Roboticists have struggled to get humanoid robots to effectively replicate athletic sports skills, such as those needed for tennis. These sports require highly dynamic motion, quick reactions, and high precision that robots are not usually equipped to handle. Past research attempted to use kinematic data and video-based extraction of human motion data, but these approaches were complex and often physically infeasible. Some robots have been trained to play sports like table tennis or football, but with limited agility and realism.

NUS researchers have developed a platform that lets lab-grown muscle tissues train themselves to record-breaking strength, with no external stimulation required. By mechanically coupling two muscle tissues so they continuously pull against each other, their own natural contractions become a round-the-clock workout. The resulting muscles powered OstraBot, an ostraciiform (a type of fish locomotion) swimming robot that reached 467 millimeters per minute—the fastest speed reported for any skeletal muscle-driven biohybrid robot.

MIT researchers have spent more than a decade studying techniques that enable robots to find and manipulate hidden objects by "seeing" through obstacles. Their methods utilize surface-penetrating wireless signals that reflect off concealed items. Now, the researchers are leveraging generative artificial intelligence models to overcome a longstanding bottleneck that limited the precision of prior approaches.