LAV
LAV copied to clipboard
dotchen
(CVPR 2022) A minimalist, mapless, end-to-end self-driving stack for joint perception, prediction, planning and control.
Hello @dotchen , impressive work! I have ran your latest LAV agent with CARLA Leaderboard. I try to understand the detailed implementation and have run across a couple of questions...
I found that in the previous V1 agent, the threshold for brake prediction is 0.3 in `lav_agent.py` ``` if float(pred_bra) > 0.3: throt, brake = 0, 1 ``` However, the...
thanks to you great work! I didn't find the part about speed embedding in the paper
Hi @dotchen I followed what said in the repo but still don't know what should I do with "wights" folder!? I run the project and it' output is like this:...
## What could be the issue ? I'm using the default settings ``` ./leaderboard/scripts/run_evaluation.sh /home/user/Desktop/shikharvashistha/lav/leaderboard/leaderboard/leaderboard_evaluator.py:85: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead. if LooseVersion(dist.version) < LooseVersion('0.9.10'): ========= Preparing...
Hi dear @dotchen When I run 'run_evaluation.sh' to evaluate, I face with wandb permission error: ------------------------------------------------------------------------------------------------------------------------- Could not set up the required agent: > It appears that you do not...
Hello, Can any one help with data collection file. When I "data_collect.py --num-runners=8", I get this error:. towns = {i: f'Town{i+1 : 02d}' for i in range(7)} ^ SyntaxError: invalid...
