Fault Environment Example
This tutorial demonstrates how to configure and use a simple BSK-RL environment to model faults in a system with four reaction wheels (RWs).
Load Modules
[1]:
import numpy as np
from typing import Iterable
from Basilisk.architecture import bskLogging
from Basilisk.utilities import macros, orbitalMotion, simIncludeRW
from Basilisk.simulation import reactionWheelStateEffector
from Basilisk.fswAlgorithms import rwNullSpace
from Basilisk.architecture import messaging
from bsk_rl import SatelliteTasking, act, data, obs, scene, sats
from bsk_rl.sim import dyn, fsw, world
from bsk_rl.utils.orbital import random_orbit, random_unit_vector
from bsk_rl.utils.functional import default_args
bskLogging.setDefaultLogLevel(bskLogging.BSK_WARNING)
Making Faults Cases
Creating a fault base class and defining individual fault types enables modeling multiple kinds of faults within a single satellite. In this example, a power draw limit is applied to RWs, causing it to operate at reduced speed compared to nominal conditions. By default, while a torque limit is enforced, there are no restrictions on power draw. time is used to define the time at which the fault occurs, reducedLimit specifies the power draw limit in watts, and wheel_Idx indicates which
RW is affected by the fault. It can be set to a value from 1 to 4, or to all to apply the fault to every RW.
[2]:
class FaultObject:
def __init__(self, name, time, verbose=True, **kwargs):
self.name = name
self.time = time
self.verbose = verbose
self.message = None
self.message_printed = False
def execute(self, satellite):
raise NotImplementedError(
f"{self.name} does not have a custom execute function!"
)
def print_message(self, message, satellite):
if not self.message_printed:
satellite.logger.info(message)
self.message_printed = True
def addFaultToSimulation(self, satellite, listIdx):
self.uniqueFaultIdx = listIdx # Index in the faultList array.
satellite.simulator.createNewEvent(
f"add{self.name}Fault",
satellite.dynamics.dyn_rate,
eventActive=True,
conditionTime=self.time,
actionList=[
f"self.faultList[{self.uniqueFaultIdx}].execute({satellite._satellite_command})",
f"self.faultList[{self.uniqueFaultIdx}].print({satellite._satellite_command})",
],
)
class RwPowerFault(FaultObject):
def __init__(self, name, time, reducedLimit, wheelIdx):
super().__init__(name, time)
self.reducedLimit = reducedLimit
if isinstance(wheelIdx, float):
# int needed around wheelIdx because np.random.choice doesn't return
# a type int, and the index will not register in execute without it.
self.wheelIdx = int(wheelIdx)
elif isinstance(wheelIdx, int) or wheelIdx == "all":
# option to trigger the fault in all wheels reflecting a larger power issue
self.wheelIdx = wheelIdx
else:
raise ValueError(
"Fault parameter 'wheelIdx' must either be a number corresponding to a reaction wheel or the string 'all'"
)
def execute(self, satellite):
dynModels = satellite.dynamics
if self.wheelIdx == 1:
dynModels.rwFactory.rwList["RW1"].P_max = self.reducedLimit
elif self.wheelIdx == 2:
dynModels.rwFactory.rwList["RW2"].P_max = self.reducedLimit
elif self.wheelIdx == 3:
dynModels.rwFactory.rwList["RW3"].P_max = self.reducedLimit
elif self.wheelIdx == 4:
dynModels.rwFactory.rwList["RW4"].P_max = self.reducedLimit
elif self.wheelIdx == "all":
# option to trigger the fault in all wheels (not supported for all fault types)
dynModels.rwFactory.rwList["RW1"].P_max = self.reducedLimit
dynModels.rwFactory.rwList["RW2"].P_max = self.reducedLimit
dynModels.rwFactory.rwList["RW3"].P_max = self.reducedLimit
dynModels.rwFactory.rwList["RW4"].P_max = self.reducedLimit
def print(self, satellite):
if self.wheelIdx == "all":
self.message = f"RW Power Fault: all RW's power limit reduced to {self.reducedLimit} Watts at {self.time * macros.NANO2MIN} minutes!"
else:
self.message = f"RW Power Fault: RW{self.wheelIdx}'s power limit reduced to {self.reducedLimit} Watts at {self.time * macros.NANO2MIN} minutes!"
super().print_message(self.message, satellite)
Configure the Simulation Models
Dynamics model:
FullFeaturedDynModelis used as the base class, andsetup_reaction_wheel_dyn_effectoris overridden to support four RWs. Two additional properties are added: the angle between the Sun and the solar panel, and the speed fraction of each RW.
[3]:
class CustomDynModel(dyn.FullFeaturedDynModel):
@property
def solar_angle_norm(self) -> float:
sun_vec_N = (
self.world.gravFactory.spiceObject.planetStateOutMsgs[self.world.sun_index]
.read()
.PositionVector
)
sun_vec_N_hat = sun_vec_N / np.linalg.norm(sun_vec_N)
solar_panel_vec_B = np.array([0, 0, -1])
mat = np.transpose(self.BN)
solar_panel_vec_N = np.matmul(mat, solar_panel_vec_B)
error_angle = np.arccos(np.dot(solar_panel_vec_N, sun_vec_N_hat))
return error_angle / np.pi
@property
def wheel_speeds_frac(self):
rw_speed = self.wheel_speeds
return rw_speed[0:4] / (self.maxWheelSpeed * macros.rpm2radsec)
@default_args(
wheelSpeeds=lambda: np.random.uniform(-1500, 1500, 4),
maxWheelSpeed=np.inf,
u_max=0.200,
)
def setup_reaction_wheel_dyn_effector(
self,
wheelSpeeds: Iterable[float],
maxWheelSpeed: float,
u_max: float,
priority: int = 997,
**kwargs,
) -> None:
"""Set the RW state effector parameters.
