eess.SYMar 16, 2026

Physicochemical-Neural Fusion for Semi-Closed-Circuit Respiratory Autonomy in Extreme Environments

Authors: Phillip Kingston, Nicholas Johnston

Organizations: Member of Technical Staff, Galactic Bioware

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

This paper introduces Galactic Bioware's Life Support System, a semi-closed-circuit breathing apparatus designed for integration into a positive-pressure firefighting suit and governed by an AI control system. The breathing loop incorporates a soda lime CO2 scrubber, a silica gel dehumidifier, and pure O2 replenishment with finite consumables. One-way exhaust valves maintain positive pressure while creating a semi-closed system in which outward venting gradually depletes the gas inventory. Part I develops the physicochemical foundations from first principles, including state-consistent thermochemistry, stoichiometric capacity limits, adsorption isotherms, and oxygen-management constraints arising from both fire safety and toxicity. Part II introduces an AI control architecture that fuses three sensor tiers, external environmental sensing, internal suit atmosphere sensing (with triple-redundant O2 cells and median voting), and firefighter biometrics. The controller combines receding-horizon model-predictive control (MPC) with a learned metabolic model and a reinforcement learning (RL) policy advisor, with all candidate actuator commands passing through a final control-barrier-function safety filter before reaching the hardware. This architecture is intended to optimize performance under unknown mission duration and exertion profiles. In this paper we introduce an 18-state, 3-control nonlinear state-space formulation using only sensors viable in structural firefighting, with triple-redundant O2 sensing and median voting. Finally, we introduce an MPC framework with a dynamic resource scarcity multiplier, an RL policy advisor for warm-starting, and a final control-barrier-function safety filter through which all actuator commands must pass, demonstrating 18-34% endurance improvement in simulation over PID baselines while maintaining tighter physiological and fire-safety margins.

