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.
Multi-robot systems have shown increasing viability in construction due to their ability to execute high-precision actions while reducing human exposure to hazardous tasks. However, these environments have high-dimensional configuration spaces and possess substantial collision-avoidance constraints, which include other robots, assembly objects, and workspace boundaries. We utilize a single factor graph for trajectory estimation and planning that incorporates measured robot states together with explicit collision and learned cable constraints. This supports changing workspaces and enables synchronized, high-dimensional robot motion planning while accounting for the stiff, vibration-induced uncertainty of heavy robotic systems. We demonstrate the success of our framework on the construction of a post-and-lintel structure using one robot arm as a timber gripper, and a second robot as a nail-fastener.
Karthik Shaji, Chisung Kim, John D'Amato +2
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
Safe and efficient robot navigation in crowds requires anticipating pedestrian motion despite uncertain and potentially shifting prediction errors. Existing reactive methods can produce oscillatory behavior, while predictive planners often treat forecasts as exact or rely on restrictive error models. Incorporating conservative uncertainty sets as hard constraints can also render model predictive control (MPC) infeasible. We propose CoCoNav, a crowd-navigation framework that combines online conformal calibration with runtime-certified planning. A horizon-specific conformal proportional--integral controller adapts trajectory-error bounds to regulate long-run empirical coverage, enabling the framework to respond to changing prediction errors. A relax-then-verify planner preserves solver feasibility by generating nominal trajectories with soft-constrained MPC and separately certifying them, together with contingency maneuvers, against the calibrated bounds before execution. Simulations and quadruped experiments show that CoCoNav achieves a favorable balance among collision avoidance, task success, and navigation efficiency relative to the evaluated baselines.
Cheng Guo, Mingzhe Ni, Zheng Liang +5
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
Robot navigation typically assumes an obstacle-free path exists between start and goal. In real environments, however, clutter may block all routes. We introduce Lifelong Interactive Navigation, where a mobile robot with manipulation capabilities must move objects to forge paths and complete sequential object-placement tasks. Because environment modifications persist, decisions impact future navigability and task difficulty. We propose CoReLIN, an LLM-driven constraint-based reasoning framework with active perception. CoReLIN reasons over a structured scene graph to decide which objects to relocate, where to place them, and where to explore next. A standard motion planner executes reliable navigation and manipulation primitives. To evaluate long-horizon behavior, we introduce 2 new metrics - Long-term Efficiency Score (LES), a unified metric capturing success, execution efficiency, environment optimality, captured by Price of Clutter. In ProcTHOR-10k, CoReLIN outperforms best baseline by 16% under standard metrics and LES, and transfers to real-world hardware.