MAROKO133 Breaking ai: Researchers develop antibacterial coating that punctures bacteria b

📌 MAROKO133 Breaking ai: Researchers develop antibacterial coating that punctures

Researchers at Chalmers University of Technology have developed a new method to stop bacteria from attaching to surfaces by physically puncturing them before they form biofilms.

The approach uses metal-organic frameworks, a material that received the 2025 Nobel Prize in Chemistry, but applies it in a way researchers say has not been tried before.

The technique avoids antibiotics and toxic metals, two common tools that carry risks like antibiotic resistance and environmental harm.

Biofilms are a major problem in healthcare and industry. Once bacteria attach to a surface, they multiply and form a protective slime layer that makes them harder to remove.

These films can grow on catheters, implants, ship hulls, and industrial pipes.

The result can be hospital infections, fuel inefficiency, clogged infrastructure, and the increased use of harsh chemicals.

Instead of chemical-based antibacterial action, the Chalmers team created a surface coating that kills bacteria on contact.

Researchers grew one metal-organic framework on top of another to form nanostructures sharp enough to rupture bacterial cells.

“Our study shows that these nanostructures can act like tiny spikes that physically injure the bacteria, quite simply puncturing them so that they die. It’s a completely new way of using such metal-organic frameworks,” said lead author Zhejian Cao, PhD in Materials Engineering.

The coating can be added to different materials, including those used in medical devices.

Cao said this approach offers a key advantage: “It fights a major global problem, as it eliminates the risk that controlling bacteria will lead to antibiotic resistance.”

Precision engineering challenge

Designing the surface required careful control of spacing between the tiny spikes. Too much distance gave bacteria room to settle. Too little spacing reduced pressure and allowed microbes to survive.

“If the distance between the nanotips is too large, bacteria can slip through and attach to the surface,” Cao said.

He explained that placing them too close has the opposite problem, similar to how a person can lie on a bed of nails without injury.

Unlike earlier antibacterial research using metal-organic frameworks, the Chalmers method does not rely on metal ions or chemical release.

It works purely by mechanical damage.

Suited for large-scale production

The team believes the technology can be produced at an industrial scale.

“These coatings can be produced at much lower temperatures than, for example, the graphene arrays previously developed at Chalmers,” said co-author and MOF researcher Lars Öhrström.

He noted that this makes the coating compatible with temperature-sensitive plastics used in implants and may also allow recycled plastics to be used in production.

The researchers say the material could help prevent hospital infections, reduce reliance on biocidal paints in marine settings, and improve efficiency in industrial systems.

As antibiotic resistance continues to rise globally, they see mechanical antibacterial surfaces as a promising alternative path.

The study is published in the journal Advanced Science.

🔗 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