The goal of this work is to adapt Segment Anything Models (SAM) into crack segmentation tasks via automatic label generation, thus eliminating manual annotation cost. In this regard, an intuitive approach is to extract edges of crack samples and generate labels via the dilation and erosion processes for fine-tuning SAM. However, this simple solution cannot guarantee the quality of generated labels, as crack regions will be corrupted due to the imperfect edge detection. To this end, this paper proposes CoGenSAM, a novel Codebook-interactive Generative Labeling framework that enables an annotation-free SAM fine-tuning. To achieve this, in the first stage, we pre-train a vector-quantized variational auto-encoder (VQVAE) by reconstructing the synthesized crack-like structures for learning crack-aware priors within the codebook. In the second stage, these priors help another VQVAE serve as the restoration model to restore the randomly corrupted structures into uncorrupted ones. Specifically, we propose the crack-aware contrastive-interaction to maximize the mutual information with the above priors via codebook interaction. Then, high-quality labels can be generated by restoring corrupted labels from edge detection, contributing to an annotation-free SAM fine-tuning. We collect a new dataset, Bridge2025, to address the limited availability of related bridge-oriented benchmarks. Experiments show that our performance is close to fully-supervised methods.

Imitation learning (IL) shows its superiority in faster strategy optimization by leveraging expert demonstrations. However, as one of the powerful IL methods, behavior cloning (BC) suffers from covariate shift problems, where the agent’s policy drifts away from the expert’s, leading to compounding errors and decreased generalization performance. To this end, we propose Search-based Inverse Dynamics Imitation Learning, namely SIDIL, to enhance the robustness of imitation learning by augmenting expert demonstrations via trajectory perturbation and stitching. Specifically, SIDIL first employs a nearest-neighbor search method to find the closest points between expert and perturbed data, generating new actions near the expert data via a stitching strategy. By exploiting this, the agent can recover from deviations and complete tasks under a wider range of conditions. Experimental results on various robotic tasks show that SIDIL outperforms baseline algorithms with higher success rates across multiple tasks. Meanwhile, SIDIL is allowed to expand the attractive region around expert demonstrations by stitching states from expert demonstrations, enjoying a higher task completion success rate even for states outside the expert distribution. These results highlight our potential to enhance humanoid locomotion and dexterous robotic hand manipulation, making it particularly suitable for industrial manufacturing automation where adaptability, robustness, and safety are essential.

Offline imitation learning (IL) enables embodied agents of AI-driven automation control systems to acquire policies from demonstrations without interacting with the environment. However, collecting extensive expert demonstrations that rely on a manually designed reward function is labor-intensive, and even impractical for dynamic real-world settings. To mitigate the reliance on large amounts of reward-annotated expert data, previous works have made great efforts by leveraging both expert and suboptimal demonstrations. In this paper, we reveal that existing methods still suffer from suboptimal results for two reasons: (i) reward signals in suboptimal demonstrations are not reliable, due to these rewards derived from inexperienced annotators, thus can not reflect the actual rewards, and (ii) those suboptimal demonstrations, which are significantly distant from expert behaviors, result in low reconstructed rewards. Moreover, motivated by the recent diffusion-based foundation model, we propose Expert-Like Transition Imitation Learning (ELTIL), a novel generative trajectory augmentation method that effectively leverages diffusion models. ELTIL re-designs the reward function based on expert proximity, and then proposes amplified return conditioning for achieving high-quality trajectory generation. More specifically, instead of relying on environment-provided rewards or manually designed rewards, ELTIL first serves as a good reward labeler for transitions by measuring their distance to expert states. These re-designed rewards then serve as guidance in the diffusion process, with amplified returns contributing as conditioning values to bias generation toward expert-consistent behaviors. Extensive experiments on diverse D4RL benchmarks demonstrate that ELTIL consistently improves the performance and stability of reward learning and offline IL methods, maintaining reliability under varying noise levels, reward sparsity, and dataset distributions. These characteristics make ELTIL well-suited for deployment in robust and reliable automated control systems such as robotic manipulation and autonomous driving.

