Skip to content
Abstract neural vascular network visualization
All Research

Research Program

Embodied AI

Research across the full scale spectrum — from planetary systems to molecular machines. Bridging lab prototypes to production reality.

Publications

15 publications in Embodied AI

2026Embodied AIMESOAutonomous ThrombectomyEndovascular RoboticsStrokeReinforcement LearningMechanical Thrombectomy

AI-Guided Autonomous Robotic Thrombectomy for Acute Ischemic Stroke

Reinforcement Learning Navigation Systems Closing the 88% Mechanical Thrombectomy Access Gap

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for autonomous robotic mechanical thrombectomy in acute ischemic stroke, targeting the 88% treatment gap identified by ARPA-H where only 12% of Americans in need currently receive the procedure. Approximately 800,000 strokes occur annually in the US alone, with 87% ischemic and an estimated 280,000 to 350,000 patients eligible for mechanical thrombectomy each year, yet fewer than 60,000 procedures are performed due to a bottleneck of roughly 2,000 practicing neurointerventionalists and severe geographic disparity (27.7% rural vs 69.5% urban access to comprehensive stroke centers). Three converging technical demonstrations (autonomous catheter navigation completing end to end thrombectomy in porcine cerebral vasculature from Artedrone/Carvolix in 2025, reinforcement learning controllers achieving 65% mean success across 10 patient specific vasculatures via TD-MPC2 world models from King's College London at MICCAI 2025, and magnetically actuated microrobots performing vascular thrombectomy with immediate flow restoration in large animal models from ETH Zurich and University of Twente in Science 2025) establish technical feasibility at TRL 3 to 4 while no commercial autonomous neurovascular thrombectomy system exists. Bottom up TAM of $8.4B to $17.5B annually for US mechanical thrombectomy at full penetration, cross checked against $56.5B in annual US direct stroke costs (AHA). The integration gap between RL driven autonomous navigation, clinical grade catheter hardware, and regulatory strategy for locked algorithm deployment represents a first mover opportunity in a device class with explicit federal funding signals from ARPA-H AIR and DARPA MASH.

2026Embodied AIMICROMicroroboticsBiofilm EradicationAntimicrobial ResistanceMagnetic ActuationMedical DevicesHealthcare-Associated Infections

Magnetically Actuated Microrobots for Active Biofilm Eradication on Indwelling Medical Devices

Magnetic Field-Driven Robotic Systems for On-Demand Biofilm Destruction on Catheters, Stents, and Implants

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for magnetically actuated microrobots that physically navigate to, mechanically disrupt, and chemically destroy biofilms on indwelling medical devices. Six peer-reviewed papers (2019-2025) in Science Robotics, Science Advances, and ACS Nano demonstrate 84-100% biofilm eradication on hernia mesh, biliary stents, urethral catheters, and dental implants, with in vivo validation in murine and rabbit models showing 93.45% bacterial reduction on infected stents (Sun et al., Science Advances, 2025). Zero commercial competitors exist for active microrobotic biofilm destruction. The CAUTI prevention market alone is valued at $3.43B (2025, Grand View Research), while total US healthcare-associated infection costs reach $28-45B annually (CDC). ARPA-H has invested over $150M in antimicrobial resistance programs since 2023. The gap between validated academic prototypes and a commercialized AI-navigated, manufacturing-ready system represents a first-mover opportunity in a device class with no existing regulatory predicate.

2026Embodied AIKILOUnderground MiningAutonomous UAVGas DetectionMine SafetyReinforcement LearningGPS-Denied Navigation

Autonomous UAV Systems for Post-Blast Underground Mine Gas Monitoring and Safety Inspection

Risk-Aware Autonomous Navigation with Integrated Multi-Gas Sensing for Post-Detonation Re-Entry Safety in Underground Mining Operations

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for autonomous UAV systems combining risk-aware 3D navigation with integrated multi-gas sensing for post-blast inspection in underground mines. Two independent research groups (Lulea University of Technology and University of Manchester) have demonstrated field-validated prototypes achieving autonomous gas measurement 40 minutes post-blast at 700m depth and borehole-deployable reconfigurable drones navigating through 130mm apertures. Zero commercial products combine autonomous GPS-denied navigation with integrated toxic gas sensing for post-blast re-entry assessment. Over 2,300 active underground mines worldwide conduct multiple blast cycles daily, with conservative re-entry waiting periods costing an estimated $50,000 to $150,000 per event in lost production. The drone inspection and monitoring market is projected to grow from $9.1 billion (2021) to $33.6 billion by 2030 at 15.7% CAGR (MarketsandMarkets). The gap between field-validated research prototypes and deployable commercial systems represents a first-mover opportunity in the post-blast autonomous inspection segment.

