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

2025-10-21

AI Summary

Quadruped robots struggle to construct persistent, consistent, and queryable object-level semantic maps in real indoor environments. Method: This paper proposes an online semantic mapping system that fuses LiDAR-based geometric data with monocular object detections. It employs cross-frame data association, co-located point-weighted fusion, and global object lifecycle management to dynamically maintain named object instances atop an occupancy grid map—ensuring object persistence under occlusion, multi-view observation fusion, and disambiguation of repeated detections. Contribution/Results: To our knowledge, this is the first real-time (>10 Hz), robust object-level semantic mapping system deployed on quadruped platforms. It outputs a compact, structured semantic layer—including object class, 6DoF pose, and confidence—directly consumable by task planners. Extensive experiments demonstrate its stability and consistency under viewpoint changes, partial occlusions, and dynamic disturbances.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Low Level & Physics-based Vision
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

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.

Problem

• Online semantic mapping for quadruped robots in indoor environments
• Integrating sensor detections into persistent global object instances
• Generating compact queryable object layers for robotic planning

Innovation

• Integrates range geometry with camera detections
• Merges co-located detections within a frame
• Associates repeated detections into persistent instances