Args:
wheelSpeeds: Initial speeds of each wheel [RPM]
maxWheelSpeed: Failure speed for wheels [RPM]
u_max: Torque producible by wheel [N*m]
priority: Model priority.
kwargs: Ignored
"""
def balancedHR16Triad(
useRandom=False, randomBounds=(-400, 400), wheelSpeeds=[500, 500, 500, 500]
):
"""Create a set of three HR16 reaction wheels.
Args:
useRandom: Use random values for wheel speeds.
randomBounds: Bounds for random wheel speeds.
wheelSpeeds: Fixed wheel speeds.
Returns:
tuple:
* **rwStateEffector**: Reaction wheel state effector instance.
* **rwFactory**: Factory containing defined reaction wheels.
* **wheelSpeeds**: Wheel speeds.
"""
rwFactory = simIncludeRW.rwFactory()
if useRandom:
wheelSpeeds = np.random.uniform(randomBounds[0], randomBounds[1], 4)
c = 3 ** (-0.5)
rwFactory.create(
"Honeywell_HR16",
[1, 0, 0],
maxMomentum=50.0,
Omega=wheelSpeeds[0],
)
rwFactory.create(
"Honeywell_HR16",
[0, 1, 0],
maxMomentum=50.0,
Omega=wheelSpeeds[1],
)
rwFactory.create(
"Honeywell_HR16",
[0, 0, 1],
maxMomentum=50.0,
Omega=wheelSpeeds[2],
)
rwFactory.create(
"Honeywell_HR16",
[c, c, c],
maxMomentum=50.0,
Omega=wheelSpeeds[3],
)
rwStateEffector = reactionWheelStateEffector.ReactionWheelStateEffector()
return rwStateEffector, rwFactory, wheelSpeeds
self.maxWheelSpeed = maxWheelSpeed
self.rwStateEffector, self.rwFactory, _ = balancedHR16Triad(
useRandom=False,
wheelSpeeds=wheelSpeeds,
)
for RW in self.rwFactory.rwList.values():
RW.u_max = u_max
self.rwStateEffector.ModelTag = "ReactionWheels"
self.rwFactory.addToSpacecraft(
self.scObject.ModelTag, self.rwStateEffector, self.scObject
)
self.simulator.AddModelToTask(
self.task_name, self.rwStateEffector, ModelPriority=priority
)
self.Gs = np.array(
[
[1, 0, 0, 1 / np.sqrt(3)], # RW1 and RW4 x-components
[0, 1, 0, 1 / np.sqrt(3)], # RW2 and RW4 y-components
[0, 0, 1, 1 / np.sqrt(3)], # RW3 and RW4 z-components
]
)
Flight software model: A custom flight software model is defined to support four RWs. It is based on the
SteeringImagerFSWModel, with the main modification being the addition of therwNullSpacemodule. Due to the redundancy of having four RWs, there are infinitely many solutions for mapping the required body control torque to individual RW torques. To address this, once the control torque is computed, the RW null space is used to decelerate the wheels without applying additional torque to the spacecraft.
[4]:
class CustomSteeringImagerFSWModel(fsw.SteeringImagerFSWModel):
def __init__(self, *args, **kwargs) -> None:
"""Convenience type that combines the imaging FSW model with MRP steering for four reaction wheels."""
super().__init__(*args, **kwargs)
def _set_config_msgs(self) -> None:
super()._set_config_msgs()
self._set_rw_constellation_msg()
def _set_rw_constellation_msg(self) -> None:
"""Set the reaction wheel constellation message."""
rwConstellationConfig = messaging.RWConstellationMsgPayload()
rwConstellationConfig.numRW = self.dynamics.rwFactory.getNumOfDevices()
rwConfigElementList = []
for i in range(4):
rwConfigElementMsg = messaging.RWConfigElementMsgPayload()
rwConfigElementMsg.gsHat_B = self.dynamics.Gs[:, i]
rwConfigElementMsg.Js = self.dynamics.rwFactory.rwList[f"RW{i + 1}"].Js
rwConfigElementMsg.uMax = self.dynamics.rwFactory.rwList[f"RW{i + 1}"].u_max
rwConfigElementList.append(rwConfigElementMsg)
rwConstellationConfig.reactionWheels = rwConfigElementList
self.rwConstellationConfigInMsg = messaging.RWConstellationMsg().write(
rwConstellationConfig
)
def _set_gateway_msgs(self) -> None:
"""Create C-wrapped gateway messages."""
self.attRefMsg = messaging.AttRefMsg_C()
self.attGuidMsg = messaging.AttGuidMsg_C()
self._zero_gateway_msgs()
# connect gateway FSW effector command msgs with the dynamics
self.dynamics.rwStateEffector.rwMotorCmdInMsg.subscribeTo(
self.rwNullSpace.rwMotorTorqueOutMsg
)
self.dynamics.thrusterSet.cmdsInMsg.subscribeTo(
self.thrDump.thrusterOnTimeOutMsg
)
class MRPControlTask(fsw.SteeringImagerFSWModel.MRPControlTask):
def _create_module_data(self) -> None:
super()._create_module_data()
self.rwNullSpace = self.fsw.rwNullSpace = rwNullSpace.rwNullSpace()
self.rwNullSpace.ModelTag = "rwNullSpace"
def _setup_fsw_objects(self, **kwargs) -> None:
super()._setup_fsw_objects(**kwargs)
self.set_rw_null_space(**kwargs)
@default_args(OmegaGain=0.3)
def set_rw_null_space(
self,
OmegaGain: float,
**kwargs,
) -> None:
"""Define the null space to slow down the wheels."""
self.rwNullSpace.rwMotorTorqueInMsg.subscribeTo(
self.rwMotorTorque.rwMotorTorqueOutMsg
)
self.rwNullSpace.rwSpeedsInMsg.subscribeTo(
self.fsw.dynamics.rwStateEffector.rwSpeedOutMsg
)
self.rwNullSpace.rwConfigInMsg.subscribeTo(
self.fsw.rwConstellationConfigInMsg
)
self.rwNullSpace.OmegaGain = OmegaGain
self._add_model_to_task(self.rwNullSpace, priority=1193)
Configure the Satellite
-
SatProperties: Body angular velocity, instrument pointing direction, body position, body velocity, battery charge (properties in flight software model or dynamics model). Also, customized dynamics property in CustomDynModel above: Angle between the sun and the solar panel and four RW speed fraction.
