Xolver Research
Research for bounded, reviewable physical intelligence.
We study how robots can learn and act while preserving explicit contracts, deterministic enforcement, reproducible evidence, and meaningful operator control.
Research implementation
Safe Play Pretraining
Learning reusable manipulation abilities through simulated play under explicit safety contracts, with a first downstream study in contact-rich peg insertion.
Manipulation priorsSafe reinforcement learningEvidence provenance
Read the research
Lite v0
ContractBench-DROID Lite
Evaluating whether robot policy data carries the contracts, safety context, replay records, and evidence needed before physical deployment.
Runtime readinessDataset contractsReplayability
Read the research
A consistent research boundary.
Across projects, learned models propose actions; explicit contracts constrain them; runtimes execute or refuse them; and evidence records preserve how an artifact was produced and evaluated.