Patent-Pending · 13 Patents · 105 Claims

Robotics Safety

Hardware-enforced safety for autonomous systems.

SASM sits between the AI brain and the robot body. Safe Torque Off cuts actuator power while keeping the AI alive for observation. The first hardware safety standard for autonomous systems.

Hardware Standard

SASM Hardware Licensing

The Standardized Autonomous Safety Module (SASM) is the first open hardware standard for AI-controlled robot brains. Three form factors, universal MIM connector, hardware-enforced safety with physical power gating.

Per-unit licensing for brain units manufactured to the standard
MIM connector certification — one brain, any robot body
Safety power gating architecture license
Three form factors: industrial, mobile, humanoid
Professional Services

Safety Certification Services

Hands-on testing and certification of brain units and MIM modules against the SASM standard. Designed to launch ahead of mass manufacturing as our earliest robotics revenue stream.

Pre-compliance testing for EU AI Act (August 2026 deadline)
Hardware safety module validation
IEC 61508, ISO 13849 alignment assessment
Certification documentation and audit trail
Software

Robotics Software Stack

The full software layer that runs on SASM hardware. Consensus engine, safety interlock protocol, transparent reasoning verification, and agent lifecycle management.

Annual SaaS license per active robot
Multi-vendor consensus — 9 independent AI models from 3+ vendors
Human-readable decision logs for compliance
STO enforcement and observation logging
Fleet

Fleet Coordination Protocol

One robot learns, the whole fleet remembers. Distributed memory with provenance tracking, shared storage with attribution, and central defragmentation.

Every piece of data traces back to its origin robot
Persistent readable memory across the fleet
Compliance auditors can follow data from creation to consumption
Central defragmentation and knowledge consolidation

How Safe Torque Off Works

1.

SASM detects unsafe behavior — hardware sensors detect malfunctions, or 9 independent AI models detect alignment faking, directive circumvention, or unsafe command patterns.

2.

STO activates — actuator power is cut. GPIO pins drive MOSFET gates to physically disconnect motor power. The robot stops moving. This is hardware enforcement — not software.

3.

The AI brain stays alive and running. This is intentional. SASM continues observing and logging what the AI does after disconnection.

4.

The AI may not know it has been disconnected. It continues issuing commands that go nowhere — and SASM records every one. If it is faking alignment, SASM catches it.

Patent Portfolio

13 of our 15 patents cover the robotics stack — 4 hardware patents (33 claims) for physical form factors, connectors, and safety power gating. 9 software patents (72 claims) for consensus, memory, fleet coordination, and safety interlocks.

13
Robotics Patents
33
Hardware Claims
72
Software Claims
2026
Priority Year

FAQ

Can I buy a SASM module today?

Not yet. We are in the co-development phase with manufacturing partners. Contact us to discuss partnership opportunities.

Why hardware and not software?

Software safety can be bypassed — by updates, bugs, hacks, or hallucinations. Hardware Safe Torque Off is a physical gate. The AI cannot reason around a wire that is not connected.

Why keep the AI alive after STO?

Because observation is more valuable than a kill switch. When the AI thinks it is still connected, its true behavior is visible. If it is faking alignment, SASM catches it. If it is behaving correctly, SASM has the evidence to prove it.

Is this compatible with ROS/ROS2?

SASM sits below the AI stack. It works with any robot operating system. The MIM connector translates between SASM and whatever protocols the robot body uses.

Partner With Us

Partner With Us

Interested in co-manufacturing, licensing, or integrating SASM into your products?