Defense Systems (United States)

ABSTRACT Research on autonomous driving in unstructured outdoor environments is less advanced than in structured urban settings due to challenges like environmental diversities and scene complexity. These environments–such as rural areas and rugged terrains–pose unique obstacles that are not common in structured urban areas. Despite these difficulties, autonomous driving in unstructured outdoor environments is crucial for applications in agriculture, mining, and military operations. Our survey reviews over 250 papers for autonomous driving in unstructured outdoor environments, covering offline mapping, pose estimation, environmental perception, path planning, end‐to‐end autonomous driving, datasets, and relevant challenges. We also discuss emerging trends and future research directions. This review aims to consolidate knowledge and encourage further research for autonomous driving in unstructured environments. To support ongoing work, we maintain an active repository of up‐to‐date literature and open‐source projects at: https://github.com/chaytonmin/Survey‐Autonomous‐Driving‐in‐Unstructured‐Environments .

In this study, the effect of heat treatment at 300°C (for residual stress relief) on the mechanical properties of Al-2.5%Fe-2%Mn alloy manufactured by laser powder bed fusion (L-PBF) was investigated. Hardness measurements showed that the heat-treated sample (HT sample) exhibited comparable hardness to the as-built one (AS sample). Exposure tests at 300°C for up to 1008 hours revealed no significant change in hardness within the first 100 hours, but a decline was observed beyond this period, consistent with the AS material's behavior. Tensile tests conducted at room temperature (RT), 200°C, and 300°C demonstrated that the HT sample maintained strength and ductility comparable to literature values. Fracture surface observations revealed dimple patterns and flat regions corresponding to melt pool boundaries, indicating fracture along these boundaries. The HT sample exhibited similar fracture modes and mechanical properties to the AS sample, suggesting that the residual stress relief heat treatment does not compromise the alloy's performance. These findings indicate that the heat-treated Al-2.5%Fe-2%Mn alloy retains sufficient mechanical properties for industrial applications, making residual stress relief heat treatment a viable option for AM-fabricated components.

Sewing garments using robots has consistently posed a research challenge due to the inherent complexities in fabric manipulation. In this paper, we introduce an intelligent robotic automation system designed to address this issue. By employing a patented technique that temporarily stiffens garments, we eliminate the traditional necessity for fabric modeling. Our methodological approach is rooted in a meticulously designed three-stage pipeline: first, an accurate pose estimation of the cut fabric pieces; second, a procedure to temporarily join fabric pieces; and third, a closed-loop visual servoing technique for the sewing process. Demonstrating versatility across various fabric types, our approach has been successfully validated in practical settings, notably with cotton material at the Bluewater Defense production line and denim material at Levi’s research facility. The techniques described in this paper integrate robotic mechanisms with traditional sewing machines, devising a real-time sewing algorithm, and providing hands-on validation through a collaborative robot setup.

The Reed-Solomon (RS) codes, which are a subset of error-correcting codes, are currently employed in a number of significant applications. The most notable of these are data recovery in storage systems, barcodes in management and advertising systems, and communication systems and networks. In the present technological era, RS codes over Galois fields GF(2m) are frequently employed in the aforementioned applications, with GF(28) being the most prevalent. This enables the representation of all 256 values of a byte as a polynomial with eight binary coefficients over GF(28). The motivation for verifying and generalizing the idea of systematic encoding of RS codes in a field with a base p other than 2 stems from the fact that the mathematical dependencies in arbitrary field GF(pm) are not only valid for GF(2m), but also have wider applicability. Consequently, the article establishes the specific features of the systematic encoding of p-ary Reed-Solomon codes and LFSR-based systematic encoder, conceptualizing them as a class of cyclic codes over any field GF(pm) whose base is a prime p other than 2.

Alakai Defense Systems has recently developed what we believe is the first lightweight UV Raman sensor for standoff trace detection of chemicals, which we refer to as Argos. Due to the small size and weight, Alakai has been able to deploy Argos on several Robotic platforms, such as Unmanned Ground Vehicles (UGV’s) and Unmanned Aerial Vehicles (UAV’s). Alakai will preset data on the detection performance of Argos along with videos of the Argos sensor deployed on UGV’s and UAV’s. We believe this standoff chemical detection from a UAV is a new capability which will allow replacement of the larger and longer-range Raman systems.

To minimize the adverse effects of noise while effectively preserving the natural randomness of atmospheric optical wireless channel characteristics, this paper firstly delves into the characteristics of denoising algorithms for shared secret key extraction from atmospheric optical wireless channels, and their similarities and differences from other signal denoising algorithms. Secondly, on the basis of the characteristics, it proposes a concept of collaborative denoising for shared secret key extraction technology, based on which an adaptive collaborative denoising algorithm based on CEEMDan (C-CD) is designed. Finally, numerical simulations are conducted to verify the performance of the proposed algorithm under diverse conditions, exhibiting its superior performance in terms of signal-to-noise ratio (SNR) and correlation.

As autonomous systems are being developed in multiple industries it has been recognized that a phased approach is needed both for technical development and user acceptance. Partially in response, the automotive and aircraft industries have published five or six Levels of Autonomy in an attempt to broadly characterize the amount of autonomy technology that is present in any particular vehicle. We propose six Spacecraft Autonomy Levels to characterize and describe the high-level autonomous capabilities for any given satellite. Our proposed spacecraft autonomy levels parallel those of the automotive and aircraft levels in an attempt to maintain consistency and a common understanding. We see these autonomy levels as useful in education and communication with lawmakers, government officials, and the general public.

In this study, we propose a neural network architecture considering feature fusion to improve active sonar target classification, where training data is scarce. We use various hand-crafted features with different perspectives for the active sonar one- and two-dimention raw data to enhance target classification performance. We use two kinds of features, in 1D feature and 2D features, because different perspectives on the same sample complement effectively by exchanging. For this, we contrived attention based complementary learning module to extract comprehensive features using the two kinds of features. To verify the generalization performance of this model, two real-ocean datasets were used and the classification results are compared with existing DL models.