Mobile Robot Reality Capture Trajectories
Full mobile robot trajectory logs with synchronized wheel odometry, 6-axis IMU telemetry, and ground-truth poses from RTK-GPS / Leica Total Stations.
Quality & Precision Benchmarks
TELEMETRY RATE
1kHz IMU / 100Hz Odometry
POSE GROUND TRUTH
Sub-Centimeter RTK / Leica
SLA TURNAROUND
< 24 Hours Express
VALIDATION PASS
100% Passed Audits
Dataset Taxonomy & Output Structure
wheel_odometry_encoder (Left/Right Encoder Counts)
imu_accel_gyro_raw (1kHz 6-Axis IMU Sensor Stream)
rtk_gps_ground_truth (Sub-Centimeter RTK Coordinates)
robot_base_frame (URDF Footprint Link)
telemetry_hz (100Hz Wheel / 1kHz IMU Stream)
Specific Type Tasks & Applications
- • AMR Odometry & SLAM Benchmark Evaluation
- • Quadruped Robot Rough-Terrain Trajectory Learning
- • Multi-Robot Fleet Map Merging
What Is Right vs What Is Wrong
| COMMON COMPETITOR ERRORS (WRONG) | BLUE PROJECTS GROUND TRUTH (RIGHT) |
|---|---|
| FAIL: Unsynchronized camera and odometry timestamps creating temporal lag in VIO algorithms | PASS: Hardware-triggered microsecond synchronization across cameras, LiDAR, and IMU odometry |
| FAIL: Missing ground-truth pose verification making it impossible to evaluate SLAM drift errors | PASS: Ground-truth millimeter poses benchmarked using optical Leica Total Stations and RTK-GPS |
Files & SLAM Data Example (Python)
import open3d as o3d
# Load Blue Projects SLAM Dataset Type: Mobile Robot Reality Capture Trajectories
pcd = o3d.io.read_point_cloud("mobile-robot-reality-capture-trajectories_scan.pcd")
print("Point Cloud Count:", len(pcd.points))
Why Blue Projects for Mobile Robot Reality Capture Trajectories?
Request a free matched 10,000 sq ft 360 SLAM point cloud mesh and 8K equirectangular video sample batch.
Request Free Sample Batch →