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 16:30]
sungbean
Member:sungbeanJo_paper [2021/04/21 22:08] (current)
sungbean
Line 1: Line 1:
-In this paper, we propose a new benchmark, called +get_config_param active timestamp_mode  
-NoCrash, and perform a large scale analysis of end-toend + TIME_FROM_INTERNAL_OSC 
-behavioral cloning systems in complex driving conditions +get_config_param active multipurpose_io_mode 
-not studied in this context before. We use a high + OUTPUT_OFF ​ 
-fidelity simulated environment based on the open source +get_config_param active sync_pulse_in_polarity 
-CARLA simulator [14] to enable reproducible large scale + ACTIVE_LOW 
-off-line training and on-line evaluation in over 80 hours +get_config_param active nmea_in_polarity 
-of driving under several different conditions. We describe + ACTIVE_HIGH 
-a strong Conditional Imitation Learning baseline, derived +get_config_param active nmea_baud_rate 
-from [12], that significantly improves upon state-of-theart + BAUD_9600 
-modular [26], affordance based [37], and reinforcement +
-learning [27] approaches, both in terms of generalization +
-performance in training environments and unseen ones.+
Navigation