v1.0.3; fix last_last_action reset, resample_command befor compute reward bugs; add self collisions

UPDATE.md

@@ -1,6 +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

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]
@@ -216,6 +220,7 @@ 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
@@ -403,20 +408,8 @@ 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 +584,17 @@ 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.
@@ -807,6 +811,7 @@ 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 +1377,7 @@ 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):

legged_gym/envs/go2/go2_config.py

@@ -151,7 +151,7 @@ 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

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

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

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

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(),