MAROKO133 Breaking ai: World’s first 6-ton tiltrotor aircraft with 342 mph top speed aces

📌 MAROKO133 Eksklusif ai: World’s first 6-ton tiltrotor aircraft with 342 mph top

A Chinese-built tiltrotor aircraft weighing about six tons reached a major aviation milestone on Sunday when it completed its maiden flight in Southwest China’s Sichuan Province.

The tiltrotor aircraft, called the Lanying R6000, is the world’s first tiltrotor in its weight class and was independently developed by United Aircraft, marking a notable step in China’s push into advanced vertical lift aviation.

Designed to combine helicopter-like flexibility with airplane-level speed and range, the R6000 aims to reshape regional air travel. Its first flight signals more than a test success. It highlights China’s growing ambitions in tiltrotor technology, a field long dominated by a handful of global players.

A new chapter for tiltrotor aircrafts in aviation

According to United Aircraft, the R6000 tiltrotor aircraft is intended for point-to-point air commuting in cities, across sea routes, and in mountainous regions. The company said the aircraft can shorten travel times and reduce geographic barriers while helping to build cross-regional “door-to-door transport networks, according to a release sent to the Global Times by United Aircraft.”

Project manager Zhao Fengming described the achievement as a breakthrough moment for the country’s aerospace sector. “The emergence of the R6000 indicates that China has reached the forefront of the world in the cutting-edge aviation field of tiltrotor, breaking the long-standing technological monopoly,” said Zhao, as reported by Global Times.

Powering the aircraft is the AES100 engine, developed independently by the Aero Engine Corporation of China.

Engineering choices that set it apart

The Lanying R6000 uses a distinctive tiltrotor configuration that allows it to smoothly transition between vertical takeoff and landing and high-speed horizontal flight. This approach blends the precise hovering and vertical lift of helicopters with the longer range and faster cruise of fixed-wing aircraft.

Unlike designs that rotate entire engine nacelles, the R6000 uses a tilting-rotor shaft system. United Aircraft says this choice reduces complexity and delivers advances in both flight control and power system design. It also prevents ground crews and nearby structures from being exposed to hot exhaust airflow during takeoff and landing.

This feature is especially important for maritime operations. By reducing heat-related risks, the aircraft can operate from ordinary ship decks and offshore platforms that lack specialized heat-resistant coatings, expanding its potential use at sea.

Speed, range, and smart storage

In fixed-wing mode, the R6000 cruises at about 342 miles per hour, roughly twice the speed of traditional helicopters. It can carry a maximum commercial payload of about 4,409 pounds, which is significantly higher than that of similarly sized helicopters.

The aircraft’s maximum range reaches roughly 2,485 miles, around four times that of conventional helicopters, with a service ceiling near 25,000 feet. These figures position the R6000 for long-distance missions that typically fall outside the reach of rotary-wing aircraft.

To address space constraints, the design includes tandem-wing folding and blade-retraction technologies. These features reduce the aircraft’s footprint when parked, making storage and deployment easier in confined areas such as urban pads and ship decks.

Roles in a growing low-altitude economy

The company said the successful maiden flight reflects breakthroughs in core tiltrotor technologies, including an intelligent tilt-and-flight control system with fully independent intellectual property rights. The transmission system meets strict aviation safety standards, supporting future large-scale use.

Beyond commuter travel, the R6000 is expected to support medical evacuations, firefighting, police patrols, and disaster relief, where rapid and precise deployment is critical. The company also sees opportunities in high-end private travel and aerial sightseeing.

These ambitions align with China’s broader low-altitude economy. Xinhua News Agency has reported growing use of drones and helicopters for deliveries and tourism.

Forecasts from the Civil Aviation Administration of China estimate the low-altitude market could reach about $210 billion by 2025 and potentially exceed $490 billion by 2035, highlighting the expanding space below 3,280 feet where new aircraft like the R6000 may soon operate.

🔗 Sumber: interestingengineering.com

📌 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