Manipulate objects
Choose bounded arm motions, grasp actions, or task intent while simulation and code handle geometry, contacts, and limits.
Explore simulated robot arms, drones, rovers, and driving experiments using typed Jev decisions. These are research demos, not real-world deployment claims. Browse the collection in Jev Library.
9 entries in this collectionChoose bounded arm motions, grasp actions, or task intent while simulation and code handle geometry, contacts, and limits.
Select drone, rover, or vehicle actions from structured observations and inspect the resulting trajectory.
Use model probabilities as one input to a coded stop, rescan, or escalation rule in a simulated rover workflow.
Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz
A 3D planetary rover sandbox for experimenting with autonomous decisions using TypeSafe AI.
Interactive experiments from support routing to a 3D driving simulation: structured sensor state in, typed steer, brake, and overtake decisions out.
This demo uses Jev from TypeSafe AI to autonomously fly a drone in a random city from point A to point B, avoiding obstacles along the way. A trip costs $0.01.
EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs
Fine-grained robot control with Jev, physics previews, and configurable LIBERO tasks.
Just a weekend project with Claude as system two, and Jev as system One.
A MuJoCo xArm7 pick-and-place experiment. Jev selects an intent and bounded Cartesian directions; the shared controller applies motion and checks physical feedback. The published comparison is one recorded trial per controller, not a success-rate benchmark.
A simulated Franka arm stacks cubes in MuJoCo. Code previews candidate moves in physics; Jev chooses a move and judges grasp, release, and completion. The README reports one recorded run for each controller.