Theory behind Robotics
The following pages will provide an overview of the following important topics of robotics: For more details be sure to check out the Self Driving cars with Duckietown edX MOOC. Also don't forget to read through the resources listed on the main page of this documentation and consult your robotics engineering text books of choice.
-
Modeling and Control
- Introduction to control systems
- Representations and models
- PID control
-
Robot Vision
- Introduction to projective geometry
- Camera modeling and calibration
- Image processing
-
Object Detection
- Convolutional neural networks
- One and two stage object detection
-
State Estimation and Localization
- Bayes filtering framework
- Parameterized methods (Kalman filter)
- Sampling-based methods (Particle and histogram filter)
- Motion models (velocity and odometry)
-
Planning I
- Planning formalization
- Graphs
-
Planning II
- Probabilistic roadmaps
- Sampling-based planning
-
Learning by Reinforcement
- Markov decision processes
- Value functions
- Policy gradients
- Domain randomization
-
Learning by Imitation
- Behaviour cloning
- Online imitation learning
- Safety and uncertainty
Resources
- Books:
- Probabilistic Robotics by Sebastian Thrun, Wolfram Burgard and Dieter Fox, MIT Press 2005 (Amazon.com, Amazon.de, affiliate links): the standard book on state estimation, localization and SLAM for mobile robots. Probability, Recursive State Estimation (chapter 2), Nonparametric Filters (chapter 4), Robot Motion (chapter 5), Markov and Gaussian Localization (chapter 7) and SLAM Overview cite it. Robot Motion shows where DiffBot's ROS packages use its two motion models: diff_drive_controller's odometry follows the velocity motion model, and amcl moves its particles with the odometry motion model.
- Feedback Systems: An Introduction for Scientists and Engineers by Karl Johan Åström and Richard M. Murray, 2nd edition, Princeton University Press 2021 (free online at fbsbook.org; Amazon.com, Amazon.de, affiliate links): feedback, stability and PID control. Wheel Dynamics in Simulation cites chapter 11 for the PID and integral windup.
- Modern Robotics: Mechanics, Planning, and Control by Kevin M. Lynch and Frank C. Park, Cambridge University Press 2017 (free preprint and videos at modernrobotics.org; Amazon.com, Amazon.de, affiliate links): rigid-body motion and dynamics, and wheeled mobile robots in chapter 13. Wheel Dynamics in Simulation cites section 8.2 for a wheel's inertia.
- Courses:
Comments
Comments are GitHub Discussions, shown with giscus. Loading them connects to giscus.app (hosted by Vercel, USA) and GitHub (USA); you need a GitHub account to comment.