MAROKO133 Hot ai: ByteDance Introduces Astra: A Dual-Model Architecture for Autonomous Rob

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

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

📌 MAROKO133 Hot ai: US Air Force plans lasers to protect HH-60W helicopters from h

The US Air Force has begun a market survey to equip its HH-60W Jolly Green II helicopters with advanced missile defense systems.

The move aims to improve protection during high-risk combat search and rescue missions.

The effort focuses on adding an Advanced Infrared Countermeasures (AIRCM) system. This technology can defeat modern heat-seeking missiles.

Officials see it as a critical upgrade for operations in contested environments. The initiative also signals a broader push to improve survivability across rotary-wing rescue fleets.

Closing capability gap

The HH-60W currently relies on missile warning sensors.

These systems can detect threats but cannot stop them. Crews must depend on evasive maneuvers during dangerous, low-altitude missions.

“The absence of a capable AIRCM [Advanced Infrared Countermeasures] system on this platform significantly increases the risk of infrared guided missile engagement, jeopardizing mission success, aircraft survivability and crew safety,” the Helicopter Sustainment Branch wrote in the notice.

To address this gap, the Air Force is evaluating two proven systems.

These include Northrop Grumman’s Common Infrared Countermeasure and Leonardo’s Distributed Aperture Infrared Countermeasure.

Both rely on laser-based technology to disrupt incoming missile seekers.

These systems can detect and defeat threats within seconds.

That capability could significantly improve survivability during rescue operations in hostile or contested airspace.

Industry integration work

The Air Force will provide the selected AIRCM system as government-furnished equipment.

Industry partners will handle integration across the HH-60W fleet.

This includes research, development, testing, and full-scale installation. Vendors must also design modification kits that fit within the helicopter’s limits.

These include power, cooling, avionics compatibility, and structural constraints.

“This effort is focused on identifying vendors with the comprehensive engineering, manufacturing and technical depth to execute the entire integration scope of work,” according to the notice.

The service also wants an open-architecture design.

Officials seek full data rights to support future upgrades and long-term sustainment.

“This market research is focused exclusively on the design, modification, and integration effort, not the procurement of the AIRCM system itself.”

The Air Force Life Cycle Management Center will oversee the process.

Officials plan to award a contract by the second quarter of fiscal 2027.

The HH-60W has already seen action in high-threat environments.

During recent operations in Iran, the aircraft supported a rescue mission for a downed F-15E Strike Eagle pilot.

The helicopters faced heavy small arms fire during the mission.

Some crew members suffered minor injuries. Despite the damage, the aircraft completed the extraction and exited the area safely.

It remains unclear whether infrared-guided missiles were used in that engagement.

However, the incident highlights the risks crews face without active countermeasures in modern combat zones.

“The integration of an AIRCM system is critical to mitigating this threat and ensuring the platform can operate effectively in contested environments,” the service said.

Budget plans reflect growing urgency behind the effort.

The Air Force has requested $87.9 million in RDT&E funding for the HH-60W in FY-27, up from $40.5 million in FY-26.

🔗 Sumber: interestingengineering.com