Get Started

Applications

Deploy general-purpose robots across manufacturing.

Telekinesis brings perception, planning, and robotic skills together to automate tasks across manufacturing and logistics industries.

See Industries

Industries

Built for the factory floor, across industries.

Works across automotive, aerospace, and more, wherever precision and quality matter. The robot stays the same. Only the skills change from industry to industry.

Automotive

Aerospace

Railway

Logistics

Metal

Applications

Automate any application that is manual.

The same skill library already runs proven applications on real lines. These are the patterns underneath most of them.

Robotics use cases

Bin Picking

Localize and grasp parts from a jumbled, unfixtured bin, then hand off a clean pose downstream.

  • Automotive
  • Logistics
  • Metal

Palletizing & Depalletizing

Stack cases onto a pallet, or unstack mixed layers off one: pipes, cylinders, and cartons, one item at a time.

  • Logistics
  • Automotive

Sorting

Route parts by type, size, or defect into the right destination, screw by screw.

  • Logistics
  • Metal
  • Aerospace

Material Handling

Move mixed-case loads between conveyors, totes, and pallets without a fixed pick plan.

  • Logistics
  • Railway
  • Automotive

Vision-based Pick and Place

Detect an item's pose with vision, then move it from an arbitrary starting point to a target. The primitive underneath almost everything else here.

  • Metal
  • Aerospace
  • Automotive

Packaging

Place parts into honeycomb trays, foam, or cartons at the exact orientation the shipment needs.

  • Aerospace
  • Automotive
  • Railway

Kitting

Assemble a defined set of different parts into one kit, staged and ready for the next station.

  • Automotive
  • Aerospace

Wire Handling

Grasp, route, and connect flexible cable and wire harnesses that don't hold a fixed shape like a rigid part does.

  • Automotive
  • Aerospace

Vision AI use cases

Conveyor Tracking

Track parts moving on the line and hand off their live position to whatever picks them next.

  • Logistics
  • Automotive

Label Classification

Read and classify labels moving past a fixed camera, flagging mismatches before the next station.

  • Logistics
  • Automotive

Empty Box Detection

Tell an empty case apart from a full one on the line, without ever touching it.

  • Logistics

Ground Segmentation

Separate the floor plane from everything on it, so a mobile platform always knows what it can drive over.

  • Logistics
  • Railway

Forklift Segmentation

Pick moving forklifts and other equipment out of a scene so the workspace around them stays safe.

  • Logistics

Pedestrian Segmentation

Detect people in the workspace in real time, ahead of anything that needs to yield to them.

  • Logistics
  • Railway

PCB Segmentation

Localize components and traces on a circuit board for inspection or precision placement.

  • Metal
  • Aerospace

Open-Vocabulary Detection

Find and localize object classes the model was never explicitly trained on, from a text prompt.

  • Logistics
  • Metal

Deployment

Steps to deploy robots.

Install the SDK, prompt the application you want, validate it in NVIDIA Isaac Sim and Isaac Lab, then ship it to hardware with a single parameter change. Manipulator, AMR, or humanoid: the application doesn't change, only the hardware underneath it does.

  1. Install

    One command installs the SDK, with no separate build step and no vendored dependencies to wrangle.

    pip install telekinesis-ai

  2. Prompt the Application

    Describe the task in plain language, and the agent composes it into a typed, auditable program from the skill library.

    Pick up the aluminum parts from the angled tray and place them in the box in a grid format

    pick_and_place.py
    from telekinesis import cornea
from telekinesis.synapse import robot, gripper

# Perceive: segment the target part
mask = cornea.segment_image_using_sam(image, color="red")
pose = estimate_pose_from_mask(mask, intrinsics)

# Act: pick and place by composing Skills
robot.set_cartesian_pose(pose, speed=0.25)
gripper.close(force=50.0)
robot.set_cartesian_pose(place_pose, speed=0.25)
gripper.open()

  3. Test in Simulation

    Validate the generated application against NVIDIA Isaac Sim and Isaac Lab before it ever touches hardware.

  4. Deploy in Hardware

    Point the same application at a real robot: one parameter change, not a rewrite or a re-integration.

    • ABB
    • FANUC
    • KUKA
    • Universal Robots
    • Epson
    • Robotiq
    • OnRobot
    • SCHUNK
    • Unitree Robotics
    • and more
Get Started

Custom applications

Don't see your application? We'll build it with you.

Every application above started as a custom integration. Tell us what you're trying to automate and we'll scope it against the existing skill library first.

Contact us