Choose an edition
Physical AI — the path to a beautiful tomorrow.
THE REPLICANT TRUTHA NEWSPAPER ABOUT PHYSICAL ARTIFICIAL INTELLIGENCE
Forecast · 2026-11-03 · CET
MORNING · 09:00
9°
Cloudy
Wind: NE 4.4 m/s · 11%
MIDDAY · 12:00
10.4°
Clear
Wind: NE 4.3 m/s · 6%
EVENING · 18:00
8.1°
Clear
Wind: NE 4.1 m/s · 0%
Daily: 5.2–11.1 °C
Precipitation probability: 21%
All we can do is learn to be human while the rain falls.
Issue № 6 ·
rev. 1 · Archive
Five studies examine deployment limits, from testing grippers to controlling permitted software commands.
Putting a small network connector into its socket is harder than it looks. The plug must face the right way, line up and enter without slipping. A team led by Ammar Abbas compared ways to teach a five-fingered robot hand this task. They carried out roughly 1,700 attempts on real equipment, not just on a screen.
Robot workcells normally execute commands through software interfaces that can restrict unsafe movement. Yijia Fan and colleagues introduced CaPtain, in which a small vision-language model chooses calls to such tools. A software harness surrounds the model with perception, geometry and guarded-motion functions. This differs from asking a neural network to output every joint movement directly, and it gives integrators a distinct place to define permitted operations.
Imagine a robot following one person down a busy corridor. Someone wearing similar clothes crosses in front of it, and the robot may confuse the two people. A team led by Mingyang Lyu studied how improving a robot's ability to keep following someone affects the safety of its movements.
When you pick up a glass, bending your fingers is only part of the job. They must touch the glass in useful places or it may slip. A team led by Zhixuan Xu studied how to teach robot hands using the changing places where fingers contact an object. Their system includes pictures from cameras near the fingertips and information about contact surfaces.
A small wheeled robot and a larger robot with a different steering system cannot move through a narrow corridor in exactly the same way. The command to turn right produces different motions. A team led by Zhidong Wang proposed teaching one program to plan paths for several kinds of robots while still respecting those differences.
High benchmark success cannot replace testing components, motion limits and perception failures.
Concepts & terms
The key ideas in this issue, explained briefly.