The future leaves
signals in time.

Tech Xplore reports a new benchmark that tests AI memory for household robots. It notes that in-home assistive robots could clean and organize a home while the owner is away, but without enhanced memory they could cause problems, such as moving items like wallets and keys without being able to tell the owner where they were placed.

The headline reports that a continuous artificial muscle unlocks dexterous soft-robot motion. The supplied context only describes the challenge: an octopus can bend one part of an arm around an obstacle while another reaches into a small crevice to grab an object, and reproducing such local control in a soft robot requires multiple actuators plus mounting hardware and connections. No specific results are given.

A new AI framework aims to help machines understand 3D spaces in finer detail, such as distinguishing whether furniture is a chair, table, or bookcase and whether an opening is a door or a window. Such distinctions can affect how a service robot plans routes, avoids obstacles, and decides what it can safely interact with.

A team of researchers has developed a new system that makes humanoid robots move and react far more reliably, which they worked out on a group of soccer-playing robots. The work targets one of the biggest drawbacks of current robotics — struggling with real-world movement — and is reported as a major step forward for coordination.

Aaron Ames, the Booth-Kresa Leadership Chair and director of Caltech's Center for Autonomous Systems and Technologies (CAST) and a leader in robotic safety, says that while humanoid robot demonstrations are dazzling, safety is crucially missing before humanoids can play a larger role in our lives and society.

Inspired by the Venus flytrap, which closes its leaves to trap prey, KAIST researchers combined the roles of a sensing "skin" and grasping "muscle" in a single soft material that reportedly senses and grasps objects under light. When an electrically charged object comes near, ions inside the material move and produce an electrical signal.

MIT engineers developed a new paper-thin aquabot powered by muscle cells that swims through a watery maze. This biohybrid robot offers a way to design small, efficient 'biohybrid' robots.

Researchers at Cambridge's Bio-Inspired Robotics Laboratory are exploring how soil behaves as an intelligent system. By studying its structure, chemistry, and networks of microbes and fungi, they aim to inspire new technologies in bio-inspired computing, precision agriculture, and environmental sensing.

A new AI control system gives MIT's tiny flying robot insect-like agility, increasing its speed by about 450 percent and enabling 10 somersaults in 11 seconds. Researchers say the technology could eventually let miniature robots search earthquake rubble and navigate dangerous spaces conventional drones cannot reach.

MIT News reports an autonomous robotic lab that sets up and runs optics experiments on demand. The system could speed up testing of high-tech materials for applications such as solar cells, sensors, video displays, and quantum technologies.