Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
Member:sungbeanJo_paper [2021/03/04 23:09] sungbean |
Member:sungbeanJo_paper [2021/04/21 22:08] (current) sungbean |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | For all controllers, the observation o is the currently | + | get_config_param active timestamp_mode |
- | observed image at 20088 pixel resolution. For the measurement | + | TIME_FROM_INTERNAL_OSC |
- | m, we used the current speed of the car, if available (in | + | get_config_param active multipurpose_io_mode |
- | the physical system the speed estimates were very noisy and | + | OUTPUT_OFF |
- | we refrained from using them). All networks are composed | + | get_config_param active sync_pulse_in_polarity |
- | of modules with identical architectures (e.g., the ConvNet | + | ACTIVE_LOW |
- | architecture is the same in all conditions). The differences are | + | get_config_param active nmea_in_polarity |
- | in the configuration of modules and branches as can be seen | + | ACTIVE_HIGH |
- | in Figure 3. The image module consists of 8 convolutional | + | get_config_param active nmea_baud_rate |
- | and 2 fully connected layers. The convolution kernel size is 5 | + | BAUD_9600 |
- | in the first layer and 3 in the following layers. The first, third, | + | |
- | and fifth convolutional layers have a stride of 2. The number | + | |
- | of channels increases from 32 in the first convolutional layer | + | |
- | to 256 in the last. Fully-connected layers contain 512 units | + | |
- | each. All modules with the exception of the image module | + | |
- | are implemented as standard multilayer perceptrons. We | + | |
- | used ReLU nonlinearities after all hidden layers, performed | + | |
- | batch normalization after convolutional layers, applied 50% | + | |
- | dropout after fully-connected hidden layers, and used 20% | + | |
- | dropout after convolutional layers. | + | |
- | Actions are two-dimensional vectors that collate steering | + | |
- | angle and acceleration: a = hs; ai. Given a predicted action | + | |
- | a and a ground truth action agt, the per-sample loss function | + | |
- | is defined as | + | |
- | All models were trained using the Adam solver [16] with | + | |
- | minibatches of 120 samples and an initial learning rate of | + | |
- | 0:0002. For the command-conditional models, minibatches | + | |
- | were constructed to contain an equal number of samples with | + | |
- | each command. | + |