Human agent and robot teaming helps handle space mission anomalies
Toward Evidence-Driven Human-Agent-Robot Teaming for Earth-Independent Anomaly Triage
RoboticsArtificial IntelligenceHuman-Computer Interaction
Summary
In deep-space missions, astronauts cannot get real-time help from Earth when unexpected problems arise. The authors present a system where humans, AI agents, and robots work together to investigate these problems. The AI organizes information and hypotheses, the robot collects evidence in risky areas, and the human crew interacts with an AI assistant to make decisions. They tested this approach using realistic space scenarios and robot hardware. This system helps crews respond to issues even when direct access or instant Earth support is unavailable.
What this means in practice
- •For space mission operators: Manage unexpected spacecraft issues with coordinated human, AI, and robot teams enabling safer and informed anomaly diagnosis without Earth support.
- •For industrial safety teams: Use collaborative AI and mobile robots to investigate hazardous site anomalies where human access is restricted or risky.
Authors
Ignacio G Lopez-Francos, Alexis Gallagher, Samira Shalal
Abstract
Deep-space crews cannot rely on real-time ground support for urgent off-nominal events. Initial alerts may underdetermine cause, while discriminating evidence may reside in crew observations or at locations that are unsafe, costly, or unavailable for crew inspection. We present an evidence-driven architecture for human-agent-robot teaming in Earth-independent anomaly triage. Agentic AI is treated as a stateful coordinator over bounded, inspectable services rather than as a fully autonomous vehicle controller. A triage state manager maintains hypotheses, evidence provenance, uncertainty, operational context, and tool status; a crew-facing embodied agent elicits observations and explains assessment changes; and a mobile robot acquires targeted, localized evidence. Typed interfaces separate dialogue and orchestration from monitoring, robot command, context retrieval, and safety-critical control. Two scenarios illustrate the architecture: a crewed deep-space mission based on an actual ISS ammonia false alarm, where suspected contamination restricts crew access, and a power-interface anomaly at a crewed lunar base, where robotic inspection distinguishes a local connector fault from other causes ambiguous in remote telemetry. Our main contribution is an authority-bounded closed evidence-loop architecture, exercised in a hardware-in-the-loop integration prototype using Reachy Mini and an Innate MARS mobile robot.