markfzp / navigation-locomotion Goto Github PK

Dear author, I have two questions for you.
First, I would like to ask what computing platform is used in this project. Can you tell me in detail? Is it Jetson Xavier NX?
Second, I want to ask whether there is no reinforcement learning code in this project. For example, the obstacle_detector.py and terrain_detector.py in the plan_cts_pid file only have interfaces to receive whether obstacles are encountered or whether speed should be limited. But there is no code in the plan_cts_pid file to judge the motion state of the robot in the previous step.

Hi, I got an error when running main.py:
`-----sleep for 2s, building up perception buffer-----

Traceback (most recent call last):
File "main.py", line 232, in
main()
File "main.py", line 193, in main
mmap, pos_mm, yaw, target_pos_mm = slam.get_global_map(target_pos)
File "main.py", line 120, in get_global_map
map, _ = self.get_map()
File "main.py", line 44, in get_map
data = self.map_buffer[-1]
IndexError: deque index out of range`
What's the reason?How can I modify it?

Hello author, I did not find any code for reinforcement learning training in the project. May I ask if this part of the code is included in the project. Additionally, I would like to know how this project can be deployed on unitree A1.
Looking forward to your reply.