Offline reinforcement learning (RL) demonstrated remarkable performance in learning valid policies by benefiting from high-quality offline datasets. However, collecting such a dataset is labor-intensive, especially for humanoid locomotion. For this reason, many data augmentation techniques have been proposed to improve the quality of offline datasets through noise injection or data synthesis. However, existing data augmentation methods are noise-sensitive, resulting in limited capability in complex robotic environments. To address these issues, we propose guided amplified learning with Lipschitz constraint (GALC), a novel trajectory augmentation method that employs the reward-amplification-guided conditional diffusion model for noise-insensitive data augmentation. Specifically, we introduce a local Lipschitz continuity constraint to regulate the reverse denoising process from the offline dataset. Consequently, the exploration of the diffusion model can be restricted within the local continuity region of the original dataset, thereby generating high-reward trajectories. Moreover, the generated trajectories are also enforced to be noise-insensitive to perturbations, thus enjoying robustness. Notably, our proposed method can prevent the generation of unsafe actions that do not align with the environment dynamics. Extensive experiments on sparse reward scenarios and high-dimensional robotic tasks show that our proposed GALC achieves significant improvements in both the augmented trajectories and policy performance.

Deep neural networks (DNNs) have substantially achieved high predictive accuracy in many vision tasks. However, we find that they are poorly calibrated for crack recognition tasks, as these DNNs tend to produce both under-confident and over-confident predictions in such safety-critical applications, thereby limiting their practical use in real-world scenarios. To address this issue, we propose a novel attack-inspired calibration loss (AICL) that explicitly regularizes class probabilities to be better confidence estimation. Specifically, we first propose the attack-inspired correctness estimation method (ACE) that aims to estimate the correctness degree of each sample via adversarial attacks. Then, we propose Correctness-aware Distribution Guidance, which starts from a distribution perspective that enforces the ordinal ranking of the predicted confidence referring to the estimated correctness degree. The proposed method can be conveniently implemented on top of any DNNs-based crack recognition model by serving as a plug-and-play loss function. To address the limited availability of related benchmarks, we collect a fully annotated dataset, namely, Bridge2024, which involves inconsistent cracks and noisy backgrounds in real-world bridges. Our AICL outperforms the state-of-art calibration methods on various benchmark datasets including CRACK2019, SDNET2018, and our BRIDGE2024.

Since 2002, hundreds of thousands of vessels have equipped the Automatic Identification System (AIS), which continuously broadcasts its identity and location information for vessel collision avoidance. To utilize these scattered AIS data for further analysis, there are multiple AIS data platforms collecting AIS data from vessels around the world through their satellites and land-based stations. Thus, users can obtain AIS data of vessels from these platforms without dedicated devices. However, existing platforms work in silos, and AIS data is distributed across different platforms, resulting in reduced data availability. In addition, AIS is vulnerable to jamming and spoofing attacks, which can undermine the authenticity of AIS data. In this paper, we propose AISChain, a secure and fast blockchain-based AIS data platform. AISChain adopts consortium blockchain, which only permits those authorized parties (i.e., AIS data providers) to participate in the consensus protocol, and is compatible with current commodity AIS hardware. Since the whole system is co-maintained by multiple authorized parties, AISChain can integrate AIS data resources in a secure way. For avoiding repeated recording of AIS data on the chain, we design the Dynamic Bloom Filter Tree (DBFT) to realize efficient duplication detection in the transaction verification phase. We also propose the dual signature scheme to clarify the AIS data ownership. Moreover, we leverage the geographical location-based blockchain sharding approach to further improve the scalability of AISChain. We implement a prototype of AISChain, and conduct extensive experiments to evaluate the performance of AISChain. Evaluation results show that the search time of DBFT is negligible (4.3 ms) with an extreme low error ratio (0.4%). Meanwhile, AISChain can achieve more than 730 tx/s throughput even when nodes scale to 36. To the best of our knowledge, AISChain is the first work to apply the blockchain technology to secure the AIS data platform.