Cognition and State Modeling

reMap

reMap exposes a ROS-based semantic mapping stack that fuses 3D region maps, robot state, and symbolic queries so robots can ask where entities are and publish query results back into the runtime.

Tool Introduction

Core parameters, trigger timing, and visual before/after demo references.

Short Explanation

Run reMap when a robot needs a persistent semantic scene model that can answer symbolic spatial questions over mapped entities.

InputROS scene state + symbolic query patterns + optional dynamic query settings

OutputJSON query results, result topics, TF frames, semantic map updates

Trigger TimingTriggered when the ROS launch file receives synchronized sensor streams.

RuntimeROS 2 Humble / C++ / OpenVDB / Conda build mirror

BeforeROS scene state + symbolic query patterns + optional dynamic query settings

Prepare the scene, image, video, sensor stream, prompt, or configuration expected by the original project.

AfterJSON query results, result topics, TF frames, semantic map updates

Read the produced visualization, prediction, map, trajectory, mask, grasp pose, or other documented artifact.

Preset Example

A quick-run style example for the documentation page.

Inputtools/reMap/ros2_ws demo scene

Promptpatterns: ['tiago_pro isIn ?room']

ExpectedA successful query response such as `[{"room":"kitchen"}]` plus a published result topic and optional TF frame.

Parameters And Output

Readable controls and the meaning of each returned artifact.

Parameter Explanation

patternstext

SPARQL-inspired symbolic patterns used to query the semantic map.

dynamictogglefalse

Whether the query should remain active and publish updates over time.

frequencytext{sec: 1, nanosec: 0}

Polling frequency for dynamic queries.

publish_tftoggletrue

Whether result entities should also be exposed as TF frames.

Output Explanation

json

Structured query answers returned by the ROS service.

success

Boolean status for the query call.

result_topics

Published point-cloud or query result topics under `/remap/query/results/...`.

tf_frames

Optional TF frames representing queried entities.

How To Use

Official resources, deployment steps, academic context, citation, and source-reported benchmark numbers.

Resources

GitHubhttps://github.com/RepresentationMaps/remap_plugin_query Code Downloadhttps://github.com/RepresentationMaps/remap_plugin_query/archive/refs/heads/main.zip remap_map_handlerhttps://github.com/RepresentationMaps/remap_map_handler RepresentationMaps Organizationhttps://github.com/RepresentationMaps Package Docshttps://github.com/RepresentationMaps/remap_plugin_query#readme

Deployment Notes

Install ROS 2 Humble, OpenVDB, Conda, and the additional dependencies listed in the deployment README.
Mirror the `ros2_ws` source tree onto the Linux filesystem before building because direct DrvFS builds under WSL were reported to hang.
Build the public packages together with the local `remap_runtime` replacement runtime and source the generated workspace before calling the services.
Call `/kb/query`, `/kb/revise`, `/remap/query`, or `/remap/remove_query` to drive the verified public deployment.

Relative Path Example

# Relative-path local entry for the reMap deployment
source /opt/ros/humble/setup.bash
source ~/anaconda3/etc/profile.d/conda.sh
conda activate vdb_env
source /home/lyd/remap_linux_build/ros2_ws/install/setup.bash

ros2 service call /remap/query remap_msgs/srv/Query "{
  patterns: ['tiago_pro isIn ?room'],
  vars: [],
  models: [],
  dynamic: false,
  duration: {sec: 0, nanosec: 0},
  frequency: {sec: 1, nanosec: 0},
  publish_tf: true,
  id: 'presence_query'
}"

Expected Result Shape

{
  "tool": "reMap",
  "status": "ok",
  "trajectory": [
    {
      "label": "Queryable semantic mapping",
      "score": 0.87,
      "output": "JSON query results, result topics, TF frames, semantic map updates"
    }
  ],
  "timing": {
    "runtime": "Interactive ROS service calls are shown in the deployment notes, but no source-reported latency number is given.",
    "device": "documented in source benchmark when available"
  },
  "artifacts": {
    "visualization": "tools/reMap/runs/visualization.png",
    "raw_predictions": "tools/reMap/runs/predictions.json"
  }
}

Paper figure

Academic Info

Paper identity and contribution summary.

TitlereMap: Spatially-Grounded and Queryable Semantics for Interactive Robots

AuthorsAdd authors

VenueLNCS / ERL@HRI 2025

ContributionConnects spatially grounded semantic maps with symbolic querying so interactive robots can recover entity locations and relations through a unified ROS service interface.

Citation

@misc{reMap2025,
  title={reMap: Spatially-Grounded and Queryable Semantics for Interactive Robots},
  author={Author},
  year={2025},
  note={LNCS / ERL@HRI 2025},
  url={https://github.com/RepresentationMaps/remap_plugin_query}
}

Benchmark

Only compact, source-reported numbers are shown here.

Dataset	Metric	Value	Runtime	Source
The bundled deployment README verifies service-level functionality on a demo scene, but it does not provide a source benchmark dataset or paper-reported numeric evaluation table.	Core result	No official numeric benchmark was found in the bundled public reMap materials, so the page leaves this as a deployment-validated tool rather than inventing a score.	Interactive ROS service calls are shown in the deployment notes, but no source-reported latency number is given.	LNCS / ERL@HRI 2025

Artifacts

Public ROS2 package READMEs, build logs, verified service calls, and runtime notes from the deployment README.

Demo Images

Visual references from the original tool. Click any image to inspect the original size.