MAROKO133 Eksklusif ai: US firm developing stealthy autonomous drone that can conduct prec

📌 MAROKO133 Eksklusif ai: US firm developing stealthy autonomous drone that can co

A California-based defense manufacturing firm has unveiled a new project to develop a stealthy autonomous drone. Named Vectis, the drone is being developed by Lockheed Martin’s secretive Skunk Works.

The company aims to fly the first Vectis prototype in 2027. Envisioned as a large “Category 5” reusable drone, the UAV will be designed to be customizable to match shifts in the threat environment.

The drone is planned to be capable of executing precision strike, ISR (Intelligence, Surveillance, and Reconnaissance) targeting, electronic warfare, and offensive and defensive counter air missions. The UAV will also provide multi-domain connectivity, whether standalone or as part of integrated teaming missions with crewed aircraft like the F-35.

Extended range

The drone is expected to offer an extended flight range to be compatible with Indo-Pacific, European, and Central Command theaters.

“Vectis is the culmination of our expertise in complex systems integration, advanced fighter development, and autonomy,” said OJ Sanchez, vice president and general manager, Lockheed Martin Skunk Works.

“We’re not simply building a new platform – we’re creating a new paradigm for air power based on a highly capable, customizable and affordable agile drone framework.”

Lethal collaborative combat aircraft

The company has revealed that Vectis’ development is underway.
Parts are ordered, and a team is executing. Skunk Works is investing the funds and manpower necessary to build and test survivable systems to meet customers’ evolving needs while broadening alignment with new tri-service architectures and global requirements as they are defined, according to a press release.

The drone will be capable of seamlessly integrating with 5th and next-gen aircraft to advance the Family of Systems vision for next-gen air dominance.

Proven Lockheed Martin performance on common control systems like the MDCX will be used to ensure compatibility across the command and control spectrum.

The Group 5 survivable and lethal collaborative combat aircraft (CCA) is aimed at advancing unparalleled air dominance for American and allied militaries.

Integrated capabilities

Lockheed Martin revealed that this system embodies the company’s pedigree in fighter aircraft, autonomous systems, and open mission architectures. As the future of air power takes shape, Skunk Works is charting a critical path with Vectis to unlock new, integrated capabilities at an ultra-competitive speed and price point. 

The company’s Skunk Works has decades of experience leveraging speed, altitude, shape, advanced materials and more to keep crewed and uncrewed platforms safe in the most challenging environments to solve the warfighter’s hardest problems. All of this pioneering work is reflected in Vectis, which delivers class-leading survivability in an agile, multi-role package. 

With Vectis, Lockheed Martin Skunk Works is acting on a bold vision to deliver high-end survivability and mission systems capability at aggressive cost targets and design, build and fly within two years, as per the release.

🔗 Sumber: interestingengineering.com

📌 MAROKO133 Breaking ai: ByteDance Introduces Astra: A Dual-Model Architecture for

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