← All CRE Flashcard Decks

CRE Sensors, Vision & Perception Flashcards

6 cards from real CRE practice questions. Tap to flip, then mark Knew It or Still Learning — missed cards come back until you master them.

Read the first 6 CRE Sensors, Vision & Perception flashcards as text
  1. SLAM stands for:

    Answer: Simultaneous Localization and Mapping

    SLAM enables a robot to incrementally build a map of an unknown environment while concurrently estimating its own pose within that map.

  2. A Kalman filter is used in sensor fusion to:

    Answer: Optimally combine noisy measurements to estimate system state with minimum variance

    The Kalman filter recursively fuses motion model predictions with sensor measurements, weighting each by their respective uncertainties for an optimal state estimate.

  3. Fiducial markers such as ArUco tags are used in robot perception to:

    Answer: Provide known visual reference points for accurate pose estimation

    Fiducial markers are uniquely identifiable patterns that robots detect and measure to precisely compute camera or robot pose relative to the known marker geometry.

  4. The primary advantage of a time-of-flight (ToF) depth camera over a stereo camera is:

    Answer: Active depth measurement that functions in textureless low-feature environments

    ToF cameras actively emit and detect light pulses, providing reliable depth data even in uniform, featureless scenes where passive stereo matching fails.

  5. Occupancy grid maps represent a robot's environment as:

    Answer: A grid where each cell stores the probability of being occupied by an obstacle

    Occupancy grids discretize space into uniform cells, each maintaining a probability estimate updated by sensor measurements indicating free or occupied status.

  6. Extrinsic camera calibration in a robot system determines:

    Answer: The rigid-body spatial transform between the camera frame and the robot base frame

    Extrinsic calibration establishes the rotation and translation relating the camera coordinate frame to the robot's reference frame, enabling accurate 3D scene interpretation.