).
$$
Generic DDPC formulations need not have this property, because their predictors may not correspond to repeated simulation of an underlying one-step map [2405.17892]. By contrast, TPC with the state-space predictor is literally equivalent to classical linear MPC, and therefore inherits the mature theory of linear MPC [2602.10936]. This supports a useful distinction within HDDPC research: some methods hybridize data and structure strongly enough to recover standard MPC semantics, whereas others remain direct trajectory-optimization schemes whose optimality theory is more delicate.

Bridging results formalize this interface. HDeePC is positioned explicitly as a middle ground between purely data-driven predictive control and fully model-based MPC [2502.12467]. Data-driven predictive control with estimated prediction matrices likewise estimates MPC prediction matrices directly from data offline, then solves an online quadratic program with similar structure and complexity as linear MPC [2104.04972]. A plausible implication is that the most MPC-like HDDPC methods are those that compress data into a predictor class with one-step or state-space semantics.

## 5. Robustness, noise, and safety layers

Robustness is a defining concern for HDDPC because data-driven predictors are sensitive to finite-sample effects, noise, and operating-regime mismatch. Several lines of work address this problem by imposing structure, separating subspaces, or adding a safeguarding controller.

Noise-tolerant hybrid predictive control focuses on the effect of measurement noise on Hankel matrices. The proposed NTDPC framework uses singular value decomposition to separate dominant dynamics from noise-dominated singular directions in reduced-order Hankel matrices, yielding the compact predictor
$$
\hat{\mathbf y}_N(k)=\mathbf P_1\mathbf z_{\text{ini},m}(k)+\mathbf P_2\mathbf u_N(k),
$$
and introduces the sensitivity index
$$
I_s=\frac{\sigma_{\max}^2(\Sigma_2)}{\sigma_{\min}^2(\Sigma_1)}
$$
to support horizon selection under different noise levels [2506.20780]. Simulation studies report improved robustness and efficiency relative to existing hybrid methods, with a reported dominant factorization cost reduction of about 11\% relative to SPC in the simplified SISO comparison [2506.20780].

Regularization-based work in stochastic DDPC similarly argues that regularization is useful only when it suppresses the appropriate noise-dominated directions. The two-stage $\gamma$-DDPC formulation separates initial-condition fitting from future-performance optimization through an LQ decomposition and reduces tuning burden by optimizing only the future-performance subspace online [2203.10846]. Causality-informed DDPC makes a complementary point: enforcing causal structure reduces variance and improves performance under stochastic noise and process nonlinearity, with no excess computational cost relative to generic $\gamma$-DDPC in the reported stochastic LTI study [2311.09545].

A distinct robustness strategy is architectural rather than statistical. The two-component safeguarding framework combines a data-driven or learning-based predictive controller with a model-free high-gain funnel controller:
$$
u(t)=\mu(t,x)+a_\tau(t,e_2(t))\,u_{\rm FC}(t).
$$
The predictive component provides performance, while the fallback controller guarantees the output-tracking constraint
$$
\|y(t)-y_{\rm ref}(t)\|<\frac{1}{\sigma(t)}\qquad\forall t\ge 0
$$
when the predictive controller cannot guarantee safety [2505.19131]. This is a different sense of “hybrid”: predictive optimization and reactive safety feedback coexist in a supervisory switching architecture.

## 6. Application domains and representative implementations

The application space of HDDPC-style methods is heterogeneous, and the nature of the hybridization varies by domain.

| Domain | HDDPC-style formulation | Reported role |
|---|---|---|
| Chemical and biochemical processes | Dynamic hybrid model identification with mechanistic DAE plus ANN surrogates | Predictor construction for NMPC [2506.18344] |
| Exoskeleton locomotion | Hankel-based hybrid planner with contact scheduling and S2S transitions | Robust and reactive walking on Atalante [2508.10269] |
| Hybrid power plants | Uncertainty-aware SPC supervisory controller for wind, solar, and battery | Load tracking under weather uncertainty [2502.13333] |
| Heavy hydraulic robots | Offline LSTM-MLP predictor plus online mismatch-learning MLP in NMPC | Tracking and energy management on a 22-ton excavator [2411.13859] |

In process systems, the control-focused case study in dynamic hybrid modeling embeds the identified hybrid model as the controller model in an NMPC framework for a water-tank research plant with controlled variables given by tank holdups, manipulated variables given by setpoints for FIC 1 and FIC 2, a sampling time of 8 s, and a prediction/control horizon of 180 s [2506.18344]. In this sense, the work is foundational for HDDPC rather than a new MPC algorithm: it builds the hybrid model that predictive control relies on [2506.18344].

