API Documentation¶

This is the detailed documentation of all public classes and functions. You can also search for specific modules, classes, or functions in the Index.

`movement_primitives.dmp`¶

Dynamical Movement Primitive (DMP)¶

This module provides implementations of various DMP types. DMPs consist of a goal-directed movement generated by the transformation system and a forcing term that defines the shape of the trajectory. They are time-dependent and usually converge to the goal after a constant execution time.

Every implementation is slightly different, but we use a similar notation for all of them:

\(y,\dot{y},\ddot{y}\) - position, velocity, and acceleration; these might be translation components only, orientation, or both
\(y_0\) - start position
\(g\) - goal of the movement (attractor of the DMP)
\(\tau\) - execution time
\(z\) - phase variable, starts at 1 and converges to 0
\(f(z)\) - forcing term, learned component that defines the shape of the movement
\(C_t\) - coupling term that is added to the acceleration of the DMP

`DMP`(n_dims[, execution_time, dt, ...])	Dynamical movement primitive (DMP).
`DMPWithFinalVelocity`(n_dims[, ...])	Dynamical movement primitive (DMP) with final velocity.
`CartesianDMP`([execution_time, dt, ...])	Cartesian dynamical movement primitive.
`DualCartesianDMP`([execution_time, dt, ...])	Dual cartesian dynamical movement primitive.
`DMPBase`(n_pos_dims, n_vel_dims)	Base class of Dynamical Movement Primitives (DMPs).
`WeightParametersMixin`()	Mixin class providing common access methods to forcing term weights.
`CouplingTermPos1DToPos1D`(desired_distance, lf)	Couples position components of a 2D DMP with a virtual spring.
`CouplingTermObstacleAvoidance2D`(...[, ...])	Coupling term for obstacle avoidance in 2D.
`CouplingTermObstacleAvoidance3D`(...[, ...])	Coupling term for obstacle avoidance in 3D.
`CouplingTermPos3DToPos3D`(desired_distance, lf)	Couples position components of a 6D DMP with a virtual spring in 3D.
`CouplingTermDualCartesianPose`(...[, ...])	Couples relative poses of dual Cartesian DMP.
`CouplingTermObstacleAvoidance3D`(...[, ...])	Coupling term for obstacle avoidance in 3D.
`CouplingTermDualCartesianDistance`(...[, k, ...])	Couples distance between 3D positions of a dual Cartesian DMP.
`CouplingTermDualCartesianTrajectory`(offset, ...)	Couples relative pose in dual Cartesian DMP with a given trajectory.

`dmp_transformation_system`(Y, V, alpha_y, ...)	Compute acceleration generated by transformation system of DMP.
`canonical_system_alpha`(goal_z, goal_t, start_t)	Compute parameter alpha of canonical system.
`phase`(t, alpha, goal_t, start_t[, int_dt, eps])	Map time to phase.
`obstacle_avoidance_acceleration_2d`(y, yd, ...)	Compute acceleration for obstacle avoidance in 2D.
`obstacle_avoidance_acceleration_3d`(y, yd, ...)	Compute acceleration for obstacle avoidance in 3D.

`movement_primitives.promp`¶

Probabilistic Movement Primitive (ProMP)¶

ProMPs represent distributions of trajectories.

ProMP(n_dims[, n_weights_per_dim])

Probabilistic Movement Primitive (ProMP).

`movement_primitives.io`¶

Input / Output¶

Input and output from and to files of movement primitives.

`write_pickle`(filename, obj)	Write object to pickle format.
`read_pickle`(filename)	Read object from pickle format.
`write_yaml`(filename, obj)	Write object to YAML format.
`read_yaml`(filename)	Read object from YAML format.
`write_json`(filename, obj)	Write object to JSON format.
`read_json`(filename)	Read object from JSON format.

`movement_primitives.base`¶

Base Classes¶

Base classes of movement primitives.

PointToPointMovement(n_pos_dims, n_vel_dims)

Base class for point to point movements (discrete motions).

`movement_primitives.data`¶

Data¶

Tools for loading datasets.

`load_lasa`(shape_idx)	Load demonstrations from LASA dataset.
`generate_minimum_jerk`(start, goal[, ...])	Create a minimum jerk trajectory.
`generate_1d_trajectory_distribution`(n_demos, ...)	Generates toy data for testing and demonstration.

`movement_primitives.kinematics`¶

Kinematics¶

Forward kinematics and a simple implementation of inverse kinematics.

`Kinematics`(urdf[, mesh_path])	Robot kinematics.
`Chain`(tm, joint_names, base_frame, ee_frame)	Kinematic chain.

`movement_primitives.plot`¶

Plotting Tools¶

Tools for plotting multi-dimensional trajectories.

`plot_trajectory_in_rows`(trajectory[, t, ...])	Plot trajectories of N dimensions in N 2D subplots.
`plot_distribution_in_rows`(mean, std_dev[, ...])	Plot distribution of N dimensions in N 2D subplots.

`movement_primitives.visualization`¶

Visualization Tools¶

3D visualization tools for movement primitives.

`plot_pointcloud`(fig, pcl_points, color[, ...])	Plot point cloud.
`to_ellipsoid`(mean, cov)	Compute error ellipsoid.

`movement_primitives.dmp_potential_