Touch is at the frontier of robotics

Robots can now work by feel. One interesting demo at IROS 2026 comes from Daimon Robotics: a robot picks up tiny beads, aligns their holes, and threads them onto a flexible string. It looks simple, but the tricky part starts when the robot makes contact. A bead can slip, the string can deform, and a small change in force can throw off the next move. Vision can tell the robot where the bead is, but not exactly what is happening in its grasp. Daimon is tackling this with Daimon-TWM, a tactile-grounded world model that uses touch to understand the interaction, predict what happens next, and adjust the robot’s actions. The model is built on Daimon’s growing vision-tactile data, collected from both robot sensors and human operators, with the goal of giving robots more useful experience with physical interaction. A small bracelet demo, but it points to something important--robots may need to learn not only how the world looks, but how objects respond when they touch them.