Figures & tables

Figure 1: Control-oriented architecture of the semi-closed positive-pressure breathing loop. Solid lines illustrate gas flow and dashed lines sensor inputs / control links. Moist exhaled gas is drawn through the soda-lime scrubber first, then the downstream silica-gel dehumidifier, before O 2 replenishment and return to the breathing zone. Outward venting through one-way exhaust valves makes the suit semi-closed; the controller uses external, in-suit, and biometric sensing to regulate O 2 injection, fan speed, and scrubber bypass.
SensorMeasurementRange / Resolution
Radiant heat flux sensorExternal thermal threat q˙rad\dot{q}_{\mathrm{rad}}0– 200 kW m−2200\text{\,}\mathrm{kW}\text{\,}{\mathrm{m}}^{-2}
External thermistor (shielded)Ambient temperature TextT_{\mathrm{ext}}−- 40 to 500 \SIUnitSymbolCelsius500\text{\,}\mathrm{\SIUnitSymbolCelsius} , ±\pm 2 \SIUnitSymbolCelsius2\text{\,}\mathrm{\SIUnitSymbolCelsius}
Toxic gas sensor (MOS array)CO, HCN, NO x (external)Multi-gas, semi-quantitative
Barometric pressure sensorAmbient pressure PaP_{a}800– 1100 hPa1100\text{\,}\mathrm{hPa} , ±\pm 0.5 hPa0.5\text{\,}\mathrm{hPa}
Table 2
SensorMeasurementRange / Resolution
NDIR CO 2 sensorIn-suit xCO2x_{\mathrm{CO_{2}}}0– 10 %10\text{\,}\mathrm{\%} , ±\pm 0.01 %0.01\text{\,}\mathrm{\%}
Galvanic O 2 ( ×3\times 3 , median voting)In-suit xO2x_{\mathrm{O_{2}}}0– 100 %100\text{\,}\mathrm{\%} , ±\pm 0.1 %0.1\text{\,}\mathrm{\%}
Capacitive RH sensorIn-suit relative humidity0– 100 %100\text{\,}\mathrm{\%} RH, ±\pm 1.5 %1.5\text{\,}\mathrm{\%}
In-suit thermistor (breathing zone)Breathing gas temperature Tsuit,bzT_{\mathrm{suit,bz}}10 to 60 \SIUnitSymbolCelsius60\text{\,}\mathrm{\SIUnitSymbolCelsius} , ±\pm 0.5 \SIUnitSymbolCelsius0.5\text{\,}\mathrm{\SIUnitSymbolCelsius}
In-suit thermistor (torso)Suit interior temperature Tsuit,torsoT_{\mathrm{suit,torso}}10 to 70 \SIUnitSymbolCelsius70\text{\,}\mathrm{\SIUnitSymbolCelsius} , ±\pm 0.5 \SIUnitSymbolCelsius0.5\text{\,}\mathrm{\SIUnitSymbolCelsius}
Thermocouple (K-type)Scrubber bed temperature TbedT_{\mathrm{bed}}−- 40 to 1000 \SIUnitSymbolCelsius1000\text{\,}\mathrm{\SIUnitSymbolCelsius} , ±\pm 1 \SIUnitSymbolCelsius1\text{\,}\mathrm{\SIUnitSymbolCelsius}
Table 3
SensorMeasurementRange / Resolution
Chest-strap ECG (dry electrode)Heart rate (HR)30– 240 bpm240\text{\,}\mathrm{bpm} , ±\pm 1 bpm1\text{\,}\mathrm{bpm}
Chest-strap ECGHeart rate variability (HRV)R–R intervals, 1 ms1\text{\,}\mathrm{ms}
Torso IMU (accelerometer + gyro)Activity level / posture3-axis, 100 Hz100\text{\,}\mathrm{Hz}
Wrist PPG sensorRedundant HR, perfusion index30– 240 bpm240\text{\,}\mathrm{bpm} , ±\pm 3 bpm3\text{\,}\mathrm{bpm}
Wrist accelerometerWrist motion / activity3-axis, 50 Hz50\text{\,}\mathrm{Hz}
Table 4
Figure 2: AI control architecture with explicit safety gating. External, in-suit, and biometric sensors feed the EKF-based sensor-fusion and state-estimation layer. The learned metabolic model provides physiological estimates to the MPC, while the RL policy advisor supplies a warm-start policy hint during nominal operation and a fallback candidate action if the MPC fails or times out. All candidate actuator commands pass through the control-barrier-function safety filter before reaching the actuators and, through them, the physical life-support plant and firefighter.
Figure 3: Oxygen tank depletion curves for Scenario A. The MPC controller’s dynamic conservation extends endurance by modulating O 2 delivery rate as the tank depletes.
More in this topic

Safety-Critical Control

Safety-critical control designs controllers that keep physical systems within hard safety constraints despite uncertainty, disturbances, and limited actuation.

See all 128 papers

Explore similar work

CardsList
Sep 18, 2026

Adaptive Uncertainty-Aware Modeling and Stochastic Radial Basis Function Predictive Control for Personalized Fluid Resuscitation

This paper presents a novel framework integrating Bayesian physiological modeling with optimal control strategies to achieve uncertainty-aware, personalized hemodynamic regulation during fluid resuscitation. An uncertainty-aware variational autoencoder state-space model (UVAE-SSM) was first developed to capture the dynamical relationship between mean arterial pressure (MAP) and fluid infusion using limited data, while explicitly modeling aleatoric uncertainty (i.e., randomness in the measurements, such as sensor noise). Then, a Bayesian nonlinear state-space model (BNSSM) was developed by utilizing Bayesian neural networks (BNNs) to capture epistemic uncertainty arising from physiological and patient-specific variability, enabling the creation of a virtual patient generator (VPG). Building on this uncertainty-aware modeling framework, a stochastic radial basis function model predictive control (sRBF-MPC) algorithm was designed to track the MAP target while satisfying physiological constraints. Finally, an online fine-tuning algorithm was developed to adapt the nominal UVAE-SSM using streaming VPG data, enabling progressive personalization during closed-loop therapy. Simulation results across unseen animal subjects and an independent human clinical dataset demonstrated the strong predictive accuracy and cross-population generalizability of the UVAE-SSM and BNSSM models. Closed-loop evaluations confirmed that the proposed sRBF-MPC framework achieved stable MAP regulation while providing better risk-aware control compared to quadratic MPC (Q-MPC) and stochastic quadratic MPC (sQ-MPC). Overall, the proposed framework accounts for inter- and intra-patient variability through online model adaptation, offering a promising step toward uncertainty-aware, personalized hemodynamic modeling and control in critical care.

