From 7558467aca3ae70e3b1c59e67326391ff62481d2 Mon Sep 17 00:00:00 2001 From: wty-yy <993660140@qq.com> Date: Tue, 7 Apr 2026 11:06:02 +0800 Subject: [PATCH] Remove useless code --- README.md | 21 +++---- README_zh.md | 22 ++++---- UPDATE.md | 8 +++ legged_gym/envs/base/legged_robot.py | 55 +++++++------------ legged_gym/envs/base/legged_robot_config.py | 2 - legged_gym/envs/go2/go2_config.py | 4 +- .../envs/go2/go2_config_fast_flat_move.py | 4 +- legged_gym/envs/go2/go2_config_vanilla.py | 2 +- .../go2_config_vanilla_with_dynamic_cmd.py | 2 +- rsl_rl/rsl_rl/runners/on_policy_runner.py | 52 ++++++++++++------ rsl_rl/rsl_rl/runners/on_policy_runner_cts.py | 52 ++++++++++++------ setup.py | 2 +- tools/logs_merge.py | 50 +++++++++++++++-- 13 files changed, 170 insertions(+), 106 deletions(-) diff --git a/README.md b/README.md index 1cd423b..6cd51ea 100644 --- a/README.md +++ b/README.md @@ -28,7 +28,7 @@ Follow the step-by-step setup guide in [setup.md](doc/setup_en.md). Run the following command to launch training: ```bash -python legged_gym/scripts/train.py --task=xxx +python legged_gym/scripts/train.py --task=xxx --headless ``` #### ⚙️ Arguments @@ -59,14 +59,15 @@ The trained model above was evaluated using the [RoboGauge](https://github.com/w | Model | Score | Tracking | Safety | Quality | Level | Download | | --- | --- | --- | --- | --- | --- | --- | -| go2_moe_cts | **0.6819** | **0.6714** | **0.7794** | **0.7748** | **7.85** | [ckpt](https://drive.google.com/drive/folders/1aoXUxw-pGK1MbyzQ4IJzlA_tW8zrWP3Y?usp=drive_link) | -| go2_moe_ng_cts | 0.6670 | 0.6552 | 0.7651 | 0.7613 | 7.67 | [ckpt](https://drive.google.com/drive/folders/1Rr89ZS0QJT-o-5LXsNqCWJdLGweqmN4Q?usp=drive_link) | -| go2_ac_moe_cts | 0.6652 | 0.6527 | 0.7615 | 0.7552 | 7.57 | [ckpt](https://drive.google.com/file/d/1CDLsaR4XR3oG09ZHQ5u3lrJLfwyH2jz2/view?usp=drive_link) | -| go2_mcp_cts | 0.6545 | 0.6440 | 0.7531 | 0.7476 | 7.48 | [ckpt](https://drive.google.com/drive/folders/1fd9cDVhV1dY6hcxuSZq2mcvFUp6V5Zfl?usp=drive_link) | -| [HIM](https://github.com/InternRobotics/HIMLoco) | 0.5209 | 0.5200 | 0.6200 | 0.6100 | 5.78 | [ckpt](https://drive.google.com/file/d/1remJbGoTorqnArsz8Z1ewY4TVobss4Fb/view?usp=drive_link) | -| [DreamWaQ](https://arxiv.org/abs/2301.10602) | 0.4832 | 0.4800 | 0.5800 | 0.5700 | 5.26 | [ckpt](https://drive.google.com/file/d/19BEBeiQqjHcPgGrN3AX6D7Yefs_8eswL/view?usp=drive_link) | +| go2_moe_cts (Ours) | **0.6713** | **0.6669** | **0.7857** | **0.7392** | **7.85** | [ckpt](https://drive.google.com/drive/folders/1aoXUxw-pGK1MbyzQ4IJzlA_tW8zrWP3Y?usp=drive_link) | +| go2_ac_moe_cts | 0.6509 | 0.6442 | 0.7644 | 0.7149 | 7.52 | [ckpt](https://drive.google.com/file/d/1CDLsaR4XR3oG09ZHQ5u3lrJLfwyH2jz2/view?usp=drive_link) | +| go2_mcp_cts | 0.6399 | 0.6355 | 0.7542 | 0.7058 | 7.41 | [ckpt](https://drive.google.com/drive/folders/1fd9cDVhV1dY6hcxuSZq2mcvFUp6V5Zfl?usp=drive_link) | +| go2_moe_ng_cts | 0.6519 | 0.6447 | 0.7639 | 0.7186 | 7.56 | [ckpt](https://drive.google.com/drive/folders/1Rr89ZS0QJT-o-5LXsNqCWJdLGweqmN4Q?usp=drive_link) | +| [CTS](https://arxiv.org/pdf/2405.10830) vanilla | 0.5786 | 0.5755 | 0.7066 | 0.6624 | 6.83 | [ckpt]() | +| [HIM](https://github.com/InternRobotics/HIMLoco) | 0.5379 | 0.5453 | 0.6476 | 0.6050 | 6.19 | [ckpt](https://drive.google.com/file/d/1remJbGoTorqnArsz8Z1ewY4TVobss4Fb/view?usp=drive_link) | +| [DreamWaQ](https://arxiv.org/abs/2301.10602) | 0.5054 | 0.5105 | 0.6149 | 0.5730 | 5.74 | [ckpt](https://drive.google.com/file/d/19BEBeiQqjHcPgGrN3AX6D7Yefs_8eswL/view?usp=drive_link) | -> In the downloaded ckpt, *.pt files are used for [Python deployment](#41-python-deployment), and *.onnx files are used for [C++ deployment](#42-c-deployment). +> In the downloaded ckpt files, `*.pt` is used for [Python deployment](#41-python-deployment), and `*.onnx` is used for [C++ deployment](#42-c-deployment). The models above were all trained with self-collision disabled. In later tests, we found that enabling self-collision can also achieve strong results; see [go2_moe_cts_self_0.6669 - ckpt](https://drive.google.com/drive/folders/1znytqHNtDiZM5J4vaBd-EuM81l91D6s5?usp=drive_link). ### 2. Play @@ -80,9 +81,9 @@ python legged_gym/scripts/play.py --task=xxx - Play launches on randomized terrain with difficulty between 7 and 9. - It automatically loads the latest checkpoint inside the experiment folder. -- Override via `experiment_name` and `checkpoint`, for example: +- You can specify another model via `experiment_name`, `load_run`, and `checkpoint`, for example: ```bash - python legged_gym/scripts/play.py --task=go2_cts --num_envs 100 --experiment_name go2_cts_hard_terrain --checkpoint 100000 + python legged_gym/scripts/play.py --task=go2_moe_cts --num_envs 100 --experiment_name go2_cts_hard_terrain --load_run Mar21_22-54-5-46_ --checkpoint 100000 ``` #### 💾 Policy Export diff --git a/README_zh.md b/README_zh.md index 2cda1a0..b9f2664 100644 --- a/README_zh.md +++ b/README_zh.md @@ -28,7 +28,7 @@ 运行以下命令进行训练： ```bash -python legged_gym/scripts/train.py --task=xxx +python legged_gym/scripts/train.py --task=xxx --headless ``` #### ⚙️ 参数说明 @@ -59,14 +59,15 @@ python legged_gym/scripts/train.py --task=xxx | Model | Score | Tracking | Safety | Quality | Level | Download | | --- | --- | --- | --- | --- | --- | --- | -| go2_moe_cts (Ours) | **0.6739** | **0.6647** | **0.7776** | **0.7739** | **7.85** | [ckpt](https://drive.google.com/drive/folders/1aoXUxw-pGK1MbyzQ4IJzlA_tW8zrWP3Y?usp=drive_link) | -| go2_ac_moe_cts | 0.6541 | 0.6425 | 0.7558 | 0.7504 | 7.52 | [ckpt](https://drive.google.com/file/d/1CDLsaR4XR3oG09ZHQ5u3lrJLfwyH2jz2/view?usp=drive_link) | -| go2_moe_ng_cts | 0.6537 | 0.6423 | 0.7554 | 0.7525 | 7.56 | [ckpt](https://drive.google.com/drive/folders/1Rr89ZS0QJT-o-5LXsNqCWJdLGweqmN4Q?usp=drive_link) | -| go2_mcp_cts | 0.6423 | 0.6323 | 0.7464 | 0.7412 | 7.41 | [ckpt](https://drive.google.com/drive/folders/1fd9cDVhV1dY6hcxuSZq2mcvFUp6V5Zfl?usp=drive_link) | -| [HIM](https://github.com/InternRobotics/HIMLoco) | 0.5401 | 0.5389 | 0.6412 | 0.6391 | 6.19 | [ckpt](https://drive.google.com/file/d/1remJbGoTorqnArsz8Z1ewY4TVobss4Fb/view?usp=drive_link) | -| [DreamWaQ](https://arxiv.org/abs/2301.10602) | 0.5032 | 0.5010 | 0.6085 | 0.6032 | 5.74 | [ckpt](https://drive.google.com/file/d/19BEBeiQqjHcPgGrN3AX6D7Yefs_8eswL/view?usp=drive_link) | +| go2_moe_cts (Ours) | **0.6713** | **0.6669** | **0.7857** | **0.7392** | **7.85** | [ckpt](https://drive.google.com/drive/folders/1aoXUxw-pGK1MbyzQ4IJzlA_tW8zrWP3Y?usp=drive_link) | +| go2_ac_moe_cts | 0.6509 | 0.6442 | 0.7644 | 0.7149 | 7.52 | [ckpt](https://drive.google.com/file/d/1CDLsaR4XR3oG09ZHQ5u3lrJLfwyH2jz2/view?usp=drive_link) | +| go2_mcp_cts | 0.6399 | 0.6355 | 0.7542 | 0.7058 | 7.41 | [ckpt](https://drive.google.com/drive/folders/1fd9cDVhV1dY6hcxuSZq2mcvFUp6V5Zfl?usp=drive_link) | +| go2_moe_ng_cts | 0.6519 | 0.6447 | 0.7639 | 0.7186 | 7.56 | [ckpt](https://drive.google.com/drive/folders/1Rr89ZS0QJT-o-5LXsNqCWJdLGweqmN4Q?usp=drive_link) | +| [CTS](https://arxiv.org/pdf/2405.10830) vanilla | 0.5786 | 0.5755 | 0.7066 | 0.6624 | 6.83 | [ckpt]() | +| [HIM](https://github.com/InternRobotics/HIMLoco) | 0.5379 | 0.5453 | 0.6476 | 0.6050 | 6.19 | [ckpt](https://drive.google.com/file/d/1remJbGoTorqnArsz8Z1ewY4TVobss4Fb/view?usp=drive_link) | +| [DreamWaQ](https://arxiv.org/abs/2301.10602) | 0.5054 | 0.5105 | 0.6149 | 0.5730 | 5.74 | [ckpt](https://drive.google.com/file/d/19BEBeiQqjHcPgGrN3AX6D7Yefs_8eswL/view?usp=drive_link) | -> 下载的ckpt中*.pt用于[py部署](#41-python实物部署)，*.onnx用于[cpp部署](#42-c实物部署) +> 下载的 ckpt 中，`*.pt` 用于[Python 实物部署](#41-python实物部署)，`*.onnx` 用于[C++ 实物部署](#42-c实物部署)。