Jev Robotics

A warehouse pick-verification step that compares a scanned item, the bin's expected contents, and the order line to decide between accept and re-scan, catching confusable picks a barcode alone would pass.

Measured robotics study that runs Jev as the decision layer for a 10,000-robot warehouse fleet over 41 bilingual incident templates and publishes a crossover against a self-hosted ModernBERT: 0.527 s p50, $24.57 per million decisions, and 91.3% agreement with template labels.

Multimodal finite-choice decision interface and MuJoCo robotic-arm workbench: dual-camera images and state go to a self-hosted Qwen3.5-9B with a corrective head, which returns one typed next-skill choice without generating text.

MuJoCo simulation where a local decider-2b model picks the next skill for an AgileX PiPER arm through a Jev-style typed-choice interface while the red cube target is pushed to new positions mid-run. Deterministic checks may reject a chosen skill but never substitute another.

Dan Makes Things wires an ESP32 robot so Jev picks the next move, and asks whether it is the first robot controlled that way.

A ManiSkill demo where plain-English goals drive a simulated Franka Panda: Jev picks one primitive per step from a catalog of about 30 hardcoded skills, and Python executes the move. No training or policy.

A Python CLI that connects multiple robots under one contract with an optional Jev stepper: Jev picks among permitted discrete calls while an LLM writes poses and prose and the executor enforces safety gates.

A MuJoCo and Franka Panda workbench where Jev chooses the next manipulation step for pick-and-place, stacking, and obstacle-carry tasks, with rule baselines and side-by-side model comparison.

Two-stage Jev control of a Franka Panda in MuJoCo: Jev selects a task intent, then X/Y/Z directions and a gripper command executed against real contacts, with 43 of 50 Jev episodes succeeding versus 48 of 50 for a rule baseline.

An SO-101 workbench where an evaluation model or rules baseline picks bounded joint steps from typed candidate actions: decision runs are spend-capped via the Vercel AI Gateway and drive a real LeRobot arm or mock hardware.

A fine-grained robot control study loop for LIBERO tasks: Jev layers an intent, a contact or motion family, and one of 27 control inputs, while reversible MuJoCo previews evaluate each candidate before execution.

A camera-only MuJoCo quadrotor that uses Jev for tactical maneuvers at 2.5 Hz while classical perception and a 50 Hz reflex layer keep safety outside Jev, clearing a five-station course.