Using BAM in MuJoCo (CPU)#
This page explains how to plug BAM friction models into a standard MuJoCo
simulation running on CPU. The entry point is bam.mujoco.MujocoController.
Installation#
BAM is available on PyPI. Install it with the mujoco extra to pull in the
MuJoCo dependency:
pip install better-actuator-models[mujoco]
Overview#
At each simulation step, MujocoController does three things:
Optionally lowers the supply voltage by a drop proportional to the previous step’s load, to model battery + cable resistance.
Computes the motor torque from a firmware-like P-controller — optionally clipping it to the firmware current limit — and applies it via
mj_data.ctrl.Evaluates the BAM friction model and writes the result into
mj_model.dof_frictionlossandmj_model.dof_damping.
Loading a model#
Use bam.model.load_model() to obtain a Model object.
Two approaches are available.
Bundled motor — the library ships identified parameters for a set of common servos:
from bam.model import load_model
model = load_model(motor_name="xl330", model="m6")
Supported motor names: "xl320", "xl330", "mx106", "mx64",
"erob80:50", "erob80:100".
Supported model variants: "m1" through "m6" (see Friction Models (M1-M6)).
Custom JSON — parameters produced by your own identification run:
model = load_model("path/to/params.json")
XML setup#
Each actuator must be declared as a motor in the MJCF file (not
position or velocity). BAM overwrites frictionloss, damping,
and armature at runtime, so any value set in the XML will be ignored.
<actuator>
<motor name="joint_1" joint="joint_1" gear="1"/>
...
<motor name="joint_n" joint="joint_n" gear="1"/>
</actuator>
Instantiating the controller#
import mujoco
from bam.mujoco import MujocoController
mj_model = mujoco.MjModel.from_xml_file("robot.xml")
mj_data = mujoco.MjData(mj_model)
controller = MujocoController(
model=model,
actuator=["joint_1", ..., "joint_n"], # must match the motor name in the XML
mujoco_model=mj_model,
mujoco_data=mj_data,
)
The actuator argument can take a single string or a list of strings, which
allows the same motor model to drive multiple joints. Each string must
match the name attribute of the <motor>.
Simulation loop#
Inside the loop, call set_q_target() to
provide the desired joint angle, then update()
before every mj_step:
mujoco.mj_resetData(mj_model, mj_data)
controller.reset(mj_data.qpos)
joint_names = ["joint_1", ..., "joint_n"]
target_angles = [...]
while True:
for joint_name, target_angle in zip(joint_names, target_angles):
controller.set_q_target(joint_name, target_angle)
controller.update()
mujoco.mj_step(mj_model, mj_data)
reset() should be called after every
mj_resetData to clear the internal velocity and torque state.
Voltage drop (optional)#
Real batteries and cables introduce a voltage drop proportional to the total current draw. BAM models this as:
where \(g_\text{drop}\) is vin_drop_gain (approximately
\(R / K_t\)) and the sum runs over all controlled joints.
A hard lower bound vin_min can be set to prevent the effective voltage
from collapsing under heavy load:
controller = MujocoController(
model=model,
actuator=["joint_1", ..., "joint_n"],
mujoco_model=mj_model,
mujoco_data=mj_data,
vin_drop_gain=0.5, # [V/Nm]
vin_min=6.0, # [V]
)
Current clipping (optional)#
Servo firmwares can cap the motor current to protect the hardware. BAM reproduces
this saturation with the max_current parameter: the motor current
\(I = \tau / K_t\) is clipped to [-max_current, max_current], which is
equivalent to clipping the motor torque to \(\pm\,\texttt{max\_current}\cdot K_t\).
controller = MujocoController(
model=model,
actuator=["joint_1", ..., "joint_n"],
mujoco_model=mj_model,
mujoco_data=mj_data,
max_current=1.75, # firmware current limit [A]
)
Leave it at None (default) to disable current clipping.
Multi-actuator config file#
For robots with many joints, bam.mujoco.load_config() loads a JSON
configuration file that maps each group of joints to a model:
from bam.mujoco import load_config
controllers, dof_to_controller = load_config(
path="config.json",
mujoco_model=mj_model,
mujoco_data=mj_data,
kp=125.0,
vin=7.5,
)
The config file has the following structure:
{
"arm": {
"dofs": ["shoulder", "elbow"],
"model": {
"kt": 1.6224667906987444,
"R": 3.949433673232461,
"armature": 0.011951238325312509,
"friction_base": 0.09038677246291783,
"friction_viscous": 0.011691602145974832,
"model": "m1",
"actuator": "mx64"
},
"error_gain": 1.0,
"max_pwm": 885
},
"leg": {
"dofs": ["hip", "knee", "ankle"],
"model": {
"kt": 2.1913757006745245,
"R": 2.9649903987776804,
"armature": 0.026609234235148084,
"friction_base": 0.10352026623606064,
"friction_viscous": 0.03520238029013507,
"model": "m1",
"actuator": "mx106"
},
"error_gain": 1.0,
"max_pwm": 885
}
}
controllers is a dict keyed by group name; dof_to_controller maps each
DOF name back to its group.