Elham Estiri, Hossein Mirinejad

School of Engineering, College of Aeronautics and Engineering, Kent State University, Kent, OH 44242 USA

Model Predictive ControlHealthcareAdaptive ControlState Space Models
AskPDF
Jun 3, 2026

VentAgent: When LLMs Learn to Breathe -- Multi-Objective Arbitration for ARDS Ventilation

Mechanical ventilation for Acute Respiratory Distress Syndrome (ARDS) requires balancing competing physiological goals, including oxygenation, lung protection, and acid-base homeostasis. However, current data-driven methods, especially those imitating retrospective Electronic Health Records (EHR), often suffer from imitation bias. They may capture superficial correlations from inconsistent clinical demonstrations, such as associating passive ventilator settings with survival because such settings are common in stable patients, and thus fail to generalize to volatile or out-of-distribution phenotypes. Standard Reinforcement Learning (RL) methods also struggle with the adversarial trade-offs of critical care and often produce opaque policies with limited clinical interpretability. To address these limitations, we introduce VentAgent, a hierarchical framework in which Large Language Models (LLMs) act as transparent arbitrators for mechanical ventilation. We reformulate ventilation control as a dynamic Multi-Objective Arbitration process rather than single-objective optimization. VentAgent decomposes decision-making into three interpretable stages: Perception, Planning, and Orchestration. By leveraging the semantic reasoning capabilities of LLMs, it synthesizes strategies from heterogeneous experts and resolves conflicting clinical priorities through an explicit coordination mechanism. Evaluations on a high-fidelity physiological simulator show that VentAgent outperforms state-of-the-art RL and classical control baselines. Moreover, it converts control decisions into human-readable reasoning chains, offering a safer, more interpretable, and adaptable paradigm for critical care automation.

Teqi Hao, Yuxuan Fu, Xiaoyu Tan +4

Tencent Youtu Lab Shanghai, Shanghai, China · Artificial Intelligence Innovation and Incubation Institute, Fudan University Shanghai, Shanghai, China · School of Electronic and Electrical Engineering, Shanghai University of Engineering Science Shanghai, Shanghai, China

Language Model-Based ControlFeedback Control
AskPDF
Jun 16, 2026

Memory-Efficient Meta-Reinforcement Learning for Adaptive Safety-Critical Control in Adversarial Spacecraft Proximity Operations

Autonomous spacecraft rendezvous and proximity operations (RPO) require controllers that guarantee safety under thrust constraints while minimizing fuel expenditure. Input-constrained control barrier functions (ICCBFs) provide a control method for nonlinear systems with actuation constraints that construct a forward-invariant safe set. Previous work has shown that learning class-K\mathcal{K} functions defining the ICCBF recursion via meta reinforcement learning (meta-RL) yields a robust, non-greedy approach to safety-critical control in RPO. This paper extends that framework further by investigating the performance of three recurrent network architectures (Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Selective State Space Model (Mamba)) and two training algorithms (Proximal Policy Optimization (PPO) and Soft Actor Critic (SAC)) to identify the best setup for tuning ICCBF class-K functions via meta-RL. In addition to cooperative test cases, performance is evaluated in the presence of adversarial behavior where the target spacecraft behaves in a way that worsens the safety of the chaser spacecraft. Results indicate that state space models such as Mamba when used with PPO achieve superior task completion, safety, and fuel-savings compared to other architectures, across all cooperative and uncooperative scenarios tested.

Alejandro Posadas-Nava, Richard Linares, Minduli Wijayatunga

Researcher, AeroAstro, MIT, 77 Massachusetts Avenue, Cambridge, MA 02139-4307. · Associate Professor and Rockwell International Career Development Professor, AeroAstro, MIT, 77 Massachusetts Avenue, Cambridge, MA 02139-4307. · Assistant Professor, Department of Aerospace Engineering, University of Illinois, Urbana-Champaign, 104 S Wright St, Urbana, IL 61801.

Spacecraft Rendezvous and Proximity OperationsControl Barrier FunctionsMeta-Reinforcement LearningSafe RLState Space Models
AskPDF