Research toward a safer autonomous world

A research lab working on safety for machines that will share space with humans, starting with perception

01
asymmetry

Autonomous technology vs safety

Autonomous machines are entering everyday life faster than the frameworks meant to govern them

deployment vs oversight
capabilitygovernance
gap · wideningtime →
02
perception

Every downstream safety failure cascades from perception

In October 2023, a Cruise robotaxi dragged a pedestrian twenty feet. It was not a planner failure. It was a perception failure, and every downstream safety guarantee was built on top of it.

safety stack · cascade trace
origin · 01
01perception
scene misread
02planner
acted on what it was shown
03safety oversight
flagged no anomaly
04outcome
harm
trace · san francisco · 2023-10-02verdict · perception
Robotics incidents→
03
research

Perception Safety Research

Research toward a perception layer that downstream autonomous systems can rely on.

perception field · per-cell confidence
16 × 8
resolvedflagged uncertainmisread
All research→
04
collaborate

If the thesis matches what you work on, write to us

Open to co-authored research, practitioner interviews, and conversation with safety engineers in humanoid and AV programs. Help us make autonomy safe for the people who will share roads, factories, and homes with these machines.

Contact→