AI for Science in Space: Orbital Laboratories, Planetary Fieldwork, and Embodied Autonomy

Abstract:Artificial intelligence for science (AI4S) is extending from interpretation of existing data to the design and execution of experiments. Space offers distinctive scientific opportunities while restricting physical support. Microgravity and extraterrestrial environments expose phenomena that terrestrial experiments cannot fully reproduce; finite samples, constrained resources, and limited opportunities for intervention complicate sustained investigation. This critical review examines orbital laboratories and planetary in situ science across biology, materials, fluid and thermal physics, and adaptive exploration. We distinguish learning from space-derived data, selecting scientific actions, executing them, and preserving experimental validity. Terrestrial self-driving laboratories provide complementary evidence on optimization, dedicated automation, robotic manipulation, and the support needed for unattended operation. The synthesis connects scientific gains already demonstrated by bounded AI systems to gaps in observation, executable actions, and continuity of valid evidence. Space robots can expand the attainable scope of autonomous science when necessary interventions exceed validated instrument capabilities and timely human support is unavailable. Their value must be established against dedicated mechanisms, redundancy, and human-supported operation. We develop a framework connecting sample history, scientific decisions, physical execution, and claim-specific validity. A worked orbital design, a planetary extension, and matched evaluation schemes separate the contributions of sensing, decision policies, and physical actions. The resulting agenda measures autonomy through valid scientific return, task coverage, intervention costs, and evidence integrity across complete campaigns.

47 pages, 5 figures, 7 tables. Ancillary evidence files included

Robotics (cs.RO)

arXiv:2610.39689 [cs.RO]

(or arXiv:2610.39689v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2610.39689 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

evidence/MANIFEST.json

evidence/README.txt

evidence/reproduce_evidence.py

evidence/research/background_records.json

evidence/research/biology_records.json

evidence/research/discovery_links.json

evidence/research/doi_verification_new.json

evidence/research/evidence_codebook.txt

evidence/research/evidence_counts.json

evidence/research/evidence_encoding_overrides.json

evidence/research/figure_provenance.json

evidence/research/figure_source_records.json

evidence/research/ground_fetch_log.json

evidence/research/ground_fulltext_retrieval_log.json

evidence/research/ground_queries_executed.json

evidence/research/ground_records.json

evidence/research/ground_search_log.json

evidence/research/ground_web_queries.json

evidence/research/literature_matrix.csv

evidence/research/literature_matrix.json

evidence/research/normalization_audit_log.json

evidence/research/normalization_overrides.json

evidence/research/orbital_physics_crossref_raw.json

evidence/research/orbital_physics_records.json

evidence/research/orbital_physics_search_log.json

evidence/research/planetary_robotics_records.json

evidence/research/planetary_robotics_search_log.json

evidence/research/pmc_retrieval_log.json

evidence/research/prior_source_audit_extracts.json

evidence/research/pubmed_screening_decisions.json

evidence/research/pubmed_search_log.json

evidence/research/raw_v3/literature_matrix.csv

evidence/research/raw_v3/literature_matrix.json

evidence/research/raw_v3/pubmed_screening_decisions.json

evidence/research/root_search_log.json

evidence/research/selection_rationale.txt

evidence/research/v4_methods_source_recheck_log.json

evidence/revision/ground_new_records.json

evidence/revision/ground_record_updates.json

evidence/revision/ground_revision_access_log.json

evidence/revision/root_revision_source_log.json

evidence/revision/space_coding_updates.json

evidence/revision/space_new_records.json

evidence/revision/space_revision_access_log.json

evidence/revision/v5_design_access_log.json

evidence/revision/v5_design_record_updates.json

evidence/revision/v5_skill_access_log.json

evidence/revision/v5_space_access_log.json

evidence/revision/v5_space_record_updates.json

evidence/tools/normalize_evidence.py

evidence/tools/reconcile_evidence.py

evidence/tools/validate_evidence.py

(47 additional files not shown) You must enabled JavaScript to view entire file list.

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.