MAROKO133 Update ai: China’s new fire-safe, 250 Wh/kg organic battery can survive extreme

📌 MAROKO133 Eksklusif ai: China’s new fire-safe, 250 Wh/kg organic battery can sur

Researchers from Tianjin University and the South China University of Technology have developed a new flexible organic battery. The breakthrough, published in Nature, could, it is claimed, change the face of wearables.

The research team, led by Prof. Xu Yunhua, based the new tech on something called Poly (benzofuran dione), or PBFDO for short. This conductive organic polymer sits at the core of the innovation.

Traditionally, organic-based batteries, especially their cathodes, suffer because of poor electrical conductivity. Generally, the molecules dissolve into the electrolyte, resulting in overall poor energy density.

This new PBFDO polymer is different because it is something called n-type conductive. In non-technical speak, that means it naturally conducts electrons.

This makes it inherently structurally stable and better able to transport ions, like lithium. The team explains that this gives the new battery high capacity per weight, and that combination is what’s been missing for years.

Organic battery breakthrough achieved

According to the team, the new battery has an impressive energy density in the order of 250 Wh/kg. To put that into perspective, most lithium iron phosphate (LFP) batteries have a density of between around 160 and 200 Wh/kg.

Many larger commercial electrical vehicle (EV) cells typically range between around 240 and 300 Wh/kg. So, if claims of its energy density are true, this would it in the serious commercial territory range.

Furthermore, the battery has a temperature tolerance of between -94°F (-70°C) and 176°F (80°C). For reference, most lithium batteries tend to lose performance below -4°F (-20°C) and can degrade rapidly above 122°F (50°C).

So, if the temperature range is also correct and could be sustained over many charge cycles, that could prove groundbreaking. This would make it interesting for various applications, ranging from aerospace or Arctic-based settings to desert-based applications like wearables.

Another interesting element is the technology’s mechanical flexibility. The team tested its ability to bend, be compressed, and even punctured. They found that it passed all tests without exploding or catching fire.

For anyone familiar with traditional lithium batteries and damage, they’ll immediately see the benefit here. Since the new battery doesn’t release oxygen, it is far less likely to suffer from runaway combustion.

Safer, more sustainable batteries

“This research breaks through the traditional constraints of battery technology in terms of resource dependence and environmental impact,” explained Professor Yunhua to the South China Morning Post (SCMP).

“It not only matches the energy density of commercial batteries but also offers superior safety and a much wider operational temperature range,” he added.

As impressive as this all sounds, it is important to note that there are still some important issues yet to be addressed before it can be scaled. The first is whether the tech has a competitive charge-decharge lifespan.

It is also unclear how the tech would perform outside the lab, and how complex (i.e., expensive) it would be to produce commercially. That said, if it can scale, it could open the door for much safer lithium-ion batteries and provide an excellent power source for flexible wearables.

It could also provide a reduced reliance on metals like cobalt and nickel.

.

🔗 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