Technical interview guide

Perception & SLAM

How a robot builds a map of an unknown environment while simultaneously figuring out its own location within it.

Read: 45 min
Practice MCQs: 25
Interview QA: 25
Edition: v4
Editorial status: Reviewed
Relevant for: Robotics Engineer

Scope: ORB-SLAM3, Cartographer, GTSAM, Ceres, OpenCV 4.x, ROS 2 Rolling, Kalibr, PCL, Nav2, TUM RGB-D, KITTI, and evo references reviewed 2026-09-04.

Interview QA

Treat each question like a live interview question: answer out loud first (structure, assumptions, tradeoffs), then open the model answer to spot gaps and rehearse a tighter follow-up.

Curated: 2026-10-05 · Written: 2026-09-09 · Reviewed: 2026-10-03

QA-1

Choose mapping, localization, odometry, or SLAM for a robot product.

QA-2

Design timestamp handling for a camera-IMU-LiDAR stack.

QA-3

Manage spatial calibration for a multi-sensor robot.

QA-4

Design robust landmark or scan data association.

QA-5

Recover and validate scale in a monocular system.

QA-6

Design visual tracking quality and degradation handling.

QA-7

Build a robust LiDAR scan-registration stage.

QA-8

Detect and handle geometric degeneracy in LiDAR odometry.

QA-9

Integrate IMU measurements into a SLAM estimator.

QA-10

Validate uncertainty reported by a localization system.

QA-11

Design a factor-graph SLAM back end.

QA-12

Diagnose rank deficiency caused by gauge freedom.

QA-13

Use robust estimation without hiding bad measurements.

QA-14

Design a safe loop-closure pipeline.

QA-15

Implement REP-105 frame semantics for navigation.

QA-16

Design lost-tracking and relocalization state transitions.

QA-17

Create a map lifecycle and compatibility contract.

QA-18

Define a fair SLAM evaluation protocol.

QA-19

Gate a new sensor into a production estimator.

QA-20

Deskew a LiDAR scan safely.

QA-21

Design scheduling and overload behavior for SLAM.

QA-22

Review a false-loop incident and prevent recurrence.

QA-23

Validate relocalization after the kidnapped-robot condition.

QA-24

Design observability for perception and SLAM.

QA-25