2026Embodied AIMICROSmart StentWireless ImplantRestenosis MonitoringCardiovascularHemodynamic SensingBatteryless Sensor

Wireless Smart Stents for Autonomous In-Vivo Restenosis Monitoring

Batteryless Implantable Sensor-Integrated Coronary Stents with Long-Range Wireless Hemodynamic Surveillance and AI-Assisted Stenosis Detection

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for wireless smart coronary stents that continuously monitor hemodynamic parameters and detect in-stent restenosis without invasive follow-up angiography. Six independent research groups (UCLA, Georgia Tech, University of Pittsburgh, UBC, University of Glasgow, Chonnam National University) have demonstrated functional prototypes across three animal models — swine carotid arteries, rabbit iliac arteries, and rat aortas — achieving wireless communication ranges up to 50 cm and real-time thrombus detection with p<0.001 discriminatory power. In-stent restenosis affects 5–15% of the 600,000 US patients receiving coronary stents annually, currently detected only through invasive angiography costing $1,708–$3,312 per procedure. Zero commercial wireless restenosis-monitoring stents exist despite $12.1M in combined ARPA-H and EU funding awarded to smart stent startups in 2024. The smart stent market is projected to reach $4.2–10.5 billion by 2033. Existing remote physiological monitoring CPT codes (99453–99458) provide an immediate reimbursement pathway generating approximately $1,248 per patient per year in recurring revenue.

2026Embodied AIMICROMicroroboticsMicroplastic RemediationWater TreatmentEnvironmental RoboticsMagnetic Swarms

Autonomous Microrobotic Swarms for Aquatic Microplastic Remediation

Magnetically Guided Self-Propelled Microrobots for Decentralized Water Treatment

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for magnetically guided microrobotic swarms targeting aquatic microplastic removal. Three independent research groups have demonstrated 77-98% microplastic removal efficiency using self-propelled, magnetically recoverable microrobots in real-world water matrices (ACS Nano, 2025; ACS AMI, 2024; Small, 2025). Zero commercial entities offer microrobotic remediation — all existing players use conventional filtration. Regulatory tailwind from ARPA-H STOMP ($144M, April 2026) and EPA draft CCL 6 microplastic listing creates a market about to be defined by regulation. Bottom-up TAM of $2.6B for US wastewater and drinking water installations, cross-checked against the $3.77B global microplastics removal technologies market (Grand View Research, 2025). The gap between validated lab-scale microrobotic capture and deployable water treatment modules — swarm intelligence optimization, continuous-flow reactor design, and batch manufacturing at industrial volumes — represents a first-mover opportunity in an unoccupied technology category.

2026Embodied AIDECAFall PreventionElderly CareAssistive RoboticsAirbag SystemsAutonomous NavigationWearable Sensors

Autonomous Fall-Prevention Mobile Robotics for Elderly Independent Living

Companion Robots Integrating Predictive Fall Detection, Autonomous Navigation, and Rapid-Deployment Airbag Systems for In-Home Elderly Fall Prevention

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for autonomous mobile robots that combine predictive fall detection via wearable IMU and depth sensors with rapid-deployment airbag protection for elderly independent living. Three independent research groups (MIT CSAIL, Purdue, multiple sensor-fusion teams) have demonstrated field-validated prototypes including the E-BAR platform achieving full body-weight support through 38cm doorways with four airbags deploying in under 250ms. Falls kill 43,020 Americans annually and cost $80 billion in healthcare spending. Zero commercial products combine mobile autonomous following, physical support, and airbag-based fall protection in a single platform. The elderly assistive robotics market is projected to grow from $3.38B (2025) to $9.85B (2033) at 14.2% CAGR. The gap between research prototypes and deployable commercial systems — scalable manufacturing, regulatory clearance, and reimbursement coding — represents a first-mover commercial opportunity.