In locomotion, HDDPC is an explicit hybrid-system planner. It uses experimentally collected motion segments in a Hankel library to represent feasible continuous-domain motions, feasible step-to-step transitions, and their coupling, while jointly optimizing contact schedules and continuous trajectories in receding horizon [2508.10269]. The framework is validated on the Atalante exoskeleton through simulation studies and hardware tests, with the reported outcome of stable walking, improved robustness, and reactive recovery from disturbances [2508.10269].

In power systems, the supervisory controller coordinates a 4 MW wind farm, a 4 MW solar farm, and a 4 MW battery using SPC and a probabilistic lower-confidence wind bound. With prediction horizon $N=20$, initialization horizon $T_{\mathrm{ini}}=20$, data length $T=1000$, and a 20 s sampling interval, the reported open-loop normalized prediction errors are about 6.5\% for wind, 8.5\% for solar, 10\% for battery, and 6.1\% for total plant output, with mean solve time about 0.3 s [2502.13333].

In hydraulic robotics, the proposed HDDPC architecture combines an offline SSMP model with an online mismatch-compensation model. The hybrid predictor
$$
X_{t+1:t+N}
=
G(F(X_t^h,U_{t-1}^h),U_{t:t+N-1})
+
H(X_t^h,U_{t-1}^h,U_{t:t+N-1})
+
X_{t-1}
$$
is embedded in NMPC and optimized by gradient descent with an adaptive learning rate [2411.13859]. The paper reports that the online model reduces ARMSE by at least 50\% compared with offline-only prediction under heavy-load interaction, and that the controller runs in real time at about 50 Hz with cycle times roughly 5.5 ms to 15.4 ms depending on horizon and network size [2411.13859].

## 7. Open issues, limitations, and research directions

The recent literature identifies several unresolved issues. First, terminology remains unsettled. Some papers use HDDPC for explicitly hybrid dynamical systems such as locomotion [2508.10269], others for partial-model or mechanistic/data-driven bridges [2502.12467; 2506.18344], and others for offline/online learned predictor combinations [2411.13859]. This suggests that comparative taxonomy remains an open editorial and methodological problem.

Second, noise and limited-data effects remain central. Mechanistic/data-driven identification depends strongly on regularization weights and on whether unknown terms can be meaningfully absorbed into latent quantities such as $\boldsymbol{p}(t)$ [2506.18344]. Hankel-based hybrid methods depend on persistent excitation, horizon selection, and spectral separation between dynamics and noise [2506.20780]. Causal and subspace-structured formulations reduce variance, but they do not eliminate the need for representative data [2311.09545; 2203.10846].

Third, optimality theory is incomplete for generic direct data-driven predictors. The literature explicitly concludes that better prediction accuracy alone does not ensure closed-loop optimality and that the decisive property is self-consistent sequential decision structure rather than the model-based/model-free dichotomy [2405.17892]. This favors HDDPC constructions that can be cast as state-space or one-step predictors, as in TPC with the state-space predictor [2602.10936], but leaves open the general theory for implicit trajectory-based schemes.

Fourth, many practical studies retain strong assumptions. Examples include exact state initialization in HDeePC [2502.12467], Gaussian weather uncertainty and unconstrained battery state of charge in hybrid power plants [2502.13333], or the absence of detailed theoretical validation in the excavator NMPC framework [2411.13859]. In process-control settings, offset-free NMPC is noted as relevant but outside scope [2506.18344].

Overall, HDDPC design is converging around a common principle: combine data-driven prediction with just enough structure to recover feasibility, interpretability, robustness, or mature MPC theory. The specific structural prior may be mechanistic equations, partial state-space knowledge, causal multistep prediction, invariant-set certification, hybrid contact logic, or a safety fallback. What unifies the field is not a single algorithmic template, but the systematic use of structure to make data-driven predictive control operational in regimes where purely black-box prediction is insufficient.

Source: https://www.emergentmind.com/topics/hybrid-data-driven-predictive-control-hddpc