OpportunityProperties: Target’s priority, normalized location, and target angle (upcoming 32 targets).
Time: Simulation time.
Eclipse: Next eclipse start and end times.
-
Desat: Manage momentum for the RWs for 60 seconds.
Charge: Enter a sun-pointing charging mode for 60 seconds.
Image: Image target from upcoming 32 targets
The fault is introduced by overriding the reset_post_sim_init function. The probability of the fault occurring can be specified using the fault_chance argument, and the time of occurrence can be set using the fault_time argument.
[5]:
class CustomSatComposed(sats.ImagingSatellite):
observation_spec = [
obs.SatProperties(
dict(prop="omega_BP_P", norm=0.03),
dict(prop="c_hat_P"),
dict(prop="r_BN_P", norm=orbitalMotion.REQ_EARTH * 1e3),
dict(prop="v_BN_P", norm=7616.5),
dict(prop="battery_charge_fraction"),
dict(prop="solar_angle_norm"),
dict(prop="wheel_speeds_frac"),
),
obs.OpportunityProperties(
dict(prop="priority"),
dict(prop="r_LP_P", norm=orbitalMotion.REQ_EARTH * 1e3),
dict(prop="target_angle", norm=np.pi),
type="target",
n_ahead_observe=32,
),
obs.Time(),
obs.Eclipse(norm=5700),
]
action_spec = [
act.Desat(duration=60.0),
act.Charge(duration=60.0),
act.Image(n_ahead_image=32),
]
# Modified the constructor to include the fault chance and list
def __init__(self, *args, fault_chance=0, fault_time=0.0, **kwargs) -> None:
super().__init__(*args, **kwargs)
self.fault_chance = fault_chance
self.fault_time = fault_time
self.faultList = [] # List to store faults
def reset_post_sim_init(self) -> None:
super().reset_post_sim_init()
if np.random.random() < self.fault_chance:
powerFault = RwPowerFault(
"rwPowerLimited", self.fault_time, reducedLimit=1.0, wheelIdx=1
)
self.faultList = [powerFault]
self.simulator.faultList = self.faultList
for i in range(len(self.faultList)):
self.faultList[i].addFaultToSimulation(self, i)
dyn_type = CustomDynModel
fsw_type = CustomSteeringImagerFSWModel
Configure Satellite Pareameters
When instantiating a satellite, these parameters can be overriden with a constant or rerandomized every time the environment is reset using the sat_args dictionary.
[6]:
dataStorageCapacity = 20 * 8e6 * 100
batteryStorageCapacity = 80.0 * 3600 * 2
sat_args = CustomSatComposed.default_sat_args(
oe=random_orbit,
imageAttErrorRequirement=0.01,
imageRateErrorRequirement=0.01,
batteryStorageCapacity=batteryStorageCapacity,
storedCharge_Init=lambda: np.random.uniform(0.4, 1.0) * batteryStorageCapacity,
u_max=0.2, # More realistic values than 1.0
K1=0.5, # Updated value to have smooth and more predictable control
nHat_B=np.array([0, 0, -1]),
imageTargetMinimumElevation=np.radians(45),
rwBasePower=20,
maxWheelSpeed=1500,
storageInit=lambda: np.random.randint(
0 * dataStorageCapacity,
0.01 * dataStorageCapacity,
),
wheelSpeeds=lambda: np.random.uniform(-900, 900, 4),
disturbance_vector=lambda: random_unit_vector(),
)
# Make the satellites
satellites = []
satellites.append(
CustomSatComposed(
"EO",
sat_args,
fault_chance=1.0,
fault_time=0.0, # Fault occurs at 0.0 (nano seconds)
)
)
Making and interacting the Environment
For this example, the single-agent SatelliteTasking environment is used. n addition to the configured satellite, the environment requires a scenario, which defines the context in which the satellite operates. In this case, the scenario uses UniformTargets, placing 1000 uniformly distributed targets across the Earth’s surface. The environment also takes a rewarder, which defines how
data collected from the scenario is rewarded. Here, UniqueImageReward is used, which assigns rewards based on the sum of the priorities of uniquely imaged targets in each episode.
[7]:
env = SatelliteTasking(
satellite=satellites,
terminate_on_time_limit=True,
world_type=world.GroundStationWorldModel,
world_args=world.GroundStationWorldModel.default_world_args(),
scenario=scene.UniformTargets(n_targets=1000),
rewarder=data.UniqueImageReward(),
sim_rate=0.5,
max_step_duration=300.0,
time_limit=95 * 60 * 3,
log_level="INFO",
failure_penalty=0,
# disable_env_checker=True, # For debugging
)
First, the environment is reset. A seed is provided to ensure reproducibility of the results; it can be removed to enable randomized testing.
[8]:
observation, info = env.reset(seed=1)
2025-12-03 22:23:09,508 gym INFO Resetting environment with seed=1
2025-12-03 22:23:09,510 scene.targets INFO Generating 1000 targets
2025-12-03 22:23:09,605 sats.satellite.EO INFO <0.00> EO: Finding opportunity windows from 0.00 to 17400.00 seconds
2025-12-03 22:23:09,886 gym INFO <0.00> Environment reset
The composed satellite action space returns a human-readable action map and each satellite has the same action space and similar observation space.
