3D Anomaly Detection (AD) is a promising means of controlling the quality of manufactured products. However, existing methods typically require carefully training a task-specific model for each category independently, leading to high cost, low efficiency, and weak generalization. This study presents a novel unified model for Multi-Category 3D Anomaly Detection (MC3D-AD) that aims to utilize both local and global geometry-aware information to reconstruct normal representations of all categories. First, to learn robust and generalized features of different categories, we propose an adaptive geometry-aware masked attention module that extracts geometry variation information to guide mask attention. Then, we introduce a local geometry-aware encoder reinforced by the improved mask attention to encode group-level feature tokens. Finally, we design a global query decoder that utilizes point cloud position embeddings to improve the decoding process and reconstruction ability. This leads to local and global geometry-aware reconstructed feature tokens for the 3D AD task. MC3D-AD is evaluated on two publicly available Real3D-AD and Anomaly-ShapeNet datasets, and exhibits significant superiority over current state-of-the-art single-category methods, achieving 3.1% and 9.3% improvement in object-level AUROC over Real3D-AD and Anomaly-ShapeNet, respectively. The code is available at https://github.com/iCAN-SZU/MC3D-AD.

A existing strapdown inertial navigation system and global navigation satellite system (SINS/GNSS) integrated ground gravimetry method cannot receive GNSS information in sheltered places, such as tunnels and dense forests, which leads to the degradation of the system to pure inertial navigation and the rapid divergence of gravimetry error. To solve the problem, a novel method of gravimetry is proposed in this letter. The proposed method utilizes an SINS and a 2-D laser Doppler velocimeter (2D-LDV), which both developed by our unit, in conjunction with GNSS to achieve dynamic ground gravimetry. A high-precision laser Doppler velocimeter (LDV) is introduced to provide velocity information in a GNSS-denied environment. Also, high velocity and interference acceleration output accuracy of LDV also can further improve the gravimetry accuracy. We also discuss the methods of LDV data compensation and data fusion. Three-repeated-measuring-line experiment in mountainous areas shows that the SINS/LDV/GNSS integrated gravimetry system has an internal accuracy of 1.59 mGal with a spatial resolution of 1.1 km and 0.68 mGal with a spatial resolution of 1.7 km. Comparing this proposed method with the traditional SINS/GNSS and SINS/LDV gravimetry methods, it appeared that the gravimetry result using SINS/LDV/GNSS has the best internal accuracy. The feasibility of the SINS/LDV/GNSS integrated gravimetry system has been demonstrated by pertinent experiment.

Traditional biological and pharmaceutical manufacturing plants are controlled by human workers or pre-defined thresholds. Modernized factories have advanced process control algorithms such as model predictive control (MPC). However, there is little exploration of applying deep reinforcement learning to control manufacturing plants. One of the reasons is the lack of high fidelity simulations and standard APIs for benchmarking. To bridge this gap, we develop an easy-to-use library that includes five high-fidelity simulation environments: BeerFMTEnv, ReactorEnv, AtropineEnv, PenSimEnv and mAbEnv, which cover a wide range of manufacturing processes. We build these environments on published dynamics models. Furthermore, we benchmark online and offline, model-based and model-free reinforcement learning algorithms for comparisons of follow-up research.