robot_gazebo_env.RobotGazeboEnv Class Reference

Inheritance diagram for robot_gazebo_env.RobotGazeboEnv:

Public Member Functions
def	__init__ (self, robot_name_space, controllers_list, reset_controls, start_init_physics_parameters=True, reset_world_or_sim="SIMULATION")
def	seed (self, seed=None)
def	step (self, action)
def	reset (self)
def	close (self)

Public Attributes
	gazebo
	controllers_object
	reset_controls
	episode_num
	cumulated_episode_reward
	reward_pub

Private Member Functions
def	_update_episode (self)
def	_publish_reward_topic (self, reward, episode_number=1)
def	_reset_sim (self)
def	_set_init_pose (self)
def	_check_all_systems_ready (self)
def	_get_obs (self)
def	_init_env_variables (self)
def	_set_action (self, action)
def	_is_done (self, observations)
def	_compute_reward (self, observations, done)
def	_env_setup (self, initial_qpos)

Constructor & Destructor Documentation

__init__()

def robot_gazebo_env.RobotGazeboEnv.__init__	(		self,
			robot_name_space,
			controllers_list,
			reset_controls,
			start_init_physics_parameters = True,
			reset_world_or_sim = "SIMULATION"
	)

Member Function Documentation

_check_all_systems_ready()

def robot_gazebo_env.RobotGazeboEnv._check_all_systems_ready (   self )

private

Checks that all the sensors, publishers and other simulation systems are
operational.

Reimplemented in firefly_env.FireflyEnv.

_compute_reward()

def robot_gazebo_env.RobotGazeboEnv._compute_reward (   self,   observations,   done  )

private

Calculates the reward to give based on the observations given.

_env_setup()

def robot_gazebo_env.RobotGazeboEnv._env_setup (   self,   initial_qpos  )

private

Initial configuration of the environment. Can be used to configure initial state
and extract information from the simulation.

Reimplemented in firefly_env.FireflyEnv.

_get_obs()

def robot_gazebo_env.RobotGazeboEnv._get_obs (   self )

private

Returns the observation.

Reimplemented in firefly_env.FireflyEnv.

_init_env_variables()

def robot_gazebo_env.RobotGazeboEnv._init_env_variables (   self )

private

Inits variables needed to be initialised each time we reset at the start
of an episode.

Reimplemented in firefly_env.FireflyEnv.

_is_done()

def robot_gazebo_env.RobotGazeboEnv._is_done (   self,   observations  )

private

Indicates whether or not the episode is done ( the robot has fallen for example).

Reimplemented in firefly_env.FireflyEnv.

_publish_reward_topic()

def robot_gazebo_env.RobotGazeboEnv._publish_reward_topic (   self,   reward,   episode_number = 1  )

private

This function publishes the given reward in the reward topic for
easy access from ROS infrastructure.
:param reward:
:param episode_number:
:return:

_reset_sim()

def robot_gazebo_env.RobotGazeboEnv._reset_sim (   self )

private

Resets a simulation

_set_action()

def robot_gazebo_env.RobotGazeboEnv._set_action (   self,   action  )

private

Applies the given action to the simulation.

Reimplemented in firefly_env.FireflyEnv.

_set_init_pose()

def robot_gazebo_env.RobotGazeboEnv._set_init_pose (   self )

private

Sets the Robot in its init pose

Reimplemented in firefly_env.FireflyEnv.

_update_episode()

def robot_gazebo_env.RobotGazeboEnv._update_episode (   self )

private

Publishes the cumulated reward of the episode and
increases the episode number by one.
:return:

close()

def robot_gazebo_env.RobotGazeboEnv.close

(

self

)

Function executed when closing the environment.
Use it for closing GUIS and other systems that need closing.
:return:

reset()

def robot_gazebo_env.RobotGazeboEnv.reset

(

self

)

seed()

def robot_gazebo_env.RobotGazeboEnv.seed	(		self,
			seed = None
	)

step()

def robot_gazebo_env.RobotGazeboEnv.step	(		self,
			action
	)

Function executed each time step.
Here we get the action execute it in a time step and retrieve the
observations generated by that action.
:param action:
:return: obs, reward, done, info

Here we should convert the action num to movement action, execute the action in the
simulation and get the observations result of performing that action.

Member Data Documentation

controllers_object

robot_gazebo_env.RobotGazeboEnv.controllers_object

cumulated_episode_reward

robot_gazebo_env.RobotGazeboEnv.cumulated_episode_reward

episode_num

robot_gazebo_env.RobotGazeboEnv.episode_num

gazebo

robot_gazebo_env.RobotGazeboEnv.gazebo

reset_controls

robot_gazebo_env.RobotGazeboEnv.reset_controls

reward_pub

robot_gazebo_env.RobotGazeboEnv.reward_pub

---

The documentation for this class was generated from the following file:

• src/ICRA-Firefly-RoboRTS/roborts_decision/dqn_decision/openai_ros/robot_gazebo_env.py