[9]:
print("Actions:", satellites[0].action_description)
print("States:", env.unwrapped.satellites[0].observation_description, "\n")
# Using the composed satellite features also provides a human-readable state:
for satellite in env.unwrapped.satellites:
for k, v in satellite.observation_builder.obs_dict().items():
print(f"{k}: {v}")
Actions: ['action_desat', 'action_charge', 'action_image_0', 'action_image_1', 'action_image_2', 'action_image_3', 'action_image_4', 'action_image_5', 'action_image_6', 'action_image_7', 'action_image_8', 'action_image_9', 'action_image_10', 'action_image_11', 'action_image_12', 'action_image_13', 'action_image_14', 'action_image_15', 'action_image_16', 'action_image_17', 'action_image_18', 'action_image_19', 'action_image_20', 'action_image_21', 'action_image_22', 'action_image_23', 'action_image_24', 'action_image_25', 'action_image_26', 'action_image_27', 'action_image_28', 'action_image_29', 'action_image_30', 'action_image_31']
States: [np.str_('sat_props.omega_BP_P_normd[0]'), np.str_('sat_props.omega_BP_P_normd[1]'), np.str_('sat_props.omega_BP_P_normd[2]'), np.str_('sat_props.c_hat_P[0]'), np.str_('sat_props.c_hat_P[1]'), np.str_('sat_props.c_hat_P[2]'), np.str_('sat_props.r_BN_P_normd[0]'), np.str_('sat_props.r_BN_P_normd[1]'), np.str_('sat_props.r_BN_P_normd[2]'), np.str_('sat_props.v_BN_P_normd[0]'), np.str_('sat_props.v_BN_P_normd[1]'), np.str_('sat_props.v_BN_P_normd[2]'), np.str_('sat_props.battery_charge_fraction'), np.str_('sat_props.solar_angle_norm'), np.str_('sat_props.wheel_speeds_frac[0]'), np.str_('sat_props.wheel_speeds_frac[1]'), np.str_('sat_props.wheel_speeds_frac[2]'), np.str_('target.target_0.priority'), np.str_('target.target_0.r_LP_P_normd[0]'), np.str_('target.target_0.r_LP_P_normd[1]'), np.str_('target.target_0.r_LP_P_normd[2]'), np.str_('target.target_0.target_angle_normd'), np.str_('target.target_1.priority'), np.str_('target.target_1.r_LP_P_normd[0]'), np.str_('target.target_1.r_LP_P_normd[1]'), np.str_('target.target_1.r_LP_P_normd[2]'), np.str_('target.target_1.target_angle_normd'), np.str_('target.target_2.priority'), np.str_('target.target_2.r_LP_P_normd[0]'), np.str_('target.target_2.r_LP_P_normd[1]'), np.str_('target.target_2.r_LP_P_normd[2]'), np.str_('target.target_2.target_angle_normd'), np.str_('target.target_3.priority'), np.str_('target.target_3.r_LP_P_normd[0]'), np.str_('target.target_3.r_LP_P_normd[1]'), np.str_('target.target_3.r_LP_P_normd[2]'), np.str_('target.target_3.target_angle_normd'), np.str_('target.target_4.priority'), np.str_('target.target_4.r_LP_P_normd[0]'), np.str_('target.target_4.r_LP_P_normd[1]'), np.str_('target.target_4.r_LP_P_normd[2]'), np.str_('target.target_4.target_angle_normd'), np.str_('target.target_5.priority'), np.str_('target.target_5.r_LP_P_normd[0]'), np.str_('target.target_5.r_LP_P_normd[1]'), np.str_('target.target_5.r_LP_P_normd[2]'), np.str_('target.target_5.target_angle_normd'), np.str_('target.target_6.priority'), np.str_('target.target_6.r_LP_P_normd[0]'), np.str_('target.target_6.r_LP_P_normd[1]'), np.str_('target.target_6.r_LP_P_normd[2]'), np.str_('target.target_6.target_angle_normd'), np.str_('target.target_7.priority'), np.str_('target.target_7.r_LP_P_normd[0]'), np.str_('target.target_7.r_LP_P_normd[1]'), np.str_('target.target_7.r_LP_P_normd[2]'), np.str_('target.target_7.target_angle_normd'), np.str_('target.target_8.priority'), np.str_('target.target_8.r_LP_P_normd[0]'), np.str_('target.target_8.r_LP_P_normd[1]'), np.str_('target.target_8.r_LP_P_normd[2]'), np.str_('target.target_8.target_angle_normd'), np.str_('target.target_9.priority'), np.str_('target.target_9.r_LP_P_normd[0]'), np.str_('target.target_9.r_LP_P_normd[1]'), np.str_('target.target_9.r_LP_P_normd[2]'), np.str_('target.target_9.target_angle_normd'), np.str_('target.target_10.priority'), np.str_('target.target_10.r_LP_P_normd[0]'), np.str_('target.target_10.r_LP_P_normd[1]'), np.str_('target.target_10.r_LP_P_normd[2]'), np.str_('target.target_10.target_angle_normd'), np.str_('target.target_11.priority'), np.str_('target.target_11.r_LP_P_normd[0]'), np.str_('target.target_11.r_LP_P_normd[1]'), np.str_('target.target_11.r_LP_P_normd[2]'), np.str_('target.target_11.target_angle_normd'), np.str_('target.target_12.priority'), np.str_('target.target_12.r_LP_P_normd[0]'), np.str_('target.target_12.r_LP_P_normd[1]'), np.str_('target.target_12.r_LP_P_normd[2]'), np.str_('target.target_12.target_angle_normd'), np.str_('target.target_13.priority'), np.str_('target.target_13.r_LP_P_normd[0]'), np.str_('target.target_13.r_LP_P_normd[1]'), np.str_('target.target_13.r_LP_P_normd[2]'), np.str_('target.target_13.target_angle_normd'), np.str_('target.target_14.priority'), np.str_('target.target_14.r_LP_P_normd[0]'), np.str_('target.target_14.r_LP_P_normd[1]'), np.str_('target.target_14.r_LP_P_normd[2]'), np.str_('target.target_14.target