MAROKO133 Breaking ai: New method to pick up even ‘faintest whispers’ of nuclear prolifera

📌 MAROKO133 Breaking ai: New method to pick up even ‘faintest whispers’ of nuclear

Nuclear activity detected from space—primarily via commercial and military satellite imagery—has played a key role in the Trump administration’s ongoing Iran conflict.

Now, scientists from the University of Florida aim to take the US’s nuclear detection capabilities to the next level. They are developing new space-based remote sensing technologies for nuclear security. According to the scientists, these could detect even the “faintest whisper” of nuclear proliferation.

Next-gen nuclear security capabilities

The new work is supported by a nuclear forensics consortium led by the Defense Threat Reduction Agency and the National Nuclear Security Administration. Together, they are developing next-generation detectors that can identify faint nuclear-related signals from orbit.

“It means UF is helping lead on a difficult and important class of space-security problems at a particularly important moment,” Kyle C. Hartig, Ph.D., a professor at the University of Florida’s Nuclear Engineering Program, explained in a press statement. “These projects position UF as a leader in developing novel technologies for detecting, characterizing, and interpreting nuclear-related signatures from space.”

Hartig and James Baciak, Ph.D., both members of the UF Astraeus Space Institute, are leading two complementary projects focused on orbital remote sensing technologies.

One of those projects is developing advanced radiation detection systems that can monitor nuclear materials from orbit. The other is exploring the use of optical and X-ray sensing techniques to detect and analyze nuclear tests from space—including any low-yield or concealed tests.

According to Hartig, his team aims to refine their method until they can pick up even the “faintest whispers” of nuclear proliferation. When it comes to the development of nuclear weapons, they aim to ensure that nothing remains hidden.

Separating nuclear threats from the noise

Space-based remote sensing technologies provide global coverage via satellites, making them a robust detection tool. However, space also presents key challenges in the form of weight and size restrictions. At the same time, any sensors must be capable of distinguishing weak signals from complex background noise.

“The problem is not just whether you can detect something,” Hartig said, “but whether you can detect it confidently and interpret it correctly.”

The teams have not disclosed any technical specifications regarding their work, presumably due to its sensitive military nature. However, they emphasize that their goal is to make space-based detection much more reliable and precise. Their work takes an end-to-end approach that integrates physics, materials science, sensor design, and data analysis.

Beyond the development of their technology, the teams are training a new generation of scientists and engineers in space-based nuclear security.

“This work can improve how we monitor activity in space, verify agreements, and support nuclear forensics and attribution,” Hartig said. “It’s about building the technical foundation for better understanding and better decision-making.”

🔗 Sumber: interestingengineering.com

📌 MAROKO133 Eksklusif ai: ByteDance Introduces Astra: A Dual-Model Architecture fo

The increasing integration of robots across various sectors, from industrial manufacturing to daily life, highlights a growing need for advanced navigation systems. However, contemporary robot navigation systems face significant challenges in diverse and complex indoor environments, exposing the limitations of traditional approaches. Addressing the fundamental questions of “Where am I?”, “Where am I going?”, and “How do I get there?”, ByteDance has developed Astra, an innovative dual-model architecture designed to overcome these traditional navigation bottlenecks and enable general-purpose mobile robots.

Traditional navigation systems typically consist of multiple, smaller, and often rule-based modules to handle the core challenges of target localization, self-localization, and path planning. Target localization involves understanding natural language or image cues to pinpoint a destination on a map. Self-localization requires a robot to determine its precise position within a map, especially challenging in repetitive environments like warehouses where traditional methods often rely on artificial landmarks (e.g., QR codes). Path planning further divides into global planning for rough route generation and local planning for real-time obstacle avoidance and reaching intermediate waypoints.

While foundation models have shown promise in integrating smaller models to tackle broader tasks, the optimal number of models and their effective integration for comprehensive navigation remained an open question.

ByteDance’s Astra, detailed in their paper “Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning” (website: https://astra-mobility.github.io/), addresses these limitations. Following the System 1/System 2 paradigm, Astra features two primary sub-models: Astra-Global and Astra-Local. Astra-Global handles low-frequency tasks like target and self-localization, while Astra-Local manages high-frequency tasks such as local path planning and odometry estimation. This architecture promises to revolutionize how robots navigate complex indoor spaces.

