EMBODIED ROBOTICS · ROADSIDE 3D LIDAR · GEOSPATIAL AI
Bo Shang
Robotics & AI Researcher · Postdoctoral Associate, University of Maryland
My research asks how the infrastructure around us — bridges, intersections, highways, and cities — can perceive itself. Combining embodied field robots with fixed 3D sensing and auditable AI simulation, I build physical-AI systems deployed with public transportation agencies.
Since July 2026, I have been a Postdoctoral Associate in Civil and Environmental Engineering and the Maryland Transportation Institute at the University of Maryland, College Park, working under Professor Xianfeng Yang. I support hardware and software development, integration, testing, troubleshooting, data collection, technical documentation, and deliverables for two sponsored transportation research projects. My broader work brings together learning-based perception, ROS-based robotics, edge inference, and inspection workflows developed with public agencies. At UMD I am extending the macro scale to the city: I build and operate CERRA (Civil, Environmental, Road & Resource Analytics), a platform that turns real-world infrastructure data into actionable insight, including an LLM-driven traffic simulation and a quantum-safe evaluation of signal broadcast.
Research: Intelligent Infrastructure Across Scales

Embodied Bridge & Concrete Robots
UAVs and climbing robots operating where GPS fails: the patented BIRDS flying-clamping bridge robot (6 experimental videos) and 3D concrete crack localization (IEEE T-ASE 2025).
Watch BIRDS flight & clamping demos →
PACO & Roadside Safety Auditing
A 120° ADAS observes 0.37 of an urban intersection, a 360° AV 0.61, and elevated roadside LiDAR (V2I) 1.00 — proving dynamic occlusion makes infrastructure sensing mathematically necessary.
Try interactive PACO simulator →
InfraLiDAR-Eval & CERRA Platform
61.9-hour continuous highway LiDAR evaluation (90.1% vs. 72.9% crossing recovery on I-95) scaled up to city-level geospatial AI and LLM-SUMO traffic simulation.
Explore highway & city systems →The three scales feed one model: fixed sensors contribute macro-level intelligence, embodied robots contribute micro-level agility, and the synthesis is a unified, multi-scale picture of the built environment. View all 7 interactive system showcases →
Resume, CV & Presentation Suite
Research Scientist Resume
Selected research contributions, deployed field systems, publications, and robotics/ML stack.
Academic CV
Complete record of academic appointments, publications, patents, teaching, and service.
Mechatronics Research Statement Slides
26-slide faculty research statement deck: BIRDS electro-mechanics, fractional-order UAV control, 3D robotic NDT & 5-year lab plan.
Infrastructure & Physical AI Slides
28-slide multi-scale seminar deck with inline experimental videos, PACO observability, InfraLiDAR-Eval & CERRA.
Research notes
- AI Agent Security After 29 Attempts — a source-first postmortem on replay noise, public-leaderboard overfitting, counterbalanced experiments, and the private-guardrail reset.
- When Should a Language Model Hand Over the Controls? — an embodied-control case study comparing screenshot-mediated LLM control with a deterministic local skill worker across 39 logged runs.
Selected publications
Selected work in urban freight sensing, roadside LiDAR, vulnerable-road-user safety, and robotic infrastructure inspection.
Drive-by Urban Freight Sensing: Large-Scale Fine-Grained Truck Classification Using Google Street View Imagery and Deep Learning
★ Published September 4, 2026; open access
Roadside LiDAR for Cooperative Safety Auditing at Urban Intersections: Toward Auditable V2X Infrastructure Intelligence
★ DriveX Workshop on Foundation Models for Autonomous Driving; archival proceedings
Robotic Inspection and Data Analytics to Localize and Visualize the Structural Defects of Concrete Infrastructure
★ Journal paper selected for presentation at IEEE IROS 2025
AI-Enhanced Sensing for Vulnerable Road User Safety at Signalized Intersections: A Survey
Citation counts: Google Scholar, 2026-10-14.