_angle_normd'), np.str_('target.target_15.priority'), np.str_('target.target_15.r_LP_P_normd[0]'), np.str_('target.target_15.r_LP_P_normd[1]'), np.str_('target.target_15.r_LP_P_normd[2]'), np.str_('target.target_15.target_angle_normd'), np.str_('target.target_16.priority'), np.str_('target.target_16.r_LP_P_normd[0]'), np.str_('target.target_16.r_LP_P_normd[1]'), np.str_('target.target_16.r_LP_P_normd[2]'), np.str_('target.target_16.target_angle_normd'), np.str_('target.target_17.priority'), np.str_('target.target_17.r_LP_P_normd[0]'), np.str_('target.target_17.r_LP_P_normd[1]'), np.str_('target.target_17.r_LP_P_normd[2]'), np.str_('target.target_17.target_angle_normd'), np.str_('target.target_18.priority'), np.str_('target.target_18.r_LP_P_normd[0]'), np.str_('target.target_18.r_LP_P_normd[1]'), np.str_('target.target_18.r_LP_P_normd[2]'), np.str_('target.target_18.target_angle_normd'), np.str_('target.target_19.priority'), np.str_('target.target_19.r_LP_P_normd[0]'), np.str_('target.target_19.r_LP_P_normd[1]'), np.str_('target.target_19.r_LP_P_normd[2]'), np.str_('target.target_19.target_angle_normd'), np.str_('target.target_20.priority'), np.str_('target.target_20.r_LP_P_normd[0]'), np.str_('target.target_20.r_LP_P_normd[1]'), np.str_('target.target_20.r_LP_P_normd[2]'), np.str_('target.target_20.target_angle_normd'), np.str_('target.target_21.priority'), np.str_('target.target_21.r_LP_P_normd[0]'), np.str_('target.target_21.r_LP_P_normd[1]'), np.str_('target.target_21.r_LP_P_normd[2]'), np.str_('target.target_21.target_angle_normd'), np.str_('target.target_22.priority'), np.str_('target.target_22.r_LP_P_normd[0]'), np.str_('target.target_22.r_LP_P_normd[1]'), np.str_('target.target_22.r_LP_P_normd[2]'), np.str_('target.target_22.target_angle_normd'), np.str_('target.target_23.priority'), np.str_('target.target_23.r_LP_P_normd[0]'), np.str_('target.target_23.r_LP_P_normd[1]'), np.str_('target.target_23.r_LP_P_normd[2]'), np.str_('target.target_23.target_angle_normd'), np.str_('target.target_24.priority'), np.str_('target.target_24.r_LP_P_normd[0]'), np.str_('target.target_24.r_LP_P_normd[1]'), np.str_('target.target_24.r_LP_P_normd[2]'), np.str_('target.target_24.target_angle_normd'), np.str_('target.target_25.priority'), np.str_('target.target_25.r_LP_P_normd[0]'), np.str_('target.target_25.r_LP_P_normd[1]'), np.str_('target.target_25.r_LP_P_normd[2]'), np.str_('target.target_25.target_angle_normd'), np.str_('target.target_26.priority'), np.str_('target.target_26.r_LP_P_normd[0]'), np.str_('target.target_26.r_LP_P_normd[1]'), np.str_('target.target_26.r_LP_P_normd[2]'), np.str_('target.target_26.target_angle_normd'), np.str_('target.target_27.priority'), np.str_('target.target_27.r_LP_P_normd[0]'), np.str_('target.target_27.r_LP_P_normd[1]'), np.str_('target.target_27.r_LP_P_normd[2]'), np.str_('target.target_27.target_angle_normd'), np.str_('target.target_28.priority'), np.str_('target.target_28.r_LP_P_normd[0]'), np.str_('target.target_28.r_LP_P_normd[1]'), np.str_('target.target_28.r_LP_P_normd[2]'), np.str_('target.target_28.target_angle_normd'), np.str_('target.target_29.priority'), np.str_('target.target_29.r_LP_P_normd[0]'), np.str_('target.target_29.r_LP_P_normd[1]'), np.str_('target.target_29.r_LP_P_normd[2]'), np.str_('target.target_29.target_angle_normd'), np.str_('target.target_30.priority'), np.str_('target.target_30.r_LP_P_normd[0]'), np.str_('target.target_30.r_LP_P_normd[1]'), np.str_('target.target_30.r_LP_P_normd[2]'), np.str_('target.target_30.target_angle_normd'), np.str_('target.target_31.priority'), np.str_('target.target_31.r_LP_P_normd[0]'), np.str_('target.target_31.r_LP_P_normd[1]'), np.str_('target.target_31.r_LP_P_normd[2]'), np.str_('target.target_31.target_angle_normd'), np.str_('time'), np.str_('eclipse[0]'), np.str_('eclipse[1]')]
sat_props: {'omega_BP_P_normd': array([0.00137284, 0.00080893, 0.00185074]), 'c_hat_P': array([-0.94095395, -0.07120216, -0.3309621 ]), 'r_BN_P_normd': array([-0.76023893, -0.76226973, 0.03873832]), 'v_BN_P_normd': array([-0.74001565, 0.72585949, -0.23976204]), 'battery_charge_fraction': 0.48805353449026784, 'solar_angle_norm': np.float64(0.3675725758375922), 'wheel_speeds_frac': array([ 0.2222634 , -0.3546573 , 0.45374092])}