上述模型均在关闭自碰撞的设置下训练；后续测试发现，开启自碰撞也能取得不错效果，参考 [go2_moe_cts_self_0.6669 - ckpt](https://drive.google.com/drive/folders/1znytqHNtDiZM5J4vaBd-EuM81l91D6s5?usp=drive_link)。 --- @@ -82,9 +83,9 @@ python legged_gym/scripts/play.py --task=xxx - Play 启动参数为随机地形，难度在7到9之间。 - 默认加载实验文件夹最新训练的一个模型。 -- 可通过 `experiment_name` 和 `checkpoint` 指定其他模型，例如 +- 可通过 `experiment_name`, `load_run` 和 `checkpoint` 指定其他模型，例如 ```bash - python legged_gym/scripts/play.py --task=go2_cts --num_envs 100 --experiment_name go2_cts_hard_terrain --checkpoint 100000 + python legged_gym/scripts/play.py --task=go2_moe_cts --num_envs 100 --experiment_name go2_cts_hard_terrain --load_run Mar21_22-54-5-46_ --checkpoint 100000 ``` #### 💾 导出网络 @@ -196,4 +197,3 @@ python deploy_real_go2.py eth0 新增内容根据 [MIT License](./LICENSE) 授权，原仓库unitree_rl_gym根据 [BSD 3-Clause License](./LICENSE) 授权。 详情请阅读完整 [LICENSE 文件](./LICENSE)。 - diff --git a/UPDATE.md b/UPDATE.md index bc85292..334903a 100644 --- a/UPDATE.md +++ b/UPDATE.md @@ -1,3 +1,11 @@ +# 20260403 +## v1.0.3 +1. 修复last_last_action重置问题，修复resample_command在计算奖励前的问题 +2. 将所有配置中加入自碰撞 +# 20260325 +## v1.0.2-rc2 +1. 修复robogauge评估中返回None导致的训练中断问题 +2. 将自碰撞打开，真机表现更好 # 20260126 ## v1.0.2-rc1 1. 修改高速移动的训练文件到最终版，删除配置中无用注释 diff --git a/legged_gym/envs/base/legged_robot.py b/legged_gym/envs/base/legged_robot.py index 5ffed46..1e221bd 100644 --- a/legged_gym/envs/base/legged_robot.py +++ b/legged_gym/envs/base/legged_robot.py @@ -129,6 +129,9 @@ class LeggedRobot(BaseTask): # compute observations, rewards, resets, ... self.check_termination() self.compute_reward() + # resample commands must after reward computing + resampling_env_ids = ((self.commands_resampling_step <= 0.0) * (self.episode_length_buf < self.max_episode_length - 1)).nonzero(as_tuple=False).flatten() + self._resample_commands(resampling_env_ids) env_ids = self.reset_buf.nonzero(as_tuple=False).flatten() self.reset_idx(env_ids) @@ -137,6 +140,7 @@ class LeggedRobot(BaseTask): self.compute_observations() # in some cases a simulation step might be required to refresh some obs (for example body positions) + self.last_last_actions[:] = self.last_actions[:] self.last_actions[:] = self.actions[:] self.last_dof_vel[:] = self.dof_vel[:] self.last_root_vel[:] = self.root_states[:, 7:13] @@ -180,7 +184,7 @@ class LeggedRobot(BaseTask): def reset_idx(self, env_ids): """ Reset some environments. Calls self._reset_dofs(env_ids), self._reset_root_states(env_ids), and self._resample_commands(env_ids) - [Optional] calls self._update_terrain_curriculum(env_ids), self.update_command_curriculum(env_ids) and + [Optional] calls self._update_terrain_curriculum(env_ids), Logs episode info Resets some buffers @@ -216,14 +220,13 @@ class LeggedRobot(BaseTask): # reset buffers self.actions[env_ids] = 0. self.last_actions[env_ids] = 0. + self.last_last_actions[env_ids] = 0. self.last_dof_vel[env_ids] = 0. self.feet_air_time[env_ids] = 0. self.episode_length_buf[env_ids] = 0 self.reset_buf[env_ids] = 1 self.commands_resampling_step[env_ids] = self.cfg.commands.resampling_time / self.dt self.commands_xy_accumulation[env_ids] = 0.0 - if self.cfg.commands.curriculum: - self.update_command_curriculum(env_ids) self._resample_commands(env_ids) # fill extras self.extras["episode"] = {} @@ -238,8 +241,7 @@ class LeggedRobot(BaseTask): for