2026Embodied AIKILOPrecision AgricultureRobotic PollinationComputer VisionAutonomous NavigationTree FruitPollinator Decline

Autonomous Precision Pollination Robots for Tree Fruit Orchards

Vision-Guided Robotic Systems for Targeted Pollen Delivery in Commercial Apple, Kiwifruit, and Almond Orchards Under Accelerating Pollinator Decline

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for autonomous ground-based robotic pollination systems targeting tree fruit orchards. Three independent research groups (Washington State University, Zhejiang Academy of Agricultural Sciences, West Virginia University) have demonstrated field-validated prototypes achieving 34.8-99.3% pollination success rates in commercial orchards. US managed honeybee colony losses reached 55.6% in 2024-2025 — the highest ever recorded — while almond pollination costs rose 15% to $209/colony. Zero commercial products exist for targeted liquid pollination of tree fruit orchards. The robotic pollination market is projected to grow from $148.5 million (2024) to $1.03 billion by 2033 at 23.7% CAGR. The gap between validated research prototypes and commercially deployable fleet systems — real-time flower detection in variable canopy conditions, autonomous orchard navigation, and precision nozzle manufacturing at scale — represents a first-mover opportunity in a space with zero direct competitors.

2026Embodied AIDECIBioelectronicsWound CareSmart BandageClosed-Loop TherapyMachine LearningDrug DeliveryChronic Wounds

Autonomous Closed-Loop Bioelectronic Wound Dressings for Chronic Wound Therapy

Machine Learning-Guided Bioelectronic Systems for Real-Time Wound Monitoring, Predictive Classification, and Autonomous Drug Delivery in Chronic Wound Management

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for autonomous closed-loop bioelectronic wound dressings that integrate multiplexed biosensors, on-device machine learning classification, and programmable drug delivery with electrical stimulation for chronic wound management. Four independent research groups (Caltech/Wei Gao, Stanford/Zhenan Bao, UC Santa Cruz/Marco Rolandi, University of Arizona/Geoffrey Gurtner) have demonstrated field-validated prototypes achieving closed-loop healing acceleration of 25% in preclinical models and ML-based wound classification comparable to expert clinicians in a 20-patient human trial. Zero commercial products combine real-time wound biomarker monitoring with autonomous closed-loop drug delivery. The United States has 8.2 million Medicare beneficiaries with chronic wounds generating $28 billion in annual Medicare spending. The smart bandage market is projected to grow from $926 million (2025) to $3.7 billion by 2035 at 15-17% CAGR. The gap between validated research prototypes and deployable commercial systems — on-device ML inference, scalable flexible electronics manufacturing, and FDA combination product regulatory strategy — represents a first-mover commercial opportunity in a space with zero direct competitors.

2026Embodied AIHECTOBridge InspectionStructural Health MonitoringDeep Reinforcement LearningDigital TwinFatigue PrognosisInfrastructure

DRL-Guided Autonomous Structural Crack Inspection for Steel Bridge Fatigue Prognosis

Deep Reinforcement Learning Agents for Autonomous Crack Following, Digital Twin Construction, and Adaptive Fatigue Life Prediction in Steel Bridge Infrastructure

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for autonomous robotic systems that combine deep reinforcement learning-guided crack following with integrated digital twin fatigue prognosis for steel bridge infrastructure. Three independent research groups (Hong Kong Polytechnic/Tongji, Drexel University, Rutgers CAIT) have demonstrated field-validated prototypes achieving 59.6% inspection time reduction, 85% autonomous crack detection rates, and 3x faster data collection versus manual methods. Zero commercial products combine DRL-guided autonomous crack exploration with finite-element digital twin fatigue life prediction. The US has 617,000 bridges requiring biennial inspection under federal mandate, with 42,067 rated structurally deficient. The Infrastructure Investment and Jobs Act committed $40 billion to bridge investment. The autonomous bridge inspection robot market is projected to grow from $1.5B (2024) to $4.8B (2034) at 11.8% CAGR. The gap between field-validated research prototypes and deployable commercial systems — scalable DRL navigation algorithms, ruggedized climbing robot manufacturing, and utility-grade digital twin integration — represents a first-mover commercial opportunity.

