Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Member:sungbeanJo_paper [2021/03/04 18:00]
sungbean
Member:sungbeanJo_paper [2021/04/21 22:08] (current)
sungbean
Line 1: Line 1:
-To cope with the +get_config_param active timestamp_mode  
-inertia problem without an explicit mapping of potential + TIME_FROM_INTERNAL_OSC 
-causes or on-policy interventions,​ we jointly train a sensorimotor +get_config_param active multipurpose_io_mode 
-controller with a network that predicts the ego vehicle’s + OUTPUT_OFF ​ 
-speed. Both neural networks share the same representation +get_config_param active sync_pulse_in_polarity 
-via our ResNet perception backbone. Intuitively,​ + ACTIVE_LOW 
-what happens is that this joint optimization enforces the +get_config_param active nmea_in_polarity 
-perception module to have speed related features into the + ACTIVE_HIGH 
-learned representation. This reduces the dependency on input +get_config_param active nmea_baud_rate 
-speed as the only way to get dynamics of the scene, + BAUD_9600 
-leveraging instead visual cues that are predictive of the car’s +
-velocity (e.g., free space, curves, traffic light states, etc).+
Navigation