What problem does it solve? SLAM maps of closed loops often show gaps, overlaps, or warped geometry because accumulated odometry drift is never corrected, or because false loop closures tear the map apart. This Skill explains how loop closure works and how to tune its parameters to produce consistent, distortion-free maps. ## Core Features & Use Cases - Parameter Tuning Guidance: Concrete thresholds and ranges for Cartographer (min_score, sampling_ratio, max_constraint_distance, huber_scale) and SLAM Toolbox (loop_match_minimum_response, chain size, search space) with recommended starting values. - False Positive Diagnosis: Symptom identification (map tearing, bending walls) and a mitigation strategy table mapping each fix to the correct parameter in both SLAM frameworks. - Visual Verification Workflow: How to read /constraint_list markers in RViz (green vs blue constraints) to confirm closures connect genuinely revisited areas. - Use Case: Your robot maps a building corridor loop but the map shows a gap where the path should close. Use this Skill to lower min_score, verify blue constraints appear in RViz, and re-map until 3 laps produce identical maps. ## Quick Start Ask the AI to explain why my SLAM map distorts after the robot revisits an area and which loop closure parameters to adjust.
