Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.onyx-robotics.com/llms.txt

Use this file to discover all available pages before exploring further.

from onyxengine.modeling import Input

feature = Input(
    name: str,
    dataset_feature: Optional[str] = None,
    scale: Union[None, Literal['mean'], List[float]] = 'mean',
    parent: Optional[str] = None,
    relation: Optional[Literal['equal', 'delta', 'derivative']] = None
)
Defines an input feature for the model, including state relationships for simulation.

​
Parameters

​
name
str
required
Name of the input feature. Used for dictionary access in simulate().
​
dataset_feature
str
default:"None"
Column name in the dataset. If None, uses name.
​
scale
Union[None, 'mean', List[float]]
default:"mean"
Scaling method:
  • 'mean': Normalize to zero mean, unit std (default)
  • None: No scaling
  • [min, max]: Scale from range to [-1, 1]
​
parent
str
default:"None"
Parent feature name for derived inputs. Required if relation is set.
​
relation
Literal
default:"None"
Relationship to parent for state updates during simulation:
  • 'derivative': input[t+1] = input[t] + parent[t] * dt
  • 'delta': input[t+1] = input[t] + parent[t]
  • 'equal': input[t+1] = parent[t]
  • None: External input (no state update)

​
Input Types

​
External Input

Inputs without a parent are “external inputs” - known values at each timestep: 
Input(name='control_input')
Input(name='motor_torque')
Input(name='disturbance')

​
State Input

Inputs with a parent are “states” - values that update during simulation: 
# Velocity integrates acceleration
Input(name='velocity', parent='acceleration', relation='derivative')

# Position integrates velocity
Input(name='position', parent='velocity', relation='derivative')

​
Examples

​
Basic State-Space Model

from onyxengine.modeling import Input, Output

outputs = [Output(name='acceleration')]
inputs = [
    # States (derived from outputs)
    Input(name='velocity', parent='acceleration', relation='derivative'),
    Input(name='position', parent='velocity', relation='derivative'),
    # External input
    Input(name='force'),
]

​
Custom Dataset Column Name

# Feature named 'velocity' maps to 'encoder_vel' in dataset
Input(
    name='velocity',
    dataset_feature='encoder_vel',
    parent='acceleration',
    relation='derivative'
)

​
Custom Scaling

# Scale torque from [-10, 10] Nm to [-1, 1]
Input(name='torque', scale=[-10, 10])

# No scaling for normalized data
Input(name='normalized_signal', scale=None)

​
State Chain

# Higher-order system: jerk → acceleration → velocity → position
outputs = [Output(name='jerk')]
inputs = [
    Input(name='acceleration', parent='jerk', relation='derivative'),
    Input(name='velocity', parent='acceleration', relation='derivative'),
    Input(name='position', parent='velocity', relation='derivative'),
    Input(name='control'),
]

​
Validation

  • If relation is set, parent must also be set
  • If parent is set, relation must also be set
  • Parent must reference an existing Output or Input name