Choose an edition
Edition: Engineer. Technology, experiments and limitations.
Physical AI — the path to a beautiful tomorrow.
THE REPLICANT TRUTHA NEWSPAPER ABOUT PHYSICAL ARTIFICIAL INTELLIGENCE
Forecast · 2026-10-31 · CET
MORNING · 09:00
6.6°
Fog
Wind: E 2.6 m/s · 0%
MIDDAY · 12:00
8.1°
Cloudy
Wind: SE 3.2 m/s · 0%
EVENING · 18:00
8.9°
Cloudy
Wind: E 2.6 m/s · 0%
Daily: 5.8–11.1 °C
Precipitation probability: 0%
All we can do is learn to be human while the rain falls.
Issue № 3 ·
rev. 2 · Archive
Two new research methods: predicting motion and learning from failed actions.
Robots can plan more effectively if they anticipate how a scene will change. WorldFlow, reported on October 29, predicts both future video frames and the movement of selected points in three-dimensional space. This is a predictive world model, not a system that directly commands motors.
A robot may keep moving while making no progress. Event2Reward, introduced on October 29, learns to distinguish stalls, setbacks and recoveries. The estimated progress helps shape rewards for reinforcement learning rather than relying only on final success labels.
The October 29 WorldFlow study predicts future video and 3D point trajectories; average displacement error on SpatialCog was 0.060 m.
Concepts & terms
The key ideas in this issue, explained briefly.