MAROKO133 Breaking ai: NASA Rover Captures Electric Dust Devils Wandering the Surface of M

📌 MAROKO133 Breaking ai: NASA Rover Captures Electric Dust Devils Wandering the Su

There’s an electrifying new development in Mars science. NASA’s Perseverance rover has just captured proof of a weather phenomenon that was long suspected, but until now, never observed: electric discharges that brew within the dust devils that torment Mars’ surface.

The discovery, described in a new study in the journal Nature, confirms that lightning discharges occur in the Martian atmosphere. The dust devils that the discharges appear in are a common fixture on the Red Planet. Like on Earth, they’re whirlwinds created by rapidly rising columns of warm air heated by their proximity to the ground, shooting their way through the cool air which falls to take the rising warm air’s place. 

On Mars specifically, it was suspected that dust trapped in this whirlwind whips together to create a static charge through friction, a manifestation of the same so-called triboelectric effect that causes a spark after you shuffle across a carpet and touch a metal doorknob.

“Triboelectric charging of sand and snow particles is well documented on Earth, particularly in desert regions, but it rarely results in actual electrical discharges,” lead author Baptiste Chide, a member of the Perseverance science team and a planetary scientist at L’Institut de Recherche en Astrophysique et Planétologie in France, said in a NASA statement about the research. “On Mars, the thin atmosphere makes the phenomenon far more likely, as the amount of charge required to generate sparks is much lower than what is required in Earth’s near-surface atmosphere.”

That lightning on Mars had eluded detection until now was a long source of frustration to Mars scientists, as it had already been established to take place on other planets like Saturn and Jupiter, which are far more distant and aren’t observed up close by robots as we do the Red Planet.

The finding required some astonishing good luck. The detection was made by a microphone on the rover’s SuperCam instrument designed to analyze the acoustics of Martian rocks zapped by the SuperCam laser — or in other words, to record sound, not zips of static discharges. 

But the instrument kept picking up more and more electrical disturbances, in all logging 55 since its mission began in 2021, NASA said. Sixteen of them were recorded when a dust devil passed directly over the rover. Because the the number of discharges didn’t increase during the planet’s frequent dust storms, the scientists surmise that it must be coming from the dust devils instead — which, in another fortunate twist, happened to pass by the rover more often than anyone anticipated, allowing them to confirm the suspicion.

The discovery has exciting implications. Lightning can cause unique chemical reactions and affect the chemical balance of the planet’s surface, perhaps altering the odds of creating complex compounds — and possibly even organic molecules.

More on Mars: Scientist Say They’ve Found Caves on Mars That May Contain Life

The post NASA Rover Captures Electric Dust Devils Wandering the Surface of Mars appeared first on Futurism.

🔗 Sumber: futurism.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