0.前置

• 机器人持续学习基准LIBERO系列1——基本介绍与安装测试
• 机器人持续学习基准LIBERO系列2——路径与基准基本信息
• 机器人持续学习基准LIBERO系列3——相机画面可视化及单步移动更新

1.robosuite的相关资料

• 是基于MuJoCo的机器人学习方针环境，提供一套基准环境，MuJoCo官方DeepMind长期支持，是通过模拟环境推进机器人智能倡议项目（ Advancing Robot Intelligence through Simulated Environments (ARISE) Initiative）的一部分。
• 是LIBERO的底层环境
• 基本介绍博文
• 简单运行和搭建简单环境的博文
• 官方网站
• 官方文档

2.robosuite最基本demo

• 创建一个简单的抓取任务环境，并可视化演示随机动作

import numpy as np
import robosuite as suite

# create environment instance
env = suite.make(
    env_name="Lift", # try with other tasks like "Stack" and "Door"
    robots="Panda",  # try with other robots like "Sawyer" and "Jaco"
    has_renderer=True,
    has_offscreen_renderer=False,
    use_camera_obs=False,
)

# reset the environment
env.reset()

action = np.random.randn(env.robots[0].dof) # sample random action
obs, reward, done, info = env.step(action)
for i in obs:
    print(i)

for i in range(1000):
    action = np.random.randn(env.robots[0].dof) # sample random action
    obs, reward, done, info = env.step(action)  # take action in the environment
    env.render()  # render on display
env.close()

• 结果
  

• 如果最后没有用env.close()手动关闭环境的话，程序结束后会报错：

Exception ignored in: <function MjRenderContext.__del__ at 0x7ff064d7fa60>
Traceback (most recent call last):
  File "/home/jiangyvhang/anaconda3/envs/maniskill2/lib/python3.8/site-packages/robosuite/utils/binding_utils.py", line 199, in __del__
  File "/home/jiangyvhang/anaconda3/envs/maniskill2/lib/python3.8/site-packages/robosuite/renderers/context/egl_context.py", line 149, in free
  File "/home/jiangyvhang/anaconda3/envs/maniskill2/lib/python3.8/site-packages/OpenGL/error.py", line 230, in glCheckError
OpenGL.raw.EGL._errors.EGLError: <exception str() failed>
Exception ignored in: <function EGLGLContext.__del__ at 0x7ff064d7f8b0>