Jh

Results 8 issues of Jh

## Question ### What's your question? I am implementing the UAV obstacle avoidance mission and want to use the distance sensor to get the distance between the UAV and the...

question
sensors

## Bug report - AirSim Version/#commit:1.2 - UE/Unity version:4.27 - autopilot version: - OS Version:Win10 ### What's the issue you encountered? I am using deep reinforcement learning to train multiple...

When I install the MPE environment, I will report an error when I use the `bin/interactive.py --scenario simple.py` command: ![image](https://user-images.githubusercontent.com/28137201/223907016-ee23a4da-0099-4e92-9daa-78637f8aafa7.png) May I ask why this happened?

我在使用深度强化学习训练多无人机避障时,将 ClockSpeed 设置为 5 来加快训练。当我完成训练后,如果我仍在 ClockSpeed 设置为 5 的环境下进行测试,无人机可以成功避碰。 但是当我将 ClockSpeed 设置为 1 进行测试时,无人机就会发生碰撞。我想请问一下这是为什么啊?难道ClockSpeed 设置会影响无人机本身的动力学吗?为什么在测试时也必须要设置跟训练时一样的ClockSpeed 值才能成功复现训练结果啊?如果是这样的话,那把策略迁移到实际环境中时不会出问题吗?毕竟真实环境下,应该相当于ClockSpeed=1的情况吧?希望大佬帮忙解答一下,非常感谢!

我想请问下,您在训练时,是否使用了Domain randomization的方法,来使得训练获得的策略具有更好的泛化性呢?比如每回合训练开始时,UAV随机初始化在不同的位置?

Hello, I noticed that there is only an executable file named "TrainEnv.exe" in the compressed package of TrainEnv. I would like to ask, can the environment be edited by myself?...

I used pybullet to create a custom environment class named MultiTrackAviary, and I want to initialize this class, as follows: env = MultiTrackAviary() env_evaluate = MultiTrackAviary() However, the following error...

Hello@JacopoPan ,I have two questions for you about the camera: 1.If I want to achieve obstacle avoidance with a drone, if I only have a forward-looking camera, does that mean...

question