2026Embodied AICENTIWater InfrastructurePipe InspectionAutonomous RobotsDefect DetectionMunicipal Utilities

Autonomous In-Pipe Robots for Drinking Water Infrastructure Condition Assessment

AI-Driven Miniature Crawlers for Non-Disruptive Inspection of Live Pressurized Water Mains

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for autonomous in-pipe inspection robots targeting drinking water distribution infrastructure. The United States operates 2.3 million miles of buried water mains, of which 770,000 miles (33%) exceed 50 years of age. These aging pipes produce 260,000 water main breaks annually at $2.6 billion in direct repair costs, with an estimated $452 billion infrastructure replacement deficit (Barfuss and Fugal, Journal AWWA, 2025). Four independent research programs — Pipebots (University of Sheffield, EPSRC £7M), MIT Mechatronics Laboratory, SubMerge (Dutch water utilities consortium), and Motmot Inc. (NSF SBIR $1.555M) — have demonstrated tetherless, sensor-equipped miniature robots capable of autonomous navigation through live pipe networks. Zero commercial products exist for autonomous condition assessment of pressurized drinking water mains; all currently deployed pipe inspection systems are either tethered camera crawlers requiring service interruption or external acoustic sensors with limited spatial resolution. Bottom-up TAM of $4.6B annually for US water utility condition assessment, cross-checked against the $2.57B in-pipe inspection robot market (Reanin, 2024) growing at 15.3% CAGR. The gap between demonstrated autonomous navigation prototypes and deployable commercial systems — robust multi-sensor defect classification algorithms, miniaturized multi-module robot manufacturing at utility procurement volumes, and integration with utility asset management platforms — represents a first-mover opportunity in a space where municipal water utilities face regulatory mandates for proactive infrastructure management.

2026Embodied AIDECASelf-Driving LabsMaterials DiscoveryAutonomous SynthesisActive LearningLaboratory Robotics

Self-Driving Laboratories for Autonomous Materials Discovery

AI-Robotic Closed-Loop Platforms Compressing Decades of Materials R&D

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for self-driving laboratories (SDLs) — autonomous robotic platforms that integrate AI-driven experimental planning with automated synthesis and characterization to accelerate materials discovery by 10-100x. Three independent systems (A-Lab at Berkeley, Polybot at Argonne, MINERVA at BAM) have demonstrated continuous autonomous operation synthesizing dozens of materials without human intervention. Zero commercial SDL products exist. The US DOE committed $320M to autonomous laboratory infrastructure through the Genesis Mission (December 2025). Bottom-up TAM of $5.7B for US materials-focused R&D laboratories, cross-checked against the $8.27B laboratory automation market (Grand View Research, 2024) growing at 9.3% CAGR. The gap between validated prototypes and deployable products — scalable active learning algorithms, modular hardware integration, and manufacturing of discovered materials — represents a first-mover commercial opportunity.

2026Embodied AIMESORehabilitation RoboticsExoskeletonsReinforcement LearningStroke RecoveryGait TrainingAdaptive Control

Reinforcement Learning-Adaptive Rehabilitation Exoskeletons for Post-Stroke Gait Recovery

Sim-to-Real Transfer and Human-in-the-Loop Optimization for Personalized Lower-Limb Assistance

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for reinforcement learning-adaptive rehabilitation exoskeletons targeting post-stroke gait recovery. Four independent research groups have demonstrated metabolic cost reductions of 24.2% (Zhang et al., Science 2017), 23% (Slade et al., Nature 2022), 24.3% (Luo et al., Nature 2024), and 5.3-19.7% across ten activities (Molinaro et al., Nature 2024) using human-in-the-loop optimization, Bayesian optimization, and sim-to-real RL transfer on hip and ankle exoskeletons tested on human subjects. Zero commercial rehabilitation exoskeletons use RL-adaptive closed-loop control — all FDA-cleared devices (ReWalk, Ekso Bionics, Indego) operate with fixed, pre-programmed gait trajectories. Bottom-up TAM of $3.2B annually for US post-stroke gait rehabilitation, cross-checked against the $1.5B rehabilitation robotics market growing at 12.5% CAGR (Verified Market Reports, 2024). The gap between demonstrated RL-adaptive control and clinical deployment — personalization for neurological impairment profiles, manufacturing of sensor-integrated exoskeletons at rehabilitation facility volumes, and regulatory strategy for adaptive AI-controlled Class II medical devices — represents a first-mover opportunity in a device class where reimbursement pathways already exist (HCPCS K1007, CPT 97116).

