Search papers, labs, and topics across Lattice.
The Physical Unified Device Architecture (PUDA) is introduced as an AI-native hardware harness specifically designed for self-driving laboratories (SDLs), enabling agents to autonomously manage experiments through a command-line interface rather than a traditional GUI. This architecture ensures that hardware execution is deterministic, atomic, and auditable, while also preserving the provenance of experimental data through structured records linked by run identifiers and timestamps. The key result is that PUDA effectively decouples scientific orchestration from physical operations, allowing for more efficient and reliable interactions between AI systems and physical tools in experimental settings.
PUDA revolutionizes self-driving laboratories by enabling AI agents to autonomously execute experiments with complete data provenance, bypassing the limitations of traditional graphical interfaces.
Physical Unified Device Architecture (PUDA) is an AI-native hardware harness for self-driving laboratories (SDLs). Rather than building a human-centered graphical user interface (GUI) orchestration layer, PUDA creates a command-line runtime environment that lets agents observe, orient, decide, and act over experiments while hardware execution remains deterministic, atomic, and auditable. Headless by design, devices appear through discoverable command-line interfaces, JSON protocols are routed through a distributed messaging system, and command responses, data products, and reports are preserved as structured records. PUDA organizes protocols, runs, samples, measurements, and command logs into an AI-native data structure linked by run identifiers and timestamps, preserving provenance from submitted protocol through hardware response to resulting data products. PUDA separates scientific orchestration from physical operation and data telemetry: agents choose experiments, while PUDA executes validated commands and captures provenance-linked state, responses, and data. The contribution is not another optimizer, orchestrator, or recipe language. It is a practical execution and data environment for agentic SDLs; the broader physical AI implication is that PUDA provides an AI-native hardware harness for AI systems to interact with physical tools.
