Active inference as a model of collision avoidance behavior in human drivers
Julian F. Schumann, Johan Engström, Leif Johnson, Matthew O’Kelly, Joao Messias, Jens Kober, Arkady Zgonnikov · 2026
Read Active inference as a model of collision avoidance behavior in human drivers by Julian F. Schumann, Johan Engström, Leif Johnson, Matthew O’Kelly, Joao Messias, Jens Kober, Arkady Zgonnikov (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13253847.txt.
Description
Julian Schumann and co-authors model how drivers dodge crashes in a 2026 paper. Avoiding a collision needs fast threat spotting and a quick, apt move, yet past models covered only parts of that skill. Their model uses active inference, a theory that the brain acts to cut surprise and uncertainty.
The model was tested on three crash setups: a lead car braking, an oncoming car drifting in, and a car failing to yield. It matched broad findings from past reviews and fine details from two simulator studies, covering timing, choice of move, and execution. The authors offer it as a general frame for driver behavior.
Catalog record
| CREATOR | Julian F. Schumann, Johan Engström, Leif Johnson, Matthew O’Kelly, Joao Messias, Jens Kober, Arkady Zgonnikov |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 157497 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |