1: OpenIN supports multi-modal (text and image) and multi-type (demand, semantic, and instance-level) object navigation. Additionally, it enables maintaining scene representations through a dynamic …

In this work, we introduce OpenIns3D, a new 3D-input-only framework for 3D open-vocabulary scene understanding. The OpenIns3D framework employs a “Mask-Snap-Lookup” scheme.

We evaluated FSR-VLN across four comprehensive indoor datasets collected by humanoid robots, utilizing 87 instructions that encompass a diverse range of object categories.

OpenIN (Tang et al., 2025) focuses on navigation tasks where the robot must locate specific objects that have been moved, introducing a Carrier-Relationship Scene Graph (CRSG) to track objects and their …

We introduce Graph- Pad, a modifiable structured memory that an agent can tai- lor to the needs of the task through API calls. It comprises a mutable scene graph representing the environment, a navi- …

Advanced Functions – iOS To use OpenIn function, turn on “Konica Minolta Mobile Print” in the OpenIn menu.

Abstract—We introduce DualMap, an online open- vocabulary mapping system that enables robots to understand and navigate dynamically changing environments through natural language queries.