Online Object-Level Semantic Mapping for Quadrupeds in Real-World Environments

TL;DR

This paper introduces an online semantic object mapping system for quadruped robots that integrates sensor data to create a persistent, queryable map of objects in real indoor environments, aiding navigation and planning.

Contribution

The system uniquely combines range and camera data for real-time, persistent object mapping in quadruped robots operating in complex indoor settings.

Findings

Map remains stable across viewpoint changes

Objects are accurately merged and tracked over time

System operates in real-time on robot hardware

Abstract

We present an online semantic object mapping system for a quadruped robot operating in real indoor environments, turning sensor detections into named objects in a global map. During a run, the mapper integrates range geometry with camera detections, merges co-located detections within a frame, and associates repeated detections into persistent object instances across frames. Objects remain in the map when they are out of view, and repeated sightings update the same instance rather than creating duplicates. The output is a compact object layer that can be queried (class, pose, and confidence), is integrated with the occupancy map and readable by a planner. In on-robot tests, the layer remained stable across viewpoint changes.