RGB + pose
Axes on every detected part — ready for approach.
SEDECO
From point cloud and STL to a reliable grasp — in-house tooling, robot control, competitively priced. Send an STL or ship samples; we move fast.
Scroll · scan
Live stack
Our 3D AI inference sees the bin, fits objects and stages the best grasp for the robot. Camera, integrations and outputs online.
Axes on every detected part — ready for approach.
Aligned depth map for volume and occlusion.
Controller linked — grasp to TCP.
Depth + metrics
Aligned metric depth beside live RGB. Capture, infer and drop timings stay visible — so you know what the stack does on the line.
Grasp tooling
Choose a point on the detected STL. Position follows every pose; distance runs along the surface normal. Approach direction and cylinder axis stabilize tool orientation.
Detect → control
Cell
Fin Ray-style or mechanical fingers — same vision stack, different end effector. Dirty parts, occlusion, pose variation: that is why 3D.
Pipeline
In-house tooling for training, synthetic data, recursive improvement and grasp selection — wired to the robot.
01
CAD as ground truth for fit and grasp.
02
Multi-GigE or Hikrobot 3D — scene to depth.
03
Fit under real occlusion and pose variation.
04
Accelerate learning when labels are scarce.
05
Feedback until the grasp is dependable.
06
Grasp point to controller and PLC handshake.
PoC
Send an STL and we move fast. Ship parts without CAD and our constructors can build an STL. Either way you get an honest PoC path — not weeks of stall.
Market systems often land in a high price band. We deliver vision, AI tooling and robot coupling as a complete stack at a sharper total cost — with performance that keeps up.
Share STL or samples, robot brand and takt — we’ll propose a PoC path.