SLAM Benchmark

---

EVO

evo: Python package for the evaluation of odometry and SLAM

1. get the ground truth file, e.g. EuRoC data.csv
2. convert it to TUM format data.tum: evo_traj euroc data.csv --save_as_tum
3. evaluate evo_ape tum data.tum pose_out.tum --align --plot
4. or directly evo_ape euroc data.csv pose_out.tum --align --plot

rgbd-dataset tools

Useful tools for the RGB-D benchmark (TUM)

1. get the ground truth file, e.g. EuRoC data.csv
2. convert it to TUM format data.tum, we can use evo
3. evaluate: ./evaluate_ate.py data.tum pose_out.tum --plot result --verbose

rpg_trajectory_evaluation

• https://github.com/uzh-rpg/rpg_trajectory_evaluation

• https://github.com/rpng/open_vins/tree/master/ov_eval