The integrated sensing and communication (ISAC) attracts growing interest in 6G due to the extension of radar capability. This paper devotes to the resource allocation problem in ISAC system design. Both static and dynamic resource allocation schemes are comprehensively investigated, with the primary distinction lying in the allocation of resources to either communication or sensing services, or their shared utilization. We construct two-class multi-server queues of each scheme, respectively, where communication and sensing services are modeled as Poisson processes with distinct arrival and service rates. To derive the steady-state probabilities of the two models, we present proofs of reversibility. Additionally, key matrices are derived for performance measurement purposes. Numerical results demonstrate the superiority of the dynamic allocation scheme while also providing insights into resource investment and division.

We present a navigation system that combines ideas from hierarchical planning and machine learning. The system uses a traditional global planner to compute optimal paths towards a goal, and a deep local trajectory planner and velocity controller to compute motion commands. The latter components of the system adjust the behavior of the robot through attention mechanisms such that it moves towards the goal, avoids obstacles, and respects the space of nearby pedestrians. Both the structure of the proposed deep models and the use of attention mechanisms make the system's execution interpretable. Our simulation experiments suggest that the proposed architecture outperforms baselines that try to map global plan information and sensor data directly to velocity commands. In comparison to a hand-designed traditional navigation system, the proposed approach showed more consistent performance.