Article

CognitiveReality: Robot-Agnostic Semantic Gaussian Mapping and LLM Agent for Immersive Collaborative VR Teleoperation

CognitiveReality builds a semantically indexed Gaussian-TSDF map from a robot's RGB-D stream, shared by a VR operator and a tool-calling language agent. A single mapping program adapts to different platforms through configuration alone, accepting poses from robot SLAM, joint kinematics, motion capture, or visual tracking, and handles localization outages with shadow tracking and keyframe-anchored PnP, maintaining open-vocabulary instance identities and per-object quality at 2 Hz.

Part of the event: CognitiveReality: Robot-Agnostic Semantic Gaussian Mapping and VR Teleoperation

This page provides a summary and source link only.