In a study published in Robot Learning journal, researchers propose a new learning-based path planning framework that allows mobile robots to navigate safely and efficiently using a Transformer model. By learning from Improved RRT* with Reduced Random Map Size path-planning algorithms and combining this knowledge with a modified right-of-way rule, the system enables reliable navigation and replanning in dynamic multi-robot environments.

As an innovative subtype of invasive brain-computer interfaces (BCIs), the Endovascular Brain-Computer Interface (EBCI) enables electrode delivery to target brain regions via endovascular intervention without craniotomy, combining high signal acquisition precision with minimally invasive safety.

In the lush landscapes of tropical agriculture, two waste products—oyster shells from the sea and coconut shells from the trees—are being combined to solve a major headache for farmers: how to turn animal manure into high-quality compost faster and more effectively. A study recently published in Carbon Research reveals that a unique "Ca-modified biochar" can act as a powerful catalyst for the composting process. Developed by a research team at Hainan University, this new material helps transform pig manure and rice straw into stable, nutrient-rich humus, significantly boosting the quality of the final fertilizer.

Professor Zhen Zhang's research group at the State Key Laboratory of Bionic Interface Materials Science, University of Science and Technology of China, proposed and constructed a neuromorphic computing system based on a cascaded van der Waals heterostructure two-dimensional nanofluidic membrane, achieving light-driven electron-ion coupling to simulate neural signal transmission and neuromorphic visual information processing. The article was published as an open access Research Article in CCS Chemistry, the flagship journal of the Chinese Chemical Society.