# Copyright (c) 2022-2026, The Isaac Lab Project Developers (https://github.com/isaac-sim/IsaacLab/blob/main/CONTRIBUTORS.md). # All rights reserved. # # SPDX-License-Identifier: BSD-3-Clause """Script to run an environment with zero action agent.""" """Launch Isaac Sim Simulator first.""" import argparse from isaaclab.app import AppLauncher # add argparse arguments parser = argparse.ArgumentParser(description="Zero agent for Isaac Lab environments.") parser.add_argument( "--disable_fabric", action="store_true", default=False, help="Disable fabric and use USD I/O operations." ) parser.add_argument("--num_envs", type=int, default=None, help="Number of environments to simulate.") parser.add_argument("--task", type=str, default=None, help="Name of the task.") # append AppLauncher cli args AppLauncher.add_app_launcher_args(parser) # parse the arguments args_cli = parser.parse_args() # launch omniverse app app_launcher = AppLauncher(args_cli) simulation_app = app_launcher.app """Rest everything follows.""" import gymnasium as gym import torch import isaaclab_tasks # noqa: F401 from isaaclab_tasks.utils import parse_env_cfg import mindbot.tasks # noqa: F401 def main(): """Zero actions agent with Isaac Lab environment.""" # parse configuration env_cfg = parse_env_cfg( args_cli.task, device=args_cli.device, num_envs=args_cli.num_envs, use_fabric=not args_cli.disable_fabric ) # create environment env = gym.make(args_cli.task, cfg=env_cfg) # print info (this is vectorized environment) print(f"[INFO]: Gym observation space: {env.observation_space}") print(f"[INFO]: Gym action space: {env.action_space}") # reset environment env.reset() # 计数器：每 120 步打印一次 step_count = 0 print_interval = 120 # simulate environment while simulation_app.is_running(): # run everything in inference mode with torch.inference_mode(): # compute zero actions actions = torch.zeros(env.action_space.shape, device=env.unwrapped.device) # apply actions env.step(actions) # ... (前面的代码保持不变) # 每 120 步打印一次坐标 step_count += 1 if step_count % print_interval == 0: scene = env.unwrapped.scene # 1. 获取 centrifuge 的世界坐标 try: centrifuge = scene["centrifuge"] centrifuge_pos = centrifuge.data.root_pos_w[0].cpu().numpy() centrifuge_quat = centrifuge.data.root_quat_w[0].cpu().numpy() print(f"[Step {step_count}] CENTRIFUGE - Pos: {centrifuge_pos}, Quat: {centrifuge_quat}") except KeyError: print(f"[Step {step_count}] CENTRIFUGE - Not found") # 2. 获取 Reservoir_A 的世界坐标 # 注意：这里的 key ("reservoir_a") 必须与你在 SceneCfg 中定义的名称一致 try: # 如果你在配置里命名为 "reservoir_a" reservoir = scene["reservoir_a"] res_pos = reservoir.data.root_pos_w[0].cpu().numpy() res_quat = reservoir.data.root_quat_w[0].cpu().numpy() print(f"[Step {step_count}] RESERVOIR_A - Pos: {res_pos}, Quat: {res_quat}") except KeyError: # 如果 Reservoir_A 是 centrifuge 机器人(Articulation)的一个 Link（身体部件） # 我们可以从 centrifuge 的 body 数据中获取 try: centrifuge = scene["centrifuge"] # 找到名为 'Reservoir_A' 的 link 索引 body_names = centrifuge.body_names if "Reservoir_A" in body_names: idx = body_names.index("Reservoir_A") res_pos = centrifuge.data.body_pos_w[0, idx].cpu().numpy() res_quat = centrifuge.data.body_quat_w[0, idx].cpu().numpy() print(f"[Step {step_count}] RESERVOIR_A (Link) - Pos: {res_pos}, Quat: {res_quat}") else: print(f"[Step {step_count}] RESERVOIR_A - Not found in scene keys or links") except Exception: print(f"[Step {step_count}] RESERVOIR_A - Not found") # 3. 