target: {'target_0': {'priority': 0.6797657443023485, 'r_LP_P_normd': array([-0.72304393, -0.69048255, 0.02100749]), 'target_angle_normd': np.float64(0.6357597658378449)}, 'target_1': {'priority': 0.1011278274566988, 'r_LP_P_normd': array([-0.8839314 , -0.46366914, -0.06063175]), 'target_angle_normd': np.float64(0.3764086411837673)}, 'target_2': {'priority': 0.6931851990942818, 'r_LP_P_normd': array([-0.92043412, -0.36952122, -0.12749548]), 'target_angle_normd': np.float64(0.3723877146688926)}, 'target_3': {'priority': 0.17225514293500632, 'r_LP_P_normd': array([-0.92565997, -0.37833103, -0.00438879]), 'target_angle_normd': np.float64(0.38981813759316086)}, 'target_4': {'priority': 0.5711709172856598, 'r_LP_P_normd': array([-0.96343073, -0.26718398, -0.02034567]), 'target_angle_normd': np.float64(0.3943146022248573)}, 'target_5': {'priority': 0.39915339691165386, 'r_LP_P_normd': array([-0.9832796 , -0.17545716, -0.04874432]), 'target_angle_normd': np.float64(0.39937897834300234)}, 'target_6': {'priority': 0.3659991252731889, 'r_LP_P_normd': array([-0.99415125, -0.07715346, -0.07556872]), 'target_angle_normd': np.float64(0.4078843692651548)}, 'target_7': {'priority': 0.8196046614443331, 'r_LP_P_normd': array([-0.99765329, -0.01207943, -0.06739442]), 'target_angle_normd': np.float64(0.4168294389284707)}, 'target_8': {'priority': 0.31321450974410614, 'r_LP_P_normd': array([-0.97449116, 0.1725315 , -0.1435265 ]), 'target_angle_normd': np.float64(0.4358647819265422)}, 'target_9': {'priority': 0.9484757208286156, 'r_LP_P_normd': array([-0.96031054, 0.17441228, -0.21767872]), 'target_angle_normd': np.float64(0.433242760838707)}, 'target_10': {'priority': 0.48592850306846924, 'r_LP_P_normd': array([-0.96853779, 0.21402263, -0.12699944]), 'target_angle_normd': np.float64(0.4426489488945429)}, 'target_11': {'priority': 0.6184129633885858, 'r_LP_P_normd': array([-0.96210743, 0.21701823, -0.16508293]), 'target_angle_normd': np.float64(0.4411215055325246)}, 'target_12': {'priority': 0.17947175160982998, 'r_LP_P_normd': array([-0.94017117, 0.243405 , -0.23839502]), 'target_angle_normd': np.float64(0.4427323667761162)}, 'target_13': {'priority': 0.7384995398085523, 'r_LP_P_normd': array([-0.80487741, 0.52282763, -0.28075545]), 'target_angle_normd': np.float64(0.48648454206124414)}, 'target_14': {'priority': 0.27114812998614257, 'r_LP_P_normd': array([-0.76729423, 0.58576762, -0.26102845]), 'target_angle_normd': np.float64(0.4977256880591026)}, 'target_15': {'priority': 0.602211552115518, 'r_LP_P_normd': array([-0.69808315, 0.6848033 , -0.20910371]), 'target_angle_normd': np.float64(0.5172281968118192)}, 'target_16': {'priority': 0.379803286768697, 'r_LP_P_normd': array([-0.49501598, 0.82573585, -0.27040613]), 'target_angle_normd': np.float64(0.5507581988576493)}, 'target_17': {'priority': 0.4436831213331952, 'r_LP_P_normd': array([-0.45042693, 0.86931897, -0.20347018]), 'target_angle_normd': np.float64(0.5625207407345922)}, 'target_18': {'priority': 0.7048706468084478, 'r_LP_P_normd': array([-0.21420724, 0.9326702 , -0.29024395]), 'target_angle_normd': np.float64(0.59373704837557)}, 'target_19': {'priority': 0.9285111717464954, 'r_LP_P_normd': array([-0.19966509, 0.94633197, -0.25414496]), 'target_angle_normd': np.float64(0.5980174335717613)}, 'target_20': {'priority': 0.6283839193934228, 'r_LP_P_normd': array([ 0.04079828, 0.96062029, -0.27485298]), 'target_angle_normd': np.float64(0.6314125127394534)}, 'target_21': {'priority': 0.1929743249397491, 'r_LP_P_normd': array([ 0.0355612 , 0.97627369, -0.21360027]), 'target_angle_normd': np.float64(0.6341742328673365)}, 'target_22': {'priority': 0.44341724161916973, 'r_LP_P_normd': array([ 0.11710105, 0.96569059, -0.23179522]), 'target_angle_normd': np.float64(0.6446733019141536)}, 'target_23': {'priority': 0.11836853522372437, 'r_LP_P_normd': array([ 0.34219224, 0.92570533, -0.16116486]), 'target_angle_normd': np.float64(0.6810789969475336)}, 'target_24': {'priority': 0.8270836989643272, 'r_LP_P_normd': array([ 0.37614852, 0.90638066, -0.19231846]), 'target_angle_normd': np.float64(0.6842502087329536)}, 'target_25': {'priority': 0.5185496026201819, 'r_LP_P_normd': array([ 0.38424706, 0.90105932, -0.20111263]), 'target_angle_normd': np.float64(0.6849377870859835)}, 'target_26': {'priority': 0.9675170836931263, 'r_LP_P_normd': array([ 0.38356319, 0.9111912 , -0.15036584]), 'target_angle_normd': np.float64(0.6878383017756565)}, 'target_27': {'priority': 0.9065897890064923, 'r_LP_P_normd': array([ 0.55753272, 0.82426831, -0.09868644]), 'target_angle_normd': np.float64(0.7179839245481688)}, 'target_28': {'priority': 0.9282669521531632, 'r_LP_P_normd': array([ 0.62887363, 0.76646723, -0.13056009]), 'target_angle_normd': np.float64(0.7278214487998897)}, 'target_29': {'priority': 0.07379201140065461, 'r_LP_P_normd': array([ 0.83349796, 0.55251892, -0.00199665]), 'target_angle_normd': np.float64(0.7770010755992804)}, 'target_30': {'priority': 0.010627938976362383, 'r_LP_P_normd': array([ 0.87933586, 0.46953401, -0.07941194]), 'target_angle_normd': np.float64(0.7821048162611637)}, 'target_31': {'priority': 0.13642904696262903, 'r_LP_P_normd': array([ 0.90564527, 0.41905752, -0.06478763]), 'target_angle_normd': np.float64(0.7904117166194159)}}
time: 0.0
eclipse: [np.float64(0.7684210526315789), np.float64(0.14210526315789473)]
The simulation runs until either the battery is depleted, a RW exceeds its maximum speed (both considered failures), or a timeout occurs (which simply stops the simulation).
