{"version":1,"type":"story","url":"https://digestai.news/story/nvidia-isaacteleop-tutorial-shows-how-to-build-a-retargeting-engine-in","json":"https://digestai.news/story/nvidia-isaacteleop-tutorial-shows-how-to-build-a-retargeting-engine-in.json","markdown":"https://digestai.news/story/nvidia-isaacteleop-tutorial-shows-how-to-build-a-retargeting-engine-in.md","slug":"nvidia-isaacteleop-tutorial-shows-how-to-build-a-retargeting-engine-in","headline":"NVIDIA IsaacTeleop tutorial shows how to build a retargeting engine in NumPy","summary":"MarkTechPost published a tutorial on NVIDIA IsaacTeleop’s retargeting engine, explaining how to turn XR hand and controller tracking into robot actions using a graph-based system. The article walks through building synthetic input data in NumPy, writing custom retargeters like a pinch detector, and composing them with built-in retargeters for gripper and SE(3) control. It demonstrates how to create a full pipeline that outputs an action vector per step, applies world-frame transforms, and manages state via a teleop state machine. All steps run on a plain Colab CPU without requiring a headset or simulator. The tutorial includes code for parameter tuning that persists across restarts and shows how to map controller inputs to dexterous hand joints. It concludes with next steps for using real hardware, recording replays, and driving simulators like Isaac Lab.","keyPoints":["The tutorial builds a retargeting engine using NumPy and TensorGroup types without hardware.","It includes a custom pinch retargeter with live-tunable parameters and built-in gripper/SE(3) retargeters.","The pipeline outputs an 8-D action vector and runs on Colab CPU, with state persistence via JSON."],"whyItMatters":"This tutorial lowers the barrier to understanding and implementing robot teleoperation pipelines, enabling developers to prototype and test IsaacTeleop workflows without expensive XR hardware or simulators.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["NVIDIA"],"models":[],"people":[]},"firstPublishedAt":"2026-10-04T00:19:38Z","updatedAt":"2026-10-04T00:19:38Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"MarkTechPost","title":"Inside NVIDIA’s IsaacTeleop: From Hand and Controller Tracking to Robot Actions with the Graph-Based Retargeting Engine","url":"https://marktechpost.com/2026/10/03/inside-nvidias-isaacteleop-from-hand-and-controller-tracking-to-robot-actions-with-the-graph-based-retargeting-engine","publishedAt":"2026-10-04T00:19:38Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"NVIDIA IsaacTeleop tutorial shows how to build a retargeting engine in NumPy\", 4 October 2026, https://digestai.news/story/nvidia-isaacteleop-tutorial-shows-how-to-build-a-retargeting-engine-in","publisher":"Digest AI","title":"NVIDIA IsaacTeleop tutorial shows how to build a retargeting engine in NumPy","datePublished":"2026-10-04T00:19:38Z","url":"https://digestai.news/story/nvidia-isaacteleop-tutorial-shows-how-to-build-a-retargeting-engine-in"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}