In Mobile Crowdsensing (MCS), online task allocation ensures timely task completion and improves overall system performance in dynamic environments through real-time scheduling and optimizing resource utilization. Existing Deep Reinforcement Learning methods have several limitations, including poor model performance, low system stability, and the problem of data privacy leakage. To address these issues, this paper proposes a lightweight privacy-preserving online task allocation framework called LO-GDRL (Lyapunov Optimization with Graph-based Deep Reinforcement Learning). LO-GDRL formulates NP-hard online task allocation as a graph-constrained optimization problem and designs a Deep Reinforcement Learning method with a new Dual-branch Graph Attention Dueling Network to enhance dynamic environment adaptation and complex dependency capture capability. To improve system stability, LO-GDRL establishes a dynamic-queue mechanism for dynamic resource coordination based on Lyapunov Optimization. Additionally, while preserving worker location privacy through differential privacy, the system achieves an optimal privacy-performance trade-off. The case studies on the simulation data of MCS systems based on the two real-world datasets verify the effectiveness of the proposed framework and demonstrate that our framework achieves more stable and superior performance across diverse environments compared to state-of-the-art methods.

Recently, Shuttle-Based Storage and Retrieval Systems (SBS/RSs) have emerged as a cornerstone of modern robotic handling systems. However, motion conflicts between four-way shuttle vehicles are introduced frequently due to the sparsely connected roadmap topology. Furthermore, the different time and energy costs between linear and direction-changing motions bring additional difficulties for classic solvers when applied directly. To address these issues, we propose Dynamic Graph-Driven A* (DGA*) for cooperative path planning in SBS/RSs. By fully exploiting the structured topology of SBS/RS roadmaps, the algorithm extracts sector-level topological graphs enriched with spatiotemporal attributes, effectively resolving conflicts while simultaneously optimizing motion costs. In addition, Recursive Preemption and Avoidance (RPA) is introduced to ensure motion coordination in congestion-prone areas commonly seen in SBS/RSs, through a combination of independent avoidance and recursive avoidance mechanisms. We implement our approach in a real warehouse with more than 240 vehicles and achieve a 17% improvement in system throughput while reducing runtime.

Recently, Shuttle-based Storage and Retrieval Systems (SBS/RSs) have garnered significant attention from both academia and industry, owing to their high spatial utilization and rapid response speed. However, the weak connectivity of roadmaps in densely stored environments increases the likelihood of congestion and deadlocks when multiple four-way shuttles operate simultaneously, thereby imposing greater demands for collaborative path planning. Instead of exhaustively coordinating the shuttle motions during the off-line planning or online local control stages, we solve the cooperative path planning challenge from the perspective of altering the road graph structure dynamically. More specifically, we propose an approach to automatically transfer the typical road graph of SBS/RSs into a hierarchical graph with a reduced size, and then dynamically adjust its edge properties to prohibit any motion conflicts. In this manner, the planning problem of large-scale shuttle groups can be easily resolved and all the potential congestions can be eliminated inherently. Finally, we build a complete multi-shuttle cooperative path planning system adaptable for large-scale problems.

Learning to predict agent motions with relationship reasoning is important for many applications. In motion prediction tasks, maintaining motion equivariance under Euclidean geometric transformations and invariance of agent interaction is a critical and fundamental principle. However, such equivariance and invariance properties are overlooked by most existing methods. To fill this gap, we propose Eq-Motion, an efficient equivariant motion prediction model with invariant interaction reasoning. To achieve motion equivariance, we propose an equivariant geometric feature learning module to learn a Euclidean transformable feature through dedicated designs of equivariant operations. To reason agent's interactions, we propose an invariant interaction reasoning module to achieve a more stable interaction modeling. To further promote more comprehensive motion features, we propose an invariant pattern feature learning module to learn an invariant pattern feature, which cooperates with the equivariant geometric feature to enhance network expressiveness. We conduct experiments for the proposed model on four distinct scenarios: particle dynamics, molecule dynamics, human skeleton motion prediction and pedestrian trajectory prediction. Experimental results show that our method is not only generally applicable, but also achieves state-of-the-art prediction performances on all the four tasks, improving by 24.0/30.1/8.6/9.2%. Code is available at https://github.com/MediaBrain-SJTU/EqMotion.

Exploring spatial-temporal dependencies from observed motions is one of the core challenges of human motion prediction. Previous methods mainly focus on dedicated network structures to model the spatial and temporal dependencies. This paper considers a new direction by introducing a model learning framework with auxiliary tasks. In our auxiliary tasks, partial body joints’ coordinates are corrupted by either masking or adding noise and the goal is to recover corrupted coordinates depending on the rest coordinates. To work with auxiliary tasks, we propose a novel auxiliary-adapted transformer, which can handle incomplete, corrupted motion data and achieve coordinate recovery via capturing spatial-temporal dependencies. Through auxiliary tasks, the auxiliary-adapted transformer is promoted to capture more comprehensive spatial-temporal dependencies among body joints’ coordinates, leading to better feature learning. Extensive experimental results have shown that our method outperforms state-of-the-art methods by remarkable margins of 7.2%, 3.7%, and 9.4% in terms of 3D mean per joint position error (MPJPE) on the Human3.6M, CMU Mocap, and 3DPW datasets, respectively. We also demonstrate that our method is more robust under data missing cases and noisy data cases. Code is available at https://github.com/MediaBrain-SJTU/AuxFormer.