Back
roboticsagentsOpen source

RoboJev

Turn natural-language standing orders into bounded robot-arm decisions.

What Jev decides

Which target, motion, speed, avoidance, and next primitive fit the scene.

RoboJev uses Jev to choose actions for a WidowX arm and a MuJoCo simulation from compact scene reports and allowed primitives.

CHOICENOUL
Jev role
Choose robot-arm primitives and target behavior from a bounded action set.
Input
A compact scene report, available primitives, task text, and standing orders.
Output
Typed selections composed into limited arm setpoints.
Decision frequency
On meaningful scene changes or a silence timeout during control.
Fallback
Code checks preconditions and limits; documented physical-arm coverage is narrow.
Author reported · Source reviewed

How it works

Input
A compact scene report, available primitives, task text, and standing orders.
Jev
CHOICE + NOUL
Output
Typed selections composed into limited arm setpoints.

Overview

The controller converts scene state and standing orders into small typed questions, then composes Jev answers into arm commands under code-enforced limits. The README reports repeated paper-cup pick-and-place cycles on real hardware and broader behavior in simulation. It explicitly says the real-arm result is fitted to one cup and table, and several safety and perception scenarios were not tested on the physical arm.

Language
Python
Author
alee792
Sources checked Sep 24, 2026

Sources

Related projects