Unstructured environments challenge unmanned ground vehicle (UGV) navigation with complex terrain and open-set obstacles. Existing inertial-aided navigation using external odometry suffers from localization errors in rugged off-road conditions, while sparse LiDAR point clouds degrade traversability prediction. The purpose of this study is to address these limitations by developing a robust autonomous navigation framework that integrates SLAM-assisted normal distributions transform (SANDT) and divergence-guided temporal point cloud fusion.
First, the authors replace conventional vehicle odometry with inertial data maintained by a LiDAR-based SLAM method, supplying a continuous and stable coarse guess for NDT registration to improve localization. Second, voxel-wise NDT representations of adjacent point clouds are computed; key historical frames are selected via Jensen-Shannon divergence and fused to densify the current point cloud and improve traversability estimation. Finally, the authors integrate these components into an autonomous navigation framework and validate it in real-world scenarios.
Experiments demonstrate that the authors’ framework achieves accurate localization and seamless indoor-to-outdoor navigation, outperforming baseline methods in traversability prediction, navigation success rate and obstacle avoidance.
This paper presents a robust autonomous navigation framework for unstructured environments. SANDT enables cross-scene navigation in complex terrains, and global divergence-based temporal fusion pioneers LiDAR-based traversability estimation. Further details on localization, traversability prediction and real-world navigation are provided in the supplementary video.
Yuenan Zhao, Ziming Zhang, Ruifeng Wang et al.· Robotic Intelligence and Aut...· 0 citations
Zero-shot industrial anomaly detection (ZIAD) aims to develop a unified model capable of directly identifying unseen anomaly categories in images without requiring reference samples. Recently, large-scale Vision-Language Models (VLMs) such as CLIP have shown great potential for solving this task. However, existing methods typically rely on manual text prompts to guide VLMs in anomaly detection, which often fail to capture fine-grained semantic cues, leading to limited accuracy. To address the challenge, this paper proposes a novel Cross-Modal Guidance Learning (CMGL) framework for ZIAD. Instead of handcrafted textual prompts, CMGL introduces learnable prompting mechanism to fully exploit the collaborative guidance between visual and textual modalities for efficient unseen anomaly detection. Leveraging the frozen image encoder of pre-trained CLIP, the CMGL extracts multi-scale patch tokens and global tokens of the input image as visual representations. Then, informed by the cross-modal information, adaptive prompt vectors are constructed to obtain textual representations. In the process, a Learnable Context Block (LCBlock) and a Multi-Layer Perceptron (MLP) are introduced to extract holistic semantics and fine-grained details, and an Adaptive State Vector Module (ASVM) is designed to learn generalized normal and abnormal state vectors from extensive text descriptions. By aggregating the outputs of these components, textual representations of the image are acquired through the frozen text encoder. Finally, a Local-Global Token Integrator (LGTI) and an Uncertainty-Aware Anomaly Fusion Module (UAFM) are proposed to achieve anomaly recognition and localization through visual–textual alignment. Extensive experiments on multiple industrial datasets demonstrate the superiority of our method. Note to Practitioners—This paper presents a Cross-Modal Guidance Learning (CMGL) framework to address anomaly detection under the zero-shot setting. Unlike previous approaches that rely on manually crafted text prompts, the proposed CMGL derives task-relevant prompt cues from cross-modal data by the designed learnable prompting mechanism, guiding the model to automatically recognize and localize unseen anomaly categories without requiring any reference samples. Extensive experiments demonstrate the effectiveness and strong generalization capability of the proposed approach. Benefiting from these properties, our method provides a novel and effective ZIAD solution for identifying potential anomalies in real-world industrial scenarios where data distributions are uncertain or anomaly-related information cannot be clearly specified. Our project page is publicly available at https://aicoder12.github.io/CMGL/
Tiyu Fang, Lin Zhang, Ran Song et al.· IEEE Transactions on Automat...· 0 citations