获取 lid 的世界坐标 try: lid = scene["lid"] lid_pos = lid.data.root_pos_w[0].cpu().numpy() lid_quat = lid.data.root_quat_w[0].cpu().numpy() print(f"[Step {step_count}] LID - Pos: {lid_pos}, Quat: {lid_quat}") except KeyError: print(f"[Step {step_count}] LID - Not found") print("-" * 80) # ... (后面的代码保持不变) # 每 120 步打印一次坐标 # step_count += 1 # if step_count % print_interval == 0: # scene = env.unwrapped.scene # # 获取 centrifuge 的世界坐标（root position） # try: # centrifuge = scene["centrifuge"] # centrifuge_pos = centrifuge.data.root_pos_w[0].cpu().numpy() # 取第一个环境 # centrifuge_quat = centrifuge.data.root_quat_w[0].cpu().numpy() # print(f"[Step {step_count}] CENTRIFUGE_CFG - World Position: {centrifuge_pos}, Quaternion: {centrifuge_quat}") # except KeyError: # print(f"[Step {step_count}] CENTRIFUGE_CFG - Not found in scene") # # 获取 lid 的世界坐标 # try: # lid = scene["lid"] # lid_pos = lid.data.root_pos_w[0].cpu().numpy() # 取第一个环境 # lid_quat = lid.data.root_quat_w[0].cpu().numpy() # print(f"[Step {step_count}] LID_CFG - World Position: {lid_pos}, Quaternion: {lid_quat}") # except KeyError: # print(f"[Step {step_count}] LID_CFG - Not found in scene") # print("-" * 80) # close the simulator env.close() if __name__ == "__main__": # run the main function main() # close sim app simulation_app.close() # # Copyright (c) 2022-2026, The Isaac Lab Project Developers (https://github.com/isaac-sim/IsaacLab/blob/main/CONTRIBUTORS.md). # # All rights reserved. # # # # SPDX-License-Identifier: BSD-3-Clause # """Script to run an environment with zero action agent.""" # """Launch Isaac Sim Simulator first.""" # import argparse # from isaaclab.app import AppLauncher # # add argparse arguments # parser = argparse.ArgumentParser(description="Zero agent for Isaac Lab environments.") # parser.add_argument( # "--disable_fabric", action="store_true", default=False, help="Disable fabric and use USD I/O operations." # ) # parser.add_argument("--num_envs", type=int, default=None, help="Number of environments to simulate.") # parser.add_argument("--task", type=str, default=None, help="Name of the task.") # # append AppLauncher cli args # AppLauncher.add_app_launcher_args(parser) # # parse the arguments # args_cli = parser.parse_args() # # launch omniverse app # app_launcher = AppLauncher(args_cli) # simulation_app = app_launcher.app # """Rest everything follows.""" # import gymnasium as gym # import torch # import isaaclab_tasks # noqa: F401 # from isaaclab_tasks.utils import parse_env_cfg # import mindbot.tasks # noqa: F401 # def main(): # """Zero actions agent with Isaac Lab environment.""" # # parse configuration # env_cfg = parse_env_cfg( # args_cli.task, device=args_cli.device, num_envs=args_cli.num_envs, use_fabric=not args_cli.disable_fabric # ) # # create environment # env = gym.make(args_cli.task, cfg=env_cfg) # # print info (this is vectorized environment) # print(f"[INFO]: Gym observation space: {env.observation_space}") # print(f"[INFO]: Gym action space: {env.action_space}") # # reset environment # env.reset() # # simulate environment # step_count = 0 # print_interval = 120 # while simulation_app.is_running(): # # run everything in inference mode # with torch.inference_mode(): # # compute zero actions # actions = torch.zeros(env.action_space.shape, device=env.unwrapped.device) # # apply actions # env.step(actions) # # close the simulator # env.close() # if __name__ == "__main__": # # run the main function # main() # # close sim app # simulation_app.close()