upkie 9.0.0
Open-source wheeled biped robots
|
Model lag by applying a low-pass filter to the action of an environment. More...
Public Member Functions | |
def | __init__ (self, env, Union[float, gym.spaces.Box] time_constant) |
Initialize wrapper. More... | |
def | reset (self, **kwargs) |
Reset the environment. More... | |
Tuple[np.ndarray, float, bool, bool, dict] | step (self, np.ndarray action) |
Step the environment. More... | |
Model lag by applying a low-pass filter to the action of an environment.
Note that there is a difference between "delay" and "lag":
output(t + delay) = input(t)
.d/dt{output}(t) = lag * (input(t) - output(t))
.In this wrapper, we model lag where the output (action forward to the wrapped environment) is a low-pass filtered version of the input (action passed to step
).