[10]:
total_reward = 0.0
while True:
observation, reward, terminated, truncated, info = env.step(
env.action_space.sample()
)
total_reward += reward
if terminated or truncated:
print("Episode complete.")
break
print("Total reward:", total_reward)
2025-12-03 22:23:09,901 gym INFO <0.00> === STARTING STEP ===
2025-12-03 22:23:09,902 sats.satellite.EO INFO <0.00> EO: target index 13 tasked
2025-12-03 22:23:09,902 sats.satellite.EO INFO <0.00> EO: Target(tgt-804) tasked for imaging
2025-12-03 22:23:09,903 sats.satellite.EO INFO <0.00> EO: Target(tgt-804) window enabled: 1146.2 to 1196.2
2025-12-03 22:23:09,904 sats.satellite.EO INFO <0.00> EO: setting timed terminal event at 1196.2
2025-12-03 22:23:09,905 sats.satellite.EO INFO <0.00> EO: RW Power Fault: RW1's power limit reduced to 1.0 Watts at 0.0 minutes!
2025-12-03 22:23:09,906 sats.satellite.EO INFO <0.50> EO: imaged Target(tgt-804)
2025-12-03 22:23:09,907 data.base INFO <0.50> Total reward: {'EO': 0.7384995398085523}
2025-12-03 22:23:09,907 comm.communication INFO <0.50> Optimizing data communication between all pairs of satellites
2025-12-03 22:23:09,908 sats.satellite.EO INFO <0.50> EO: Satellite EO requires retasking
2025-12-03 22:23:09,913 gym INFO <0.50> Step reward: 0.7384995398085523
2025-12-03 22:23:09,913 gym INFO <0.50> === STARTING STEP ===
2025-12-03 22:23:09,914 sats.satellite.EO INFO <0.50> EO: target index 24 tasked
2025-12-03 22:23:09,914 sats.satellite.EO INFO <0.50> EO: Target(tgt-760) tasked for imaging
2025-12-03 22:23:09,915 sats.satellite.EO INFO <0.50> EO: Target(tgt-760) window enabled: 2273.6 to 2359.5
2025-12-03 22:23:09,916 sats.satellite.EO INFO <0.50> EO: setting timed terminal event at 2359.5
2025-12-03 22:23:09,917 sats.satellite.EO INFO <1.00> EO: imaged Target(tgt-760)
2025-12-03 22:23:09,918 data.base INFO <1.00> Total reward: {'EO': 0.5185496026201819}
2025-12-03 22:23:09,918 comm.communication INFO <1.00> Optimizing data communication between all pairs of satellites
2025-12-03 22:23:09,919 sats.satellite.EO INFO <1.00> EO: Satellite EO requires retasking
2025-12-03 22:23:09,923 gym INFO <1.00> Step reward: 0.5185496026201819
2025-12-03 22:23:09,924 gym INFO <1.00> === STARTING STEP ===
2025-12-03 22:23:09,924 sats.satellite.EO INFO <1.00> EO: target index 5 tasked
2025-12-03 22:23:09,925 sats.satellite.EO INFO <1.00> EO: Target(tgt-97) tasked for imaging
2025-12-03 22:23:09,926 sats.satellite.EO INFO <1.00> EO: Target(tgt-97) window enabled: 482.7 to 557.8
2025-12-03 22:23:09,926 sats.satellite.EO INFO <1.00> EO: setting timed terminal event at 557.8
2025-12-03 22:23:09,928 sats.satellite.EO INFO <1.50> EO: imaged Target(tgt-97)
2025-12-03 22:23:09,929 data.base INFO <1.50> Total reward: {'EO': 0.39915339691165386}
2025-12-03 22:23:09,929 comm.communication INFO <1.50> Optimizing data communication between all pairs of satellites
2025-12-03 22:23:09,930 sats.satellite.EO INFO <1.50> EO: Satellite EO requires retasking
2025-12-03 22:23:09,934 gym INFO <1.50> Step reward: 0.39915339691165386
2025-12-03 22:23:09,934 gym INFO <1.50> === STARTING STEP ===
2025-12-03 22:23:09,935 sats.satellite.EO INFO <1.50> EO: target index 13 tasked
2025-12-03 22:23:09,936 sats.satellite.EO INFO <1.50> EO: Target(tgt-594) tasked for imaging
2025-12-03 22:23:09,937 sats.satellite.EO INFO <1.50> EO: Target(tgt-594) window enabled: 1276.7 to 1383.1
2025-12-03 22:23:09,937 sats.satellite.EO INFO <1.50> EO: setting timed terminal event at 1383.1
2025-12-03 22:23:09,939 sats.satellite.EO INFO <2.00> EO: imaged Target(tgt-594)
2025-12-03 22:23:09,939 data.base INFO <2.00> Total reward: {'EO': 0.602211552115518}
2025-12-03 22:23:09,939 comm.communication INFO <2.00> Optimizing data communication between all pairs of satellites
2025-12-03 22:23:09,940 sats.satellite.EO INFO <2.00> EO: Satellite EO requires retasking
2025-12-03 22:23:09,945 gym INFO <2.00> Step reward: 0.602211552115518
2025-12-03 22:23:09,945 gym INFO <2.00> === STARTING STEP ===
2025-12-03 22:23:09,946 sats.satellite.EO INFO <2.00> EO: target index 2 tasked
2025-12-03 22:23:09,946 sats.satellite.EO INFO <2.00> EO: Target(tgt-38) tasked for imaging
2025-12-03 22:23:09,947 sats.satellite.EO INFO <2.00> EO: Target(tgt-38) window enabled: 354.3 to 376.5
2025-12-03 22:23:09,947 sats.satellite.EO INFO <2.00> EO: setting timed terminal event at 376.5
2025-12-03 22:23:09,949 sats.satellite.EO INFO <2.50> EO: imaged Target(tgt-38)
2025-12-03 22:23:09,949 data.base INFO <2.50> Total reward: {'EO': 0.6931851990942818}
2025-12-03 22:23:09,950 comm.communication INFO <2.50> Optimizing data communication between all pairs of satellites
2025-12-03 22:23:09,950 sats.satellite.EO INFO <2.50> EO: Satellite EO requires retasking