2026Embodied AIMESOSurgical RoboticsAutonomous SurgeryImitation LearningLaparoscopic SurgerySoft Tissue

Autonomous Soft Tissue Surgical Systems with Learned Dexterity

Imitation Learning and Hierarchical Control for Surgeon-Independent Laparoscopic Procedures

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for autonomous soft tissue surgical systems operating at Level 4 surgical autonomy. Three landmark studies — autonomous intestinal anastomosis in live porcine models (Science Translational Medicine, 2016; Science Robotics, 2022) and autonomous cholecystectomy clipping-and-cutting in ex vivo porcine gallbladders with 100% task completion across 8 unseen specimens (Science Robotics, 2025) — establish that AI-driven surgical robots can match or exceed expert surgeon consistency in soft tissue procedures. Zero commercial products exist at Level 4 autonomy; all FDA-cleared surgical robots operate at Level 1-3. ARPA-H committed $12M to the ALISS program (2024) for autonomous surgical development. Bottom-up TAM of $4.1B annually for US laparoscopic cholecystectomy alone, cross-checked against the $12.8B surgical robotics market (Mordor Intelligence, 2025). The gap between demonstrated autonomous capability and clinical deployment — regulatory strategy for AI-controlled surgical instruments, manufacturing of sensor-rich end-effectors at clinical volumes, and validated safety architectures for human-supervised autonomous operation — represents a first-mover opportunity in a device class with no commercial precedent.

2026Embodied AIMICROBioelectronic MedicineVagus Nerve StimulationNeuroimmune ModulationReinforcement LearningAutoimmune Disease

Closed-Loop Adaptive Bioelectronic Implants for Chronic Inflammatory Disease

Reinforcement Learning-Optimized Vagus Nerve Stimulation for Autoimmune Conditions

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for closed-loop adaptive bioelectronic implants targeting chronic inflammatory disease. The biological mechanism — vagus nerve-mediated neuroimmune modulation — received FDA approval in July 2025 via SetPoint Medical's open-loop device for rheumatoid arthritis (Nature Medicine, 2025). Zero commercial products exist for closed-loop adaptive stimulation, where reinforcement learning algorithms optimize stimulation parameters in real time based on physiological biomarkers. Computational studies demonstrate 67% power reduction versus open-loop while preserving therapeutic efficacy (IEEE TNSRE, 2024). Bottom-up TAM of $6.2B annually for US treatment-resistant moderate-to-severe RA, cross-checked against the $25.8B bioelectronic medicine market (Grand View Research, 2023). The gap between FDA-validated biology and AI-optimized delivery — adaptive control algorithms, miniaturized closed-loop hardware, and manufacturing at clinical volumes — represents a first-mover opportunity in a device class with established regulatory precedent.

2026Embodied AIMICRODrug DeliveryMicroroboticsTargeted TherapyOncology

Magnetically Guided Microrobots for Targeted Intravascular Drug Delivery

Sub-Millimeter Autonomous Navigation for Precision Chemotherapy

Hass Dhia — Smart Technology Investments Research Institute

Market opportunity analysis for magnetically guided microrobotic drug delivery platforms. Foundational research validated in large animal models (Science 2025) demonstrates sub-millimeter capsule navigation against physiological blood flow under clinical fluoroscopy. Zero commercial products exist at the sub-millimeter intravascular scale. Bottom-up TAM of $2.5B annually for US oncology applications alone, cross-checked against the $10.7B targeted drug delivery market (Coherent Market Insights, 2025). The gap between laboratory validation and clinical deployment — AI-driven autonomous navigation, batch manufacturing, and regulatory strategy — represents a first-mover opportunity in a space where academic labs lack commercialization infrastructure.

15

Publications

84

Domains

0

Open-Source Repos

0

Published Packages

Collaborate with us

We welcome research collaborations, dataset contributions, and open-source partnerships across any discipline. Reach out to discuss.