CORNAV: Construction-Aware Reasoning for Robot Navigation on Active Worksites
Authors: Parastoo Ali Pour, Deepak Prakash Kumar, Tommy Zhou, Pramod Khargonekar, Mohammad Abdullah Al Faruque
Organizations: Department of Mechanical and Aerospace Engineering, University of California at Irvine, Irvine, CA 92697 USA · Department of Aerospace Engineering, Indian Institute of Technology Bombay, Mumbai 400076, India · Department of Electrical Engineering and Computer Science, University of California at Irvine, Irvine, CA 92697 USA
The construction industry faces persistent labor shortages, low productivity that costs the global economy over $1.6 trillion annually, and one of the highest injury rates among major industries. These factors motivate the use of autonomous robots to improve efficiency and worker safety. Existing language-grounded navigation systems, however, rely on semantic scene understanding alone and lack access to construction-specific context such as architectural plans, evolving work schedules, and safety constraints. As a result, they localize permanent building features unreliably and cannot safely navigate active jobsites. We present CORNAV, a blueprint-grounded, schedule-aware navigation framework that operates from 2D CAD drawings and project schedules without requiring a Building Information Model. CORNAV aligns architectural blueprints against hierarchical open-vocabulary 3D scene graphs to ground object queries, converts project schedules into time-varying navigation constraints, and validates requests through an LLM-based safety module that escalates hazardous zones before planning. An A* planner then enforces mandatory exclusion zones while preferentially avoiding higher-risk areas. Across an indoor office and a real construction site, blueprint grounding raises task success from 13.0% to 72.2% over semantic retrieval alone, schedule awareness eliminates all hard-zone violations, and the safety module correctly rejects hazardous requests arising from mislabeled project schedules.
Figures & tables
Fig. 1: CORNAV framework integrates open-vocabulary scene understanding with construction-specific knowledge including blueprints, project schedules, and safety constraints, to ground natural-language instructions and generate semantically informed, schedule-compliant, safety-validated navigation plans.
Fig. 2: Pipeline of the proposed system. Offline pre-processing runs once per site; the four-stage online pipeline runs per query, taking a natural-language task (e.g., “find the chair in office 1 on floor 0”) and a requested date and time, returning either robot-frame waypoints or an infeasibility verdict with a reason. In the planning maps, the blue circle marks the robot start, the red star the goal, and green the planned path.
Fig. 3: Offline map pre-processing. (a) native CAD drawing, (b) extracted room boundaries, (c) robot-generated occupancy map, (d) blueprint scene graph aligned to the occupancy map, (e) sample project schedule applied to the occupancy map, with free space in white and a hard exclusion zone in black, and (f) 3D scene graph built from robot observations [ 11 ] .
Fig. 4: Blueprint overlaid on the occupancy map after alignment, floor 1.
Fig. 5: Schedule-aware navigation under changing construction constraints. The same navigation request is evaluated at different schedule states, demonstrating adaptation to inactive, soft, and hard work zones. Left: no active constraints affect the route, resulting in the baseline path. Center: active soft zones (tan) introduce a cost penalty. The planner exits the start region and routes the remainder of the path through unaffected rooms, minimizing traversal of the penalized area rather than continuing through it as in the unconstrained case. Right: an active hard zone (black) overlaps the goal region, causing the planner to correctly return an infeasible result. Blue circle: robot start; red star: goal; blue polygons: blueprint room boundaries; green: planned path.
Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta 30332, USA · School of Civil and Environmental Engineering, Georgia Institute of Technology, Atlanta 30332, USA · Institute of Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta 30332, USA
Department of Computer Science, The University of Manchester, Manchester, UK. · Human-Robot Interfaces and Interaction Laboratory, Italian Institute of Technology, Genoa, Italy. · Genisom AI, Shanghai, China. +3