Research

Research Thrusts

Three connected steps of one loop.

Energy systems are dynamic, interconnected and only partially observable. Their evolving physical states and operational constraints shape what an intelligent agent can observe, predict and safely do. In turn, the agent’s actions can change energy flows, equipment operation and system performance.
Energy-System Perception & Observability

Energy-System Perception & Observability

What information is sufficient for reliable energy decisions?
We investigate how incomplete observations affect energy-state estimation and how active sensing can provide decision-relevant information.

Physics-Grounded Energy World Models

Physics-Grounded Energy World Models

How do energy systems respond to changes and actions?
We develop physics-grounded world models to predict energy-system dynamics and action consequences under uncertainty and physical constraints.

Energy-Constrained Embodied Decision & Control

Energy-Constrained Embodied Decision & Control

How can energy agents act safely and adaptively?
We investigate autonomous, energy-constrained decision-making and control, connecting intelligent planning with physical actions and feedback-driven adaptation.

Flagship Research Scenarios

Embodied Intelligence in Energy Systems

A unified embodied intelligence framework across diverse energy systems, physical constraints, and feedback dynamics.

We investigate how intelligent agents perceive, model, and interact with physical energy systems. Across complementary research scenarios, we explore how energy constraints, incomplete observations, and physical feedback shape autonomous adaptation and coordinated action.
Autonomous Urban BIPV & Solar–Storage Systems
Active

Autonomous Urban BIPV & Solar–Storage Systems

Integrating active urban sensing, physics-grounded solar assessment, building-integrated photovoltaics, and adaptive energy management. We investigate how intelligent sensing, physical world models, and autonomous control enable more reliable renewable energy assessment, deployment, and operation in complex urban environments.

Embodied Intelligence for Data Center Energy & Cooling
Active

Embodied Intelligence for Data Center Energy & Cooling

Integrating indoor spatial perception, BIM-informed energy–thermal world models, autonomous inspection, and adaptive cooling control. We investigate how intelligent agents interact with physical data center environments to improve energy efficiency, thermal management, and operational reliability.

Climate-Resilient Urban Renewable Energy Networks
Active

Climate-Resilient Urban Renewable Energy Networks

Investigating autonomous coordination among distributed renewable generation, buildings, energy storage, electric vehicles, and urban energy networks under climate extremes. We study how multi-agent intelligence, physical energy interactions, and adaptive control enhance energy resilience, service continuity, and system recovery.

Low-Altitude Energy & Mobility Systems
Emerging

Low-Altitude Energy & Mobility Systems

Exploring the coupling among low-altitude mobility, onboard energy constraints, and ground-based energy infrastructure. We investigate energy-aware autonomous missions, intelligent charging and storage coordination, and adaptive energy management for UAVs, future eVTOL systems, and low-altitude mobility networks.

Energy-Integrated Smart Agriculture
Emerging

Energy-Integrated Smart Agriculture

Exploring embodied intelligence in coupled agricultural energy, environmental, and biological systems. We investigate how intelligent perception, physics-grounded world models, and autonomous physical control can coordinate energy supply, environmental regulation, water use, and crop growth for efficient and adaptive agricultural operations.