Your Robot's Safety Functions Already Work. What If the Input Lies?

Summary

VicOne LAB R7 shows that robots can act on manipulated inputs while following their safety rules, and that safety functions depend on sensor readings, estimates and stop signals that can be wrong or spoofed. The blog cites research on adversarial images against vision-language-action models and reports its own tests in which text on a poster changed a robot dog's movement and inaudible crafted audio changed a hospital robot's simulated behavior. It recommends testing adversarial scenarios before deployment and revisiting safety evidence as software, models, sensors and conditions change.

Mitigation

Teams can test adversarial scenarios before deployment and revisit the evidence as software, models, sensors, and operating conditions change.

Topics

• Robotics and embodied AI

Related items

• InfoAnthropic sets price range of $70 to $78 in upcoming IPO as AI lab marches toward NasdaqSame vendor · CNBC Technology
• InfoWhat could China get from Jensen Huang?Same vendor · The Verge (AI)
• InfoJim Cramer says Anthropic's IPO could make or break the AI trade. Here's whySame vendor · CNBC Technology
• InfoHugging Face’s CEO Says His P(Doom) Is ‘Close to Zero’Same vendor · Wired (Security)
• InfoBuilding on open source AI? Hugging Face’s policy chief on the costs, risks, and trade-offsSame vendor · TechCrunch (Security)