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 17:33] sungbean |
Member:sungbeanJo_paper [2021/04/21 22:08] (current) sungbean |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | Behavior cloning [32, 38, 35, 25] is a form of supervised | + | get_config_param active timestamp_mode |
- | learning that can learn sensorimotor policies from off-line | + | TIME_FROM_INTERNAL_OSC |
- | collected data. The only requirements are pairs of input | + | get_config_param active multipurpose_io_mode |
- | sensory observations associated with expert actions. We use | + | OUTPUT_OFF |
- | an expanded formulation for self-driving cars called Conditional | + | get_config_param active sync_pulse_in_polarity |
- | Imitation Learning, CIL [12]. It uses a high-level navigational | + | ACTIVE_LOW |
- | command c that disambiguates imitation around | + | get_config_param active nmea_in_polarity |
- | multiple types of intersections. Given an expert policy | + | ACTIVE_HIGH |
- | π(x) with access to the environment state x, we can execute | + | get_config_param active nmea_baud_rate |
- | this policy to produce a dataset, D = {hoi, ci, aii}N | + | BAUD_9600 |
- | i=1, | + | |
- | where oi are sensor data observations, ci are high-level | + | |
- | commands (e.g., take the next right, left, or stay in lane) | + | |
- | 9330 | + | |
- | and ai = π(xi) are the resulting vehicle actions (low-level | + | |
- | controls). Observations oi = {i, vm} contain a single image | + | |
- | i and the ego car speed vm [12] added for the system to | + | |
- | properly react to dynamic objects on the road. Without the | + | |
- | speed context, the model cannot learn if and when it should | + | |
- | accelerate or brake to reach a desired speed or stop. | + | |
- | We want to learn a policy π parametrized by to produce | + | |
- | similar actions to π based only on observations o and highlevel | + | |
- | commands c. The best parameters are obtained by | + | |
- | minimizing an imitation cost ℓ: | + |