Astra-Global: The Intelligent Brain for Global Localization

Astra-Global serves as the intelligent core of the Astra architecture, responsible for critical low-frequency tasks: self-localization and target localization. It functions as a Multimodal Large Language Model (MLLM), adept at processing both visual and linguistic inputs to achieve precise global positioning within a map. Its strength lies in utilizing a hybrid topological-semantic graph as contextual input, allowing the model to accurately locate positions based on query images or text prompts.

The construction of this robust localization system begins with offline mapping. The research team developed an offline method to build a hybrid topological-semantic graph G=(V,E,L):

• V (Nodes): Keyframes, obtained by temporal downsampling of input video and SfM-estimated 6-Degrees-of-Freedom (DoF) camera poses, act as nodes encoding camera poses and landmark references.
• E (Edges): Undirected edges establish connectivity based on relative node poses, crucial for global path planning.
• L (Landmarks): Semantic landmark information is extracted by Astra-Global from visual data at each node, enriching the map’s semantic understanding. These landmarks store semantic attributes and are connected to multiple nodes via co-visibility relationships.

In practical localization, Astra-Global’s self-localization and target localization capabilities leverage a coarse-to-fine two-stage process for visual-language localization. The coarse stage analyzes input images and localization prompts, detects landmarks, establishes correspondence with a pre-built landmark map, and filters candidates based on visual consistency. The fine stage then uses the query image and coarse output to sample reference map nodes from the offline map, comparing their visual and positional information to directly output the predicted pose.

For language-based target localization, the model interprets natural language instructions, identifies relevant landmarks using their functional descriptions within the map, and then leverages landmark-to-node association mechanisms to locate relevant nodes, retrieving target images and 6-DoF poses.

To empower Astra-Global with robust localization abilities, the team employed a meticulous training methodology. Using Qwen2.5-VL as the backbone, they combined Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO). SFT involved diverse datasets for various tasks, including coarse and fine localization, co-visibility detection, and motion trend estimation. In the GRPO phase, a rule-based reward function (including format, landmark extraction, map matching, and extra landmark rewards) was used to train for visual-language localization. Experiments showed GRPO significantly improved Astra-Global’s zero-shot generalization, achieving 99.9% localization accuracy in unseen home environments, surpassing SFT-only methods.

Astra-Local: The Intelligent Assistant for Local Planning

Astra-Local acts as the intelligent assistant for Astra’s high-frequency tasks, a multi-task network capable of efficiently generating local paths and accurately estimating odometry from sensor data. Its architecture comprises three core components: a 4D spatio-temporal encoder, a planning head, and an odometry head.

The 4D spatio-temporal encoder replaces traditional mobile stack perception and prediction modules. It begins with a 3D spatial encoder that processes N omnidirectional images through a Vision Transformer (ViT) and Lift-Splat-Shoot to convert 2D image features into 3D voxel features. This 3D encoder is trained using self-supervised learning via 3D volumetric differentiable neural rendering. The 4D spatio-temporal encoder then builds upon the 3D encoder, taking past voxel features and future timestamps as input to predict future voxel features through ResNet and DiT modules, providing current and future environmental representations for planning and odometry.

The planning head, based on pre-trained 4D features, robot speed, and task information, generates executable trajectories using Transformer-based flow matching. To prevent collisions, the planning head incorporates a masked ESDF loss (Euclidean Signed Distance Field). This loss calculates the ESDF of a 3D occupancy map and applies a 2D ground truth trajectory mask, significantly reducing collision rates. Experiments demonstrate its superior performance in collision rate and overall score on out-of-distribution (OOD) datasets compared to other methods.

The odometry head predicts the robot’s relative pose using current and past 4D features and additional sensor data (e.g., IMU, wheel data). It trains a Transformer model to fuse information from different sensors. Each sensor modality is processed by a specific tokenizer, combined with modality embeddings and temporal positional embeddi…

Konten dipersingkat otomatis.

🔗 Sumber: syncedreview.com