Yafei Li

The rapid growth of e-commerce has driven an increasing demand for robotized warehouses to handle large-scale logistics orders. Upon receiving orders, a warehouse engages in task planning that involves two crucial stages: matching the orders with racks that contain the required items, and planning the robot routes to deliver those racks for order fulfillment. Hence, effective task planning is essential for maximizing order throughput. However, while existing techniques perform well for orders that involve items from a single rack, they exhibit low efficiency and poor performance when dealing with complex orders that require multiple items from different racks. In this paper, we introduce the robotized warehouse complex task planning problem and propose a novel Complex Order Online Planning (COOP) framework to address the challenge. Specifically, the framework matches orders with racks using a maximal coverage matching method, optimized through vector similarity search and a residual matching strategy. Then, it adopts an effective progressive prioritized pathfinding algorithm to transport matched racks with minimal delivery cost. Finally, the framework introduces an enhanced pathfinding-aware rack selection model that considers rack delivery costs from the pathfinding stage to collaboratively optimize rack matching and overall planning scheme. Extensive experiments on real-world and synthetic datasets demonstrate that our approaches exhibit strong performance across various parameter configurations.

Load balancing during resource allocation (RA) in multicell multi-input multi-output non-orthogonal multiple access (MC-MIMO-NOMA) poses significant challenges for the deployment of massive MIMO-NOMA in next-generation networks. This paper introduces load-balancing algorithms to address RA challenges in massive MIMO-NOMA systems. First, we formulate the general RA problem as a load minimization problem, involving the joint optimization of resource allocation and user clustering. To minimize computation complexity, this problem is then reduced to a suboptimal RA problem within each cell. However, due to the non-convex nature of the problem, obtaining an optimal solution is not straightforward. To overcome this, we propose the power to targeted load optimization (PTLO) approach to solve the RA problem in each cell based on underload and overload scenarios. By leveraging the PTLO approach, we develop a user clustering strategy using branch-and-bound and weighted matching theory to optimize RA in each cell. Through simulations, we evaluate the performance of the proposed load-balancing algorithms (LB-BB-MIMO-NOMA and LB-M2O-MIMO-NOMA) against benchmark algorithms such as Correlated-MIMO-NOMA, Coalition-MIMO-NOMA, Gain-Diff-MIMO-NOMA, Greedy-MIMO-NOMA, and MIMO-OMA. The results demonstrate that the proposed algorithms consistently outperform the benchmarks. Furthermore, we provide a detailed analysis highlighting the efficiency of the proposed algorithms in the MC-MIMO-NOMA networks.

Federated Learning (FL) can be coordinated under the orchestration of a central server to build a privacy-preserving model without collaborative data exchange. However, participant data heterogeneity leads to local optima divergence, affecting convergence outcomes. Recent research focused on global sharpness-aware minimization (SAM) and dynamic regularization to enhance consistency between global and local generalization and optimization objectives in FL. Nonetheless, the estimation of global SAM introduces additional computational and memory overhead. At the same time, the local dynamic regularizer cannot capture the global update state due to training isolation. This paper proposes a novel FL algorithm, FedTOGA, designed to consider optimization and generalization objectives while maintaining minimal uplink communication overhead. By linking local perturbations to global updates, we improve global generalization consistency. Additionally, by linking the dynamic regularizer to global updates, FedTOGA improves global gradient perception and strengthens optimization consistency. Crucially, global updates are directly delivered to clients, allowing them to incorporate global knowledge without communication and computational cost. We also propose neighborhood perturbation to enhance local perturbation, analyzing its strengths and working principles. Theoretical analysis shows FedTOGA achieves faster convergence $O(1/T)$ on the non-convex function. Empirical studies demonstrate that FedTOGA outperforms existing algorithms, with a 1% accuracy increase and 30% faster convergence, achieving SOTA.