Channel Knowledge Map Enabled Low-Altitude ISAC Networks: Joint Air Corridor Planning and Base Station Deployment

This letter addresses the joint air corridor planning and base station (BS) deployment problem for low-altitude integrated sensing and communication (ISAC) networks. In the considered system, unmanned aerial vehicles (UAVs) operate within a structured air corridor composed of connected cubic segments, and multiple BSs need to be selectively deployed at a set of candidate locations to ensure both sensing and communication coverage throughout the corridor. In particular, we leverage the channel knowledge map (CKM) to characterize wireless channels for candidate BS sites prior to deployment, thereby facilitating the offline planning. Under this setup, we minimize the system cost in terms of the weighted sum of the air corridor length and the number of deployed BSs, subject to the constraints on both sensing and communication performance across the corridor. To solve the formulated large-scale nonconvex integer programming problem, we develop a hierarchical coarse-to-fine grid decomposition algorithm. Simulation results demonstrate the benefit of the proposed joint design in reducing the overall deployment cost while ensuring the coverage of the low-altitude ISAC networks.

💡 Research Summary

This paper addresses the critical infrastructure planning problem for the emerging low-altitude economy (LAE). It focuses on the joint optimization of air corridor planning and base station (BS) deployment for low-altitude Integrated Sensing and Communication (ISAC) networks. The goal is to design a dedicated, structured flight path (air corridor) for unmanned aerial vehicles (UAVs) or electric vertical takeoff and landing (eVTOL) aircraft while simultaneously determining the optimal placement of ground BSs to provide seamless communication and sensing coverage throughout the entire corridor.

The system model defines the air corridor as a sequence of connected cubic segments at a fixed altitude H, forming a continuous, non-branching path from a departure point to a destination point on a discretized grid map. A set of K candidate BS locations on the ground is considered, from which a subset must be selected for deployment. A key enabler for offline planning is the use of a Channel Knowledge Map (CKM). The CKM, constructed using 3D environmental models and ray-tracing techniques, provides prior knowledge of channel power gains, Line-of-Sight (LoS) conditions, and sensing echo power between any candidate BS site and any point in the airspace, even before physical deployment.

The core optimization problem (P1) is formulated to minimize the total system cost, defined as a weighted sum of the air corridor length (proportional to the number of active grid cells) and the number of deployed BSs. The constraints ensure that for every segment of the active corridor: 1) the aggregated sensing signal power from all deployed BSs exceeds a threshold (ε1), 2) LoS links exist from at least three deployed BSs for reliable localization, and 3) the communication Signal-to-Interference-plus-Noise Ratio (SINR) from at least one BS is above a threshold (ε2). Additional constraints enforce the connectivity and structure of the air corridor path. This formulation results in a large-scale, non-convex integer programming problem, which is computationally challenging to solve directly.

To tackle this complexity, the authors propose a hierarchical coarse-to-fine grid decomposition algorithm. The algorithm operates in two main layers:

1. Coarse Layer Optimization: The original fine N×N grid map is coarsened into an M×M grid (M « N). Channel metrics (minimum/maximum gain for SINR calculation, LoS condition, sensing power) are re-evaluated for each coarse grid cell, discarding outlier samples (top and bottom 10%) to improve robustness. The non-convex SINR constraint involving a max operator is transformed using a Big-M reformulation. Furthermore, bilinear terms involving products of binary variables (corridor and BS deployment indicators) are linearized using the McCormick method. These steps reformulate the original problem into a linear integer program (P2) with significantly reduced variable count, making it solvable with standard solvers. This yields an initial coarse-resolution air corridor path and BS deployment plan.
2. Fine Layer Refinement: The solution from the coarse layer defines which large grid cells the corridor passes through. Each of these coarse cells is then decomposed back into its original fine-grid sub-region. An alternating optimization (AO) procedure is applied within these regions to refine the detailed fine-grid path and fine-tune the BS deployment. This step improves spatial coverage accuracy and can further reduce the number of required BSs or the corridor length.

Simulation results demonstrate the significant advantages of the proposed joint design. Compared to baseline methods that plan the air corridor and deploy BSs separately or sequentially, the proposed algorithm achieves a shorter air corridor and requires fewer BS deployments while still satisfying all sensing and communication performance requirements across the corridor. This work provides a comprehensive and practical methodology for the cost-effective and performance-guaranteed planning of future low-altitude ISAC network infrastructure, effectively bridging the gap between high-level network design and physical environmental constraints through the innovative use of CKM.