Case study 2023 Flashcards
(27 cards)
Bundle Adjustment
describes the sum of errors between the measured pixel coordinates and the re-projected pixel coordinates when working in a 3d space. Used to estimate the surroundings.
Computer Vision
Processor techniques to understand visual data.
Dead reckoning data
using the previous data to estimate the next amount of data
Edge computing
Edge computing is a distributed computing paradigm that brings computation and data storage closer to the sources of data. This is expected to improve response times and save bandwidth.
global map optimisation
In essence, it’s the process of improving the accuracy and consistency of a map that a robot has created of its environment.
global positioning system
a network of satellites and receiving devices used to determine the location of something on Earth
gps-degraded environment
refers to any situation or location where the Global Positioning System (GPS) signals are unreliable, weak, or completely unavailable.
gps-denied environment
a location or situation where the Global Positioning System (GPS) signals are not available at all.
Human pose estimation (HPE)
a computer vision task that includes detecting, associating, and tracking semantic key points. Examples of semantic key points are “right shoulders,” “left knees,”.
Inertial measurement unit (IMU)
an electronic device that measures and reports acceleration, orientation, angular rates, and other gravitational forces
Keyframe selection
a term commonly used in the field of computer vision, especially in video processing and robotics.
Key points/pairs
In structure from motion or SLAM (Simultaneous Localisation and Mapping), key point pairs are used to reconstruct 3D structure and camera movement from a series of 2D images.
Light detection and ranging (LIDAR)
The distance is measured by sending a short laser pulse and recording the time lapse between outgoing light pulse and the detection of the reflected (back-scattered) light pulse.
Optimization
the action of making the best or most effective use of a situation or resource.
Object occlusion
Occurs when an object hides a part of another object.
Odometry sensor
indicate how far the robot has traveled, based on the amount that the wheels have turned.
Relocalization
a repetitive process in which the localized Information is re-scaled and re-adjusted for backtracking purposes.
Simultaneous localization and mapping (SLAM)
Using SLAM software, a device can simultaneously localize (locate itself in the map) and map (create a virtual map of the location) using SLAM algorithms.
Rigid pose estimation (RPE)
determine an object’s primary key points and then track these key points as they move across real-world spaces
Robot drift
the accumulated error in a robot’s estimated position and orientation over time.
Sensor fusion model
The fusion of data from different sensor types, such as cameras, LIDAR, ultrasonic sensors, and inertial measurement units (IMUs), allows robots to perceive and interact with their environment more effectively.
Visual simultaneous localization and mapping (vSLAM) modules
The process of calculating the position and orientation of a camera, with respect to its surroundings, while simultaneously mapping the environment.
Initialization in terms of vslam
“Initialization” refers to the process of setting up the initial conditions or starting point for the algorithm.
Local mapping in terms of vslam
The robot builds a smaller, more immediate map of its surroundings,
