Difference between revisions of "Curriculum"
Jump to navigation
Jump to search
| Line 43: | Line 43: | ||
* [http://karpathy.github.io/2015/05/21/rnn-effectiveness/ The Unreasonable Effectiveness of Recurrent Neural Networks] | * [http://karpathy.github.io/2015/05/21/rnn-effectiveness/ The Unreasonable Effectiveness of Recurrent Neural Networks] | ||
* [http://colah.github.io/posts/2015-08-Understanding-LSTMs/ Understanding LSTM Networks] | * [http://colah.github.io/posts/2015-08-Understanding-LSTMs/ Understanding LSTM Networks] | ||
== Sensors == | == Sensors == | ||
Revision as of 15:52, 23 October 2017
The following topics will be covered in this class:
Vehicle Components
- Basher SaberTooth 1/8 Scale Truggy
- 1845KV Brushless Inrunner Motor (Waterproof)
- 100A Brushless ESC w/ Reverse (waterproof)
- 18Kg Heavy Duty Steering Servo (waterproof)
- Full time 4WD (video on differential gear)
- Alloy oil filled big bore adjustable screw shock absorbers
- Adjustable camber, caster, toe-in and toe-out
- Independent wishbone suspension
- Electronics
- Batteries
- Servo controller
- Raspberry PI
- Camera
- Emergency switch
Robot Motion
- Differential drive
- Ackermann steering
- Basic path planning
Neural Networks
Some links for interesting tutorial style reading on CNN:
- Machine Learning is Fun. Check out specially Part 3!
- Tensorflow Tutorial on Image recognition
Some links of RNN:
Sensors
- Encoders
- IMU
- Camera
Feedback control
- Why feedback?
- PID control
Odometry
- Encoders
- IMU
- Visual
Vision
- Open CV
- Obstacle avoidance
- Performance considerations
Embedded Systems
- Introduction to robotics
- Centralized vs. distributed control
- Closed loop vs. open loop control in mobile robots
- On-board, off-board computing vs. on-line-computing and hybrid mode
- Real-time systems vs. non-deterministic embedded systems
- Robotics telemetry - low range high throughput, long range low throughput
Autonomous Vehicle
- State-of-the-art