Skip to content

Sim benchmark report

  • generated (UTC): 20261103T183034Z
  • git commit: 8a32837
  • trials per world: 2
  • goal order: pickup,dropoff,home
  • wheel_mu: 1.0
  • nav2 params: mote_bringup/config/nav2_params.yaml with FollowPath.use_path_orientations: true (MOTE_NAV2_PARAMS_FILE, variant F of variants.py)
  • ROS_DOMAIN_ID: 28

office_world.sdf

  • map revision: 20260708T000623
  • map: mote_simulation/sim_home/sites/office_world/floors/ground/map/map.yaml
  • successful trials: 0/2
metric mean std min max CV
goal success rate 0.667 0.000 0.667 0.667 0.0%
time-to-goal mean (s) 91.5 7.2 84.4 98.7 7.8%
ATE rmse (m) 0.073 0.005 0.068 0.079 7.0%
ATE max (m) 0.226 0.015 0.211 0.241 6.7%
odom ATE rmse (m) 0.022 0.005 0.016 0.027 24.9%
odom ATE max (m) 0.041 0.007 0.035 0.048 15.8%
min clearance (m) 0.146 0.011 0.135 0.157 7.4%
mean clearance (m) 1.002 0.018 0.984 1.019 1.8%
linear jerk rms 9.53 0.10 9.43 9.63 1.1%
direction reversals 2.0 0.0 2.0 2.0 0.0%
recoveries total 4.0 1.0 3.0 5.0 25.0%
aborts 1.0 0.0 1.0 1.0 0.0%
est path length (m) 30.49 0.13 30.35 30.62 0.4%
per-trial | trial | goals ok | ATE rmse (m) | odom ATE (m) | min clr (m) | recoveries | aborts | | --- | --- | --- | --- | --- | --- | --- | | 0 | 2/3 | 0.079 | 0.027 | 0.157 | 5 | 1 | | 1 | 2/3 | 0.068 | 0.016 | 0.135 | 3 | 1 |

Notes

  • Localization error is ATE (truth vs estimate) after a rigid SE(2) alignment — the SLAM map frame and the Gazebo world frame do not share a fixed transform, so alignment is required before differencing.
  • Ground truth is the robot's true pose bridged from Gazebo's PosePublisher (/model/mote/pose, gz.msgs.Pose → PoseStamped).
  • Recovery counts are distinct goal IDs seen on the behavior-server action status topics (/spin, /backup, /drive_on_heading, /wait) — a best-effort proxy for how often Nav2 recovered.
  • CV = coefficient of variation (std/mean); the run-to-run variance to weigh when comparing two configs.