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 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. | + |