Adaptive Building Envelope Robotics for Energy-Neutral Retrofit

Thesis Abstract

This study addresses the persistent inefficiencies in aging building envelopes that restrict energy performance, indoor environmental quality, and retrofit adaptability in urban contexts. Contemporary retrofit practices often rely on static, labor-intensive interventions that fail to adapt to dynamic environmental conditions and occupant behaviors, resulting in suboptimal energy savings and higher lifecycle costs. The aim is to develop and validate an adaptive building envelope robotics framework that enables energy-neutral retrofit through autonomous, modular, and programmable envelope elements. Specific objectives are to (1) design a modular robotic envelope system capable of autonomous sensing, actuation, and reconfiguration for solar shading, insulation, and airtightness; (2) formulate a control strategy integrating model predictive control (MPC) with reinforcement learning to optimize envelope performance under varying weather and occupancy scenarios; (3) evaluate energy performance, occupant comfort, and retrofit cost implications across representative climates using a multi-scale simulation-empirical workflow; (4) assess robustness, reliability, and maintenance requirements of the robotic system in real-world retrofit campaigns; and (5) develop guidelines for scaling the technology to standard urban building types. The methodology combines a mixed-methods approach anchored in design research and empirical evaluation. The population includes 60 mid-rise residential and commercial buildings across three climate zones representing temperate, hot-humid, and dry climates. A sample of 18 buildings will be instrumented with a prototype adaptive envelope robot module on two façade segments per building over a 12-month monitoring period. Data collection instruments comprise high-resolution energy meters, external and internal environmental sensors (temperature, humidity, solar irradiance, wind speed), occupant comfort surveys, indoor air quality monitors, and the robotic system’s performance logs (actuation events, fault rates, maintenance intervals). Validity and reliability are ensured through calibration protocols for sensors, redundancy in measurements, and a pilot test phase with three buildings prior to full deployment. Analytical techniques include regression analysis to quantify energy savings attributable to the robotic envelope, time-series analysis for environmental condition trends, and a joint probability framework to model uncertainty in performance. The study applies model predictive control (MPC) to forecast thermal loads and reinforcement learning (specifically proximal policy optimization) to adapt control policies based on observed performance. A life-cycle cost analysis compares traditional retrofit approaches with the robotic framework, using net present value (NPV) and levelized energy cost (LEC) metrics. Theoretical grounding draws on the Theory of Planned Behavior for occupant interaction with adaptive systems and the Diffusion of Innovations theory to contextualize adoption pathways. A conceptual model will map the interactions among sensing, actuation, control decisions, material performance, and energy outcomes. Expected findings include (i) demonstrable reductions in heating and cooling energy consumption by 18–32% relative to conventional retrofits under corresponding climate profiles; (ii) measurable improvements in thermal comfort indices (PMV/PPD) and perceived indoor environmental quality without compromising daylight autonomy; (iii) robust robotic performance with mean time between failures exceeding 520 hours and repair latency under 48 hours across climate zones; (iv) positive economic indicators with 8–12 year payback periods when considering energy savings, retrofit speed, and lifecycle maintenance; and (v) identification of critical design parameters for modular envelope components and control strategies that maximize energy-neutral performance. The study contributes to knowledge by integrating robotics with adaptive envelope design, expanding the evidence base for automation-driven energy retrofits, and providing a scalable framework and decision-support tools for practitioners and policymakers. A key conclusion is that energy-neutral retrofit is feasible at scale when envelope adaptability is driven by real-time sensing, climate-responsive control, and modular robotics that minimize disruption and financial risk. Recommendations include developing standardized protocols for component interoperability, regulatory pathways for robotic retrofit approvals, and further longitudinal studies to capture long-term maintenance costs and performance degradation, alongside explorations of integration with on-site renewable energy systems and high-performance porous insulation advancements.