Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MapForest: A Modular Field Robotics System for Forest Mapping and Invasive Species Localization

Sandeep Zachariah, Francisco Yandun, Sachet Korada, Abhisesh Silwal

Abstract

Monitoring and controlling invasive tree species across large forests, parks, and trail networks is challenging due to limited accessibility, reliance on manual scouting, and degraded under-canopy GNSS. We present MapForest, a modular field robotics system that transforms multi-modal sensor data into GIS-ready invasive-species maps. Our system features: (i) a compact, platform-agnostic sensing payload that can be rapidly mounted on UAV, bicycle, or backpack platforms, and (ii) a software pipeline comprising LiDAR-inertial mapping, image-based invasive-species detection, and georeferenced map generation. To ensure reliable operation in GNSS-intermittent environments, we enhance a LiDAR-inertial mapping backbone with covariance-aware GNSS factors and robust loss kernels. We train an object detector to detect the Tree-of-Heaven (Ailanthus altissima) from onboard RGB imagery and fuse detections with the reconstructed map to produce geospatial outputs suitable for downstream decision making. We collected a dataset spanning six sites across urban environments, parks, trails, and forests to evaluate individual system modules, and report end-to-end results on two sites containing Tree-of-Heaven. The enhanced mapping module achieved a trajectory deviation error of 1.95 m over a 1.2 km forest traversal, and the Tree-of-Heaven detector achieved an F1 score of 0.653. The datasets and associated tooling are released to support reproducible research in forest mapping and invasive-species monitoring.

MapForest: A Modular Field Robotics System for Forest Mapping and Invasive Species Localization

Abstract

Monitoring and controlling invasive tree species across large forests, parks, and trail networks is challenging due to limited accessibility, reliance on manual scouting, and degraded under-canopy GNSS. We present MapForest, a modular field robotics system that transforms multi-modal sensor data into GIS-ready invasive-species maps. Our system features: (i) a compact, platform-agnostic sensing payload that can be rapidly mounted on UAV, bicycle, or backpack platforms, and (ii) a software pipeline comprising LiDAR-inertial mapping, image-based invasive-species detection, and georeferenced map generation. To ensure reliable operation in GNSS-intermittent environments, we enhance a LiDAR-inertial mapping backbone with covariance-aware GNSS factors and robust loss kernels. We train an object detector to detect the Tree-of-Heaven (Ailanthus altissima) from onboard RGB imagery and fuse detections with the reconstructed map to produce geospatial outputs suitable for downstream decision making. We collected a dataset spanning six sites across urban environments, parks, trails, and forests to evaluate individual system modules, and report end-to-end results on two sites containing Tree-of-Heaven. The enhanced mapping module achieved a trajectory deviation error of 1.95 m over a 1.2 km forest traversal, and the Tree-of-Heaven detector achieved an F1 score of 0.653. The datasets and associated tooling are released to support reproducible research in forest mapping and invasive-species monitoring.
Paper Structure (22 sections, 6 equations, 9 figures, 6 tables)

This paper contains 22 sections, 6 equations, 9 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. System Overview
  4. Hardware Setup
  5. Mapping
  6. Invasive Species Detection
  7. Geospatial Grounding
  8. Aerial-Terrestrial Map Alignment
  9. Likelihood-Field Representation
  10. Aerial likelihood field
  11. Terrestrial likelihood field
  12. Alignment via Normalized Mutual Information
  13. Multi-start Optimization
  14. Experiments
  15. Testing Sites
  16. ...and 7 more sections

Figures (9)

  • Figure 1: System overview. Multi-modal sensing and logging feed a GLIM-based koide2024glim LiDAR-inertial mapping backbone and a YOLOv8 detector. Detections are fused with the estimated trajectory to produce georeferenced map layers (e.g., GeoTIFF/KML). Optional modules include GNSS priors, and aerial-terrestrial map alignment.
  • Figure 2: Sensor payload deployed across multiple carriers, demonstrating platform-agnostic operation.
  • Figure 3: Likelihood fields used for aerial–terrestrial alignment. Top row: likelihood fields for (a) aerial, (b) terrestrial, and (c) aligned results. Bottom row: the corresponding point-cloud maps for each case.
  • Figure 4: Estimated vs. ground-truth DBH for 11 Flagstaff trees (FSCT on reconstructed map vs. tape-measured).
  • Figure 5: Reconstructed maps on the Flagstaff site for two GLIM variants.
  • ...and 4 more figures