2025-12-03 22:23:09,955 gym INFO <2.50> Step reward: 0.6931851990942818
2025-12-03 22:23:09,955 gym INFO <2.50> === STARTING STEP ===
2025-12-03 22:23:09,956 sats.satellite.EO INFO <2.50> EO: target index 25 tasked
2025-12-03 22:23:09,957 sats.satellite.EO INFO <2.50> EO: Target(tgt-146) tasked for imaging
2025-12-03 22:23:09,957 sats.satellite.EO INFO <2.50> EO: Target(tgt-146) window enabled: 2874.9 to 2909.4
2025-12-03 22:23:09,958 sats.satellite.EO INFO <2.50> EO: setting timed terminal event at 2909.4
2025-12-03 22:23:09,959 sats.satellite.EO INFO <3.00> EO: imaged Target(tgt-146)
2025-12-03 22:23:09,960 data.base INFO <3.00> Total reward: {'EO': 0.010627938976362383}
2025-12-03 22:23:09,961 comm.communication INFO <3.00> Optimizing data communication between all pairs of satellites
2025-12-03 22:23:09,961 sats.satellite.EO INFO <3.00> EO: Satellite EO requires retasking
2025-12-03 22:23:09,966 gym INFO <3.00> Step reward: 0.010627938976362383
2025-12-03 22:23:09,967 gym INFO <3.00> === STARTING STEP ===
2025-12-03 22:23:09,967 sats.satellite.EO INFO <3.00> EO: target index 4 tasked
2025-12-03 22:23:09,968 sats.satellite.EO INFO <3.00> EO: Target(tgt-378) tasked for imaging
2025-12-03 22:23:09,968 sats.satellite.EO INFO <3.00> EO: Target(tgt-378) window enabled: 564.0 to 650.0
2025-12-03 22:23:09,969 sats.satellite.EO INFO <3.00> EO: setting timed terminal event at 650.0
2025-12-03 22:23:09,970 sats.satellite.EO INFO <3.50> EO: imaged Target(tgt-378)
2025-12-03 22:23:09,971 data.base INFO <3.50> Total reward: {'EO': 0.3659991252731889}
2025-12-03 22:23:09,971 comm.communication INFO <3.50> Optimizing data communication between all pairs of satellites
2025-12-03 22:23:09,972 sats.satellite.EO INFO <3.50> EO: Satellite EO requires retasking
2025-12-03 22:23:09,976 gym INFO <3.50> Step reward: 0.3659991252731889
2025-12-03 22:23:09,977 gym INFO <3.50> === STARTING STEP ===
2025-12-03 22:23:09,977 sats.satellite.EO INFO <3.50> EO: target index 1 tasked
2025-12-03 22:23:09,978 sats.satellite.EO INFO <3.50> EO: Target(tgt-634) tasked for imaging
2025-12-03 22:23:09,978 sats.satellite.EO INFO <3.50> EO: Target(tgt-634) window enabled: 214.4 to 324.0
2025-12-03 22:23:09,979 sats.satellite.EO INFO <3.50> EO: setting timed terminal event at 324.0
2025-12-03 22:23:09,980 sats.satellite.EO INFO <4.00> EO: imaged Target(tgt-634)
2025-12-03 22:23:09,981 data.base INFO <4.00> Total reward: {'EO': 0.1011278274566988}
2025-12-03 22:23:09,981 comm.communication INFO <4.00> Optimizing data communication between all pairs of satellites
2025-12-03 22:23:09,981 sats.satellite.EO INFO <4.00> EO: Satellite EO requires retasking
2025-12-03 22:23:09,986 gym INFO <4.00> Step reward: 0.1011278274566988
2025-12-03 22:23:09,987 gym INFO <4.00> === STARTING STEP ===
2025-12-03 22:23:09,988 sats.satellite.EO INFO <4.00> EO: target index 17 tasked
2025-12-03 22:23:09,988 sats.satellite.EO INFO <4.00> EO: Target(tgt-533) tasked for imaging
2025-12-03 22:23:09,989 sats.satellite.EO INFO <4.00> EO: Target(tgt-533) window enabled: 2225.7 to 2339.0
2025-12-03 22:23:09,990 sats.satellite.EO INFO <4.00> EO: setting timed terminal event at 2339.0
2025-12-03 22:23:09,991 sats.satellite.EO INFO <4.50> EO: imaged Target(tgt-533)
2025-12-03 22:23:09,992 data.base INFO <4.50> Total reward: {'EO': 0.11836853522372437}
2025-12-03 22:23:09,992 comm.communication INFO <4.50> Optimizing data communication between all pairs of satellites
2025-12-03 22:23:09,993 sats.satellite.EO INFO <4.50> EO: Satellite EO requires retasking
2025-12-03 22:23:09,997 gym INFO <4.50> Step reward: 0.11836853522372437
2025-12-03 22:23:09,997 gym INFO <4.50> === STARTING STEP ===
2025-12-03 22:23:09,998 sats.satellite.EO INFO <4.50> EO: target index 10 tasked
2025-12-03 22:23:09,998 sats.satellite.EO INFO <4.50> EO: Target(tgt-12) tasked for imaging
2025-12-03 22:23:09,999 sats.satellite.EO INFO <4.50> EO: Target(tgt-12) window enabled: 1488.7 to 1592.6
2025-12-03 22:23:09,999 sats.satellite.EO INFO <4.50> EO: setting timed terminal event at 1592.6
2025-12-03 22:23:10,068 sim.simulator INFO <304.50> Max step duration reached
2025-12-03 22:23:10,068 data.base INFO <304.50> Total reward: {}
2025-12-03 22:23:10,069 comm.communication INFO <304.50> Optimizing data communication between all pairs of satellites
2025-12-03 22:23:10,074 sats.satellite.EO WARNING <304.50> EO: failed rw_speeds_valid check
2025-12-03 22:23:10,074 gym INFO <304.50> Step reward: 0.0
2025-12-03 22:23:10,075 gym INFO <304.50> Episode terminated: True
2025-12-03 22:23:10,075 gym INFO <304.50> Episode truncated: False
Episode complete.
Total reward: 3.5477227174801618