A single species found in the Alcatrazes Archipelago, brain coral, produces around 170 tons of calcium carbonate annually. This represents the retention of approximately 20 tons of carbon in mineral form, which can last for centuries or millennia. A study by the Federal University of São Paulo highlights the potential ecosystem services provided by subtropical corals.

Panoramic visual-inertial odometry (VIO) systems are crucial for navigating Global Positioning System (GPS)-denied environments, but their potential is hindered by image distortions caused by geometric inconsistent projection models.  

Self-driving cars know their own way in unpredictable traffic, thanks to path planning technology. Among current AI-driven efforts to make path planning more efficient and reliable, a research team has developed an optimization framework proven especially effective in uncertain environments. The results were published June 3 under the title “Action-Curiosity-Based Deep Reinforcement Learning Algorithm for Path Planning in a Nondeterministic Environment” in Intelligent Computing, a Science Partner Journal.

Could robots help those with mobility issues make a pizza? With support from the National Science Foundation, a team of Virginia Tech mechanical engineers are using robotic grippers and artificial intelligence to make that idea a reality.

The targeted engineering of artificial proteins with unique properties – that is possible with the assistance of a novel method developed by a research team led by Prof. Dr Dominik Niopek at the Institute of Pharmacy and Molecular Biotechnology (IPMB) of Heidelberg University. It centers around a new AI model. This allows for forecasting how two proteins have to be fitted together at the molecular level from individual parts – subunits – in order to engineer a functional, adjustable new protein. Called ProDomino, this open-source tool opens up many different possible applications in biotechnology and medicine.

Just like when multiple people gather simultaneously in a meeting room, higher-order interactions—where many entities interact at once—occur across various fields and reflect the complexity of real-world relationships. However, due to technical limitations, in many fields, only low-order pairwise interactions between entities can be observed and collected, which results in the loss of full context and restricts practical use. KAIST researchers have developed the AI model “MARIOH,” which can accurately reconstruct* higher-order interactions from such low-order information, opening up innovative analytical possibilities in fields like social network analysis, neuroscience, and life sciences.  *Reconstruction: Estimating/reconstructing the original structure that has disappeared or was not observed.