key in self.episode_sums.keys(): self.extras["episode"]['rew_' + key] = torch.mean(self.episode_sums[key][env_ids]) / self.max_episode_length_s self.episode_sums[key][env_ids] = 0. - if self.cfg.commands.curriculum: - self.extras["episode"]["max_command_x"] = self.command_ranges["lin_vel_x"][1] + self.extras["episode"]["max_command_x"] = self.command_ranges["lin_vel_x"][1] # send timeout info to the algorithm if self.cfg.env.send_timeouts: self.extras["time_outs"] = self.time_out_buf @@ -403,20 +405,8 @@ class LeggedRobot(BaseTask): def _post_physics_step_callback(self): """ Callback called before computing terminations, rewards, and observations - Default behaviour: Compute ang vel command based on target and heading, compute measured terrain heights and randomly push robots + Default behaviour: Compute measured terrain heights and randomly push robots """ - # env_ids = (self.episode_length_buf % int(self.cfg.commands.resampling_time / self.dt)==0).nonzero(as_tuple=False).flatten() - resampling_env_ids = ((self.commands_resampling_step <= 0.0) * (self.episode_length_buf < self.max_episode_length - 1)).nonzero(as_tuple=False).flatten() - self._resample_commands(resampling_env_ids) - if self.cfg.commands.heading_command: - mask = (self.stop_heading == 0.0) - forward = quat_apply(self.base_quat[mask], self.forward_vec[mask]) - heading = torch.atan2(forward[:, 1], forward[:, 0]) - self.commands[mask, 2] = torch.clip( - 0.5*wrap_to_pi(self.commands[mask, 3] - heading), - self.env_command_ranges["ang_vel_yaw"][:, 0], - self.env_command_ranges["ang_vel_yaw"][:, 1] - ) if self.cfg.terrain.measure_heights: self.measured_heights = self._get_heights() @@ -591,6 +581,17 @@ class LeggedRobot(BaseTask): self.commands_xy_accumulation[env_ids] += self.commands[env_ids, :2] + if self.cfg.commands.heading_command: + heading_env_ids = env_ids[self.stop_heading[env_ids] == 0.0] + if len(heading_env_ids) > 0: + forward = quat_apply(self.base_quat[heading_env_ids], self.forward_vec[heading_env_ids]) + heading = torch.atan2(forward[:, 1], forward[:, 0]) + self.commands[heading_env_ids, 2] = torch.clip( + 0.5 * wrap_to_pi(self.commands[heading_env_ids, 3] - heading), + self.env_command_ranges["ang_vel_yaw"][heading_env_ids, 0], + self.env_command_ranges["ang_vel_yaw"][heading_env_ids, 1] + ) + def _compute_torques(self, actions): """ Compute torques from actions. Actions can be interpreted as position or velocity targets given to a PD controller, or directly as scaled torques. @@ -722,21 +723,7 @@ class LeggedRobot(BaseTask): self.gym.set_actor_root_state_tensor_indexed(self.sim, gymtorch.unwrap_tensor(self.root_states), gymtorch.unwrap_tensor(env_ids_int32), len(env_ids_int32)) - - - def update_command_curriculum(self, env_ids): - """ Implements a curriculum of increasing commands - - Args: - env_ids (List[int]): ids of environments being reset - """ - # If the tracking reward is above 80% of the maximum, increase the range of commands - if torch.mean(self.episode_sums["tracking_lin_vel"][env_ids]) / self.max_episode_length > 0.8 * self.reward_scales["tracking_lin_vel"]: - self.command_ranges["lin_vel_x"][0] = np.clip(self.command_ranges["lin_vel_x"][0] - 0.5, -self.cfg.commands.max_curriculum, 0.) - self.command_ranges["lin_vel_x"][1] = np.clip(self.command_ranges["lin_vel_x"][1] + 0.5, 0., self.cfg.commands.max_curriculum) - - def _get_noise_scale_vec(self, cfg): """ Sets a vector used to scale the noise added to the observations. [NOTE]: Must be adapted when changing the observations structure @@ -807,6 +794,7 @@ class LeggedRobot(BaseTask): self.d_gains = torch.zeros(self.num_actions, dtype=torch.float, device=self.device, requires_grad=False) self.actions = torch.zeros(self.num_envs, self.num_actions, dtype=torch.float, device=self.device, requires_grad=False) self.last_actions = torch.zeros(self.num_envs, self.num_actions, dtype=torch.float, device=self.device, requires_grad=False) + self.last_last_actions = torch.zeros(self.num_envs, self.num_actions, dtype=torch.float, device=self.device, requires_grad=False) self.last_dof_vel = torch.zeros_like(self.dof_vel) self.last_root_vel = torch.zeros_like(self.root_states[:, 7:13]) self.commands = torch.zeros(self.num_envs, self.cfg.commands.num_commands, dtype=torch.float, device=self.device, requires_grad=False) # x vel, y vel, yaw vel, heading @@ -1372,10 +1360,7 @@ class LeggedRobot(BaseTask): def _reward_action_smoothness(self): # a_t - 2a_{t-1} + a_{t-2} - if not hasattr(self, 'last_last_actions'): - self.last_last_actions = torch.zeros_like(self.last_actions) rew = torch.sum((self.actions - 2 * self.last_actions + self.last_last_actions).pow(2), dim=1) - self.last_last_actions[:] = self.last_actions[:] return rew def _reward_dof_power(self): diff --git a/legged_gym/envs/base/legged_robot_config.py b/legged_gym/envs/base/legged_robot_config.py index c763440..569f882 100644 --- a/legged_gym/envs/base/legged_robot_config.py +++ b/legged_gym/envs/base/legged_robot_config.py @@ -41,8 +41,6 @@ class LeggedRobotCfg(BaseConfig): move_down_by_accumulated_xy_command = False # move down the terrain curriculum based on accumulated xy command distance instead of absolute distance class commands: - curriculum = False - max_curriculum = 1. num_commands = 4 # default: lin_vel_x, lin_vel_y, ang_vel_yaw, heading (in heading mode ang_vel_yaw is recomputed from heading error) resampling_time = 10. # time before command are changed[s] heading_command = False # if true: compute ang vel command from heading error diff --git a/legged_gym/envs/go2/go2_config.py b/legged_gym/envs/go2/go2_config.py index 778d40b..a67b65c 100644 --- a/legged_gym/envs/go2/go2_config.py +++ b/legged_gym/envs/go2/go2_config.py @@ -96,8 +96,6 @@ class GO2Cfg(LeggedRobotCfg): move_down_by_accumulated_xy_command = True # move down the terrain curriculum based on accumulated xy command distance instead of absolute distance class commands(LeggedRobotCfg.commands): - curriculum = False - max_curriculum = 1. num_commands = 4 # default: lin_vel_x, lin_vel_y, ang_vel_yaw (in heading mode ang_vel_yaw is recomputed from heading error) resampling_time = 5. # time before command are changed[s] heading_command = False # if true: compute ang vel command from heading error @@ -151,7 +149,7 @@ class GO2Cfg(LeggedRobotCfg): foot_name = "foot" penalize_contacts_on = ["thigh", "calf"] terminate_after_contacts_on = ["base"] - self_collisions = 1 # 1 to disable, 0 to enable...bitwise filter + self_collisions = 0 # 1 to disable, 0 to enable...bitwise filter class rewards(LeggedRobotCfg.rewards): soft_dof_pos_limit = 0.9 diff --git a/legged_gym/envs/go2/go2_config_fast_flat_move.py b/legged_gym/envs/go2/go2_config_fast_flat_move.py index 23d9ddc..7dc873d 100644 --- a/legged_gym/envs/go2/go2_config_fast_flat_move.py +++ b/legged_gym/envs/go2/go2_config_fast_flat_move.py @@ -146,7 +146,7 @@ class GO2Cfg(LeggedRobotCfg): 'heading': [-1.57, 1.57], # min max [rad] }, { # list for command range curriculums at specific training iterations 'iter': 40000, # training iteration at which the command ranges are updated - 'lin_vel_x': [-2.0, 4.2], # min max [m/s] + 'lin_vel_x': [-2.0, 4.5], # min max [m/s] 'lin_vel_y': [-0.5, 0.5], # min max [m/s] 'ang_vel_yaw': [-1.0, 1.0], # min max [rad/s] 'heading': [-1.57, 