pid

Torch-based PID controllers for batched simulation.

类：

名称	描述
PID	Vectorized PID controller for multiple environments.
FlightController	PID flight controller (batched).
TrackController	PID track controller (batched).

PID

PID(Kp: Tensor, Ki: Tensor | None = None, Kd: Tensor | None = None, dt: float = 0.01, N: float = 100.0, integral_limit: Tensor | None = None, num_envs: int = 1)

Vectorized PID controller for multiple environments.

Initialize PID gains and state tensors.

参数：

名称	类型	描述	默认
Kp	Tensor	Proportional gain tensor with a leading environment dimension.	必需
Ki	Tensor | None	Integral gain tensor with the same shape as Kp.	None
Kd	Tensor | None	Derivative gain tensor with the same shape as Kp.	None
dt	float	Controller time step.	0.01
N	float	First-order derivative filter coefficient.	100.0
integral_limit	Tensor | None	Optional clamp applied elementwise to the integral state.	None
num_envs	int	Number of environments.	1

方法：

名称	描述
reset	Reset PID state for selected environments.
update	Compute PID output for the given error tensor.

reset

reset(env_ids: slice | Sequence[int] | Tensor) -> None

Reset PID state for selected environments.

参数：

名称	类型	描述	默认
env_ids	slice | Sequence[int] | Tensor	Indices or slice selecting which environments to reset.	必需

update

update(error: Tensor) -> torch.Tensor

Compute PID output for the given error tensor.

参数：

名称	类型	描述	默认
error	Tensor	Batched control error tensor compatible with the internal state shape determined from Kp.	必需

返回：

类型	描述
Tensor	torch.Tensor: Combined P+I+D control output.

FlightController

FlightController(params: VehicleParams = VehicleParams(), control_mask: dict | None = None, gains: dict | None = None, limits: dict | None = None, num_envs: int = 1, device: str | device = 'cpu')

Bases: ControllerBase

PID flight controller (batched).

Initialize the batched flight PID controller.

方法：

名称	描述
randomize	Randomize configured PID gains, controller limits, and physical params.
reset	Reset PID loops for selected environments.
update	Update controller.
gains_to_randomization_ranges	Convert static gains dict to domain randomization min/max ranges.

属性：

名称	类型	描述
params	VehicleParams	Vehicle parameters for the controller.

params instance-attribute

params: VehicleParams = params

Vehicle parameters for the controller.

randomize

randomize(env_ids=None, gains=None, limits=None, params=None)

Randomize configured PID gains, controller limits, and physical params.

reset

reset(env_ids)

Reset PID loops for selected environments.

update

update(target: dict, state: dict) -> torch.Tensor

Update controller.

参数：

名称	类型	描述	默认
target	dict	dict with batched tensors, keys matching mask.	必需
state	dict	dict: pos(N,3), vel(N,3), att_euler(N,3), ang_vel(N,3).	必需

返回：

名称	类型	描述
Tensor	(N, 4)	[thrust, roll_moment, pitch_moment, yaw_moment].

gains_to_randomization_ranges classmethod

gains_to_randomization_ranges(gains=None, scale=0.2)

Convert static gains dict to domain randomization min/max ranges.

Each non-zero gain is scaled by (1-scale) for min and (1+scale) for max. Defaults to cls.DEFAULT_GAINS when gains is None.

TrackController

TrackController(params: VehicleParams = VehicleParams(), control_mask: dict | None = None, gains: dict | None = None, num_envs: int = 1, device: str | device = 'cpu')

Bases: ControllerBase

PID track controller (batched).

Initialize the batched track controller.

方法：

名称	描述
randomize	Randomize configured PID gains for all or selected environments.
reset	Reset PID loops for selected environments.
update	Update controller.

属性：

名称	类型	描述
params	VehicleParams	Vehicle parameters for the controller.

params instance-attribute

params: VehicleParams = params

Vehicle parameters for the controller.

randomize

randomize(env_ids=None, gains=None)

Randomize configured PID gains for all or selected environments.

reset

reset(env_ids)

Reset PID loops for selected environments.

update

update(target: dict, state: dict) -> torch.Tensor

Update controller.

参数：

名称	类型	描述	默认
target	dict	dict: pos(N,3), vel_b(N,3), att_euler(N,3), ang_vel(N,3). Only pos[:,:2], vel_b[:,0], att_euler[:,2], ang_vel[:,2] are used.	必需
state	dict	dict with same keys.	必需

返回：

名称	类型	描述
Tensor	(N, 2)	left/right acceleration commands.