# MIT and Motional test explainable driving-planner module

_Published Wednesday, September 2, 2026 at 1:07 PM EDT · Robotics · Latest · Tier 2 — Notable_

![MIT and Motional test explainable driving-planner module — Primary](https://news.mit.edu/sites/default/files/images/202609/MIT-InterpretCars-01-press.jpg)

MIT and Motional researchers reported that their Concept-Wrapper Network, or CW-Net, produced real-time, understandable explanations of an autonomous vehicle planner's decisions without altering driving performance. In private-track tests using a Motional robotaxi, the explanations helped a safety driver better predict surprising vehicle behavior. Online simulations with nonexpert users produced similar results. The paper appears in Nature, and the system was trained on 130 million labeled driving scenes.

## Sources

- [MIT News](https://news.mit.edu/2026/system-helps-humans-predict-when-self-driving-cars-will-make-mistakes-0902)

---
Canonical: https://techandbusiness.org/newswire/2qN_sp8TT4STnLp5TWanpD
Published: 2026-09-02T17:07:12.386Z
Story chronology: 2026-09-02T15:00:00.000Z
Retrieved: 2026-10-17T22:18:55.184Z
Publisher: Tech & Business (techandbusiness.org)