1.57], # min max [rad] @@ -181,7 +181,7 @@ class GO2Cfg(LeggedRobotCfg): foot_name = "foot" penalize_contacts_on = ["thigh", "calf"] terminate_after_contacts_on = ["base"] - self_collisions = 1 # 1 to disable, 0 to enable...bitwise filter + self_collisions = 0 # 1 to disable, 0 to enable...bitwise filter class rewards(LeggedRobotCfg.rewards): soft_dof_pos_limit = 0.9 diff --git a/legged_gym/envs/go2/go2_config_vanilla.py b/legged_gym/envs/go2/go2_config_vanilla.py index a7bd616..8d8ed6d 100644 --- a/legged_gym/envs/go2/go2_config_vanilla.py +++ b/legged_gym/envs/go2/go2_config_vanilla.py @@ -165,7 +165,7 @@ class GO2Cfg(LeggedRobotCfg): foot_name = "foot" penalize_contacts_on = ["thigh", "calf"] terminate_after_contacts_on = ["base"] - self_collisions = 1 # 1 to disable, 0 to enable...bitwise filter + self_collisions = 0 # 1 to disable, 0 to enable...bitwise filter class rewards(LeggedRobotCfg.rewards): soft_dof_pos_limit = 0.9 diff --git a/legged_gym/envs/go2/go2_config_vanilla_with_dynamic_cmd.py b/legged_gym/envs/go2/go2_config_vanilla_with_dynamic_cmd.py index 4473a69..ae0a3c6 100644 --- a/legged_gym/envs/go2/go2_config_vanilla_with_dynamic_cmd.py +++ b/legged_gym/envs/go2/go2_config_vanilla_with_dynamic_cmd.py @@ -165,7 +165,7 @@ class GO2Cfg(LeggedRobotCfg): foot_name = "foot" penalize_contacts_on = ["thigh", "calf"] terminate_after_contacts_on = ["base"] - self_collisions = 1 # 1 to disable, 0 to enable...bitwise filter + self_collisions = 0 # 1 to disable, 0 to enable...bitwise filter class rewards(LeggedRobotCfg.rewards): soft_dof_pos_limit = 0.9 diff --git a/rsl_rl/rsl_rl/runners/on_policy_runner.py b/rsl_rl/rsl_rl/runners/on_policy_runner.py index 1ef82e2..03d266e 100644 --- a/rsl_rl/rsl_rl/runners/on_policy_runner.py +++ b/rsl_rl/rsl_rl/runners/on_policy_runner.py @@ -253,38 +253,56 @@ class OnPolicyRunner: if self.robogauge_client is None: return - if it % 500 == 0 or last_model: - # export jit model - jit_dir = os.path.join(self.log_dir, 'jit_models') - jit_path = os.path.join(jit_dir, f'policy_jit_{it}.pt') - export_policy_as_jit(self.alg.actor_critic, jit_dir, filename=f'policy_jit_{it}.pt') - # upload to robogauge - task_name = 'go2' - self.robogauge_client.submit_task( - model_path=jit_path, - step=it, - task_name=task_name, - experiment_name=self.cfg["experiment_name"] - ) + try: + if it % 500 == 0 or last_model: + # export jit model + jit_dir = os.path.join(self.log_dir, 'jit_models') + jit_path = os.path.join(jit_dir, f'policy_jit_{it}.pt') + export_policy_as_jit(self.alg.actor_critic, jit_dir, filename=f'policy_jit_{it}.pt') + # upload to robogauge + task_name = 'go2' + self.robogauge_client.submit_task( + model_path=jit_path, + step=it, + task_name=task_name, + experiment_name=self.cfg["experiment_name"] + ) + except Exception as e: + print(f"[WARN] RoboGauge submit failed at step {it}: {e}") + return check_times = 1 if last_model: check_times = int(1e9) # keep checking until the last model is evaluated while check_times > 0: check_times -= 1 - self.robogauge_client.monitor_tasks() + try: + self.robogauge_client.monitor_tasks() + except Exception as e: + print(f"[WARN] RoboGauge monitor failed at step {it}: {e}") + break results_dir = os.path.join(self.log_dir, 'robogauge_results') os.makedirs(results_dir, exist_ok=True) result_received = False for task_id, resp in self.robogauge_client.response_data.items(): - scores = resp['results']['scores'] - step = resp['step'] + if not isinstance(resp, dict): + print(f"[WARN] RoboGauge returned an invalid response for task {task_id}: {resp}") + continue + results = resp.get('results') + step = resp.get('step', it) + if results is None: + print(f"[WARN] RoboGauge returned empty results for task {task_id} at step {step}.") + continue + scores = results.get('scores') + if scores is None: + print(f"[WARN] RoboGauge results for task {task_id} at step {step} do not contain 'scores'.") + continue if step == it: result_received = True for key, val in scores.items(): self.writer.add_scalar(f'RoboGauge/{key}', val, step) results_path = os.path.join(results_dir, f'results_{step}.yaml') with open(results_path, 'w', encoding='utf-8') as f: - yaml.dump(resp['results'], f, allow_unicode=True, sort_keys=False) + yaml.dump(results, f, allow_unicode=True, sort_keys=False) if last_model and result_received: print(f"RoboGauge result for step {it} received. Exiting wait loop.") diff --git a/rsl_rl/rsl_rl/runners/on_policy_runner_cts.py b/rsl_rl/rsl_rl/runners/on_policy_runner_cts.py index 05eee9e..8b34115 100644 --- a/rsl_rl/rsl_rl/runners/on_policy_runner_cts.py +++ b/rsl_rl/rsl_rl/runners/on_policy_runner_cts.py @@ -298,38 +298,56 @@ class OnPolicyRunnerCTS: if self.robogauge_client is None: return - if it % 500 == 0 or last_model: - # export jit model - jit_dir = os.path.join(self.log_dir, 'jit_models') - jit_path = os.path.join(jit_dir, f'policy_jit_{it}.pt') - export_policy_as_jit(self.alg.model, jit_dir, filename=f'policy_jit_{it}.pt') - # upload to robogauge - task_name = 'go2_moe' # Both cts, moe-cts actor return a tuple `action, (latent, ...)` - self.robogauge_client.submit_task( - model_path=jit_path, - step=it, - task_name=task_name, - experiment_name=self.cfg["experiment_name"] - ) + try: + if it % 500 == 0 or last_model: + # export jit model + jit_dir = os.path.join(self.log_dir, 'jit_models') + jit_path = os.path.join(jit_dir, f'policy_jit_{it}.pt') + export_policy_as_jit(self.alg.model, jit_dir, filename=f'policy_jit_{it}.pt') + # upload to robogauge + task_name = 'go2_moe' # Both cts, moe-cts actor return a tuple `action, (latent, ...)` + self.robogauge_client.submit_task( + model_path=jit_path, + step=it, + task_name=task_name, + experiment_name=self.cfg["experiment_name"] + ) + except Exception as e: + print(f"[WARN] RoboGauge submit failed at step {it}: {e}") + return check_times = 1 if last_model: check_times = int(1e9) # keep checking until manually stopped while check_times > 0: check_times -= 1 - self.robogauge_client.monitor_tasks() + try: + self.robogauge_client.monitor_tasks() + except Exception as e: + print(f"[WARN] RoboGauge monitor failed at step {it}: {e}") + break results_dir = os.path.join(self.log_dir, 'robogauge_results') os.makedirs(results_dir, exist_ok=True) result_received = False for task_id, resp in self.robogauge_client.response_data.items(): - scores = resp['results']['scores'] - step = resp['step'] + if not isinstance(resp, dict): + print(f"[WARN] RoboGauge returned an invalid response for task {task_id}: {resp}") + continue + results = resp.get('results') + step = resp.get('step', it) + if results is None: + print(f"[WARN] RoboGauge returned empty results for task {task_id} at step {step}.") + continue + scores = results.get('scores') + if scores is None: + print(f"[WARN] RoboGauge results for task {task_id} at step {step} do not contain 'scores'.") + continue if step == it: result_received = True for key, val in scores.items(): self.writer.add_scalar(f'RoboGauge/{key}', val, step) results_path = os.path.join(results_dir, f'results_{step}.yaml') with open(results_path, 'w', encoding='utf-8') as f: - yaml.dump(resp['results'], f, allow_unicode=True, sort_keys=False) + yaml.dump(results, f, allow_unicode=True, sort_keys=False) if last_model and result_received: print(f"RoboGauge result for step {it} received. Exiting wait loop.") diff --git a/setup.py b/setup.py index 6545e11..5854aeb 100644 --- a/setup.py +++ b/setup.py @@ -2,7 +2,7 @@ from setuptools import find_packages from distutils.core import setup setup(name='go2_rl_gym', - version='1.0.2', + version='1.0.3', author='Wu Tianyang', license="MIT", packages=find_packages(), diff --git a/tools/logs_merge.py b/tools/logs_merge.py index 8a72ddc..92fc62f 100644 --- a/tools/logs_merge.py +++ b/tools/logs_merge.py @@ -36,7 +36,39 @@ def fast_read(event_file_path, tag_names): if value.tag in tag_names: tag_data[event.step][value.tag] = value.simple_value - return pd.DataFrame(tag_data).T + df = pd.DataFrame(tag_data).T + df.index.name = 'step' + return df + +def normalize_tb_df(tb_df): + tb_df = tb_df.copy() + + if 'step' not in tb_df.columns: + first_col = tb_df.columns[0] if len(tb_df.columns) > 0 else None + if first_col is not None and str(first_col).startswith('Unnamed:'): + tb_df = tb_df.rename(columns={first_col: 'step'}) + elif tb_df.index.name == 'step': + tb_df = tb_df.reset_index() + else: + tb_df = tb_df.reset_index().rename(columns={'index': 'step'}) + + tb_df['step'] = pd.to_numeric(tb_df['step'], errors='coerce') + tb_df = tb_df.dropna(subset=['step']) + tb_df['step'] = tb_df['step'].astype(int) + return tb_df + +def get_tb_value(tb_df, step, candidate_tags): + row = tb_df[tb_df['step'] == step] + if row.empty: + raise KeyError(f"No tensorboard entry found for step={step}.") + + for tag in candidate_tags: + if tag not in row.columns: + continue + values = row[tag].dropna().values + if len(values) > 0: + return float(values[0]) + raise KeyError(f"No tensorboard value found for step={step} in tags: {candidate_tags}") class Collector: def __init__(self, log_dirs): @@ -58,14 +90,14 @@ class Collector: self.output_tb = self.output_dir / "tb.csv" if self.output_tb.exists(): print(f"Loading existing tensorboard data from {self.output_tb}") - self.tb_df = pd.read_csv(self.output_tb) + self.tb_df = normalize_tb_df(pd.read_csv(self.output_tb)) else: start_time = time.time() print(f"Start reading tensorboard events at {time.ctime(start_time)}") - self.tb_df = fast_read(str(self.log_dirs.glob("events.out.tfevents.*").__next__()), [ + self.tb_df = normalize_tb_df(fast_read(str(self.log_dirs.glob("events.out.tfevents.*").__next__()), [ 'Terrain/terrain_level_all', 'Episode/terrain_level_all', 'RoboGauge/benchmark' - ]) + ])) print(f"Finished reading tensorboard events in {time.time() - start_time:.2f} seconds.") self.tb_df.to_csv(self.output_tb, index=False) print(f"Saved tensorboard data to {self.output_tb}") @@ -109,7 +141,11 @@ class Collector: self.datas[f'{terrain_name}_mean@25'].append(float(data['robust_score'][terrain_name]['mean@25'])) self.datas[f'{terrain_name}_mean@50'].append(float(data['robust_score'][terrain_name]['mean@50'])) - self.datas['terrain_level'].append(float(self.tb_df[self.tb_df['step'] == it]['value'].values[0])) + self.datas['terrain_level'].append(get_tb_value( + self.tb_df, + it, + ['Terrain/terrain_level_all', 'Episode/terrain_level_all'] + )) df = pd.DataFrame(self.datas) df.to_csv(self.output_csv, index=False) print(f"Saved merged results to {self.output_csv}") @@ -117,6 +153,8 @@ class Collector: if __name__ == '__main__': parser = argparse.ArgumentParser() parser.add_argument("--log-dirs") + parser.add_argument("--read-robogauge", default=True, type=lambda x: (str(x).lower() in ['true', '1']), help="Whether to read robogauge_results") args = parser.parse_args() collector = Collector(args.log_dirs) - # collector.collect() + if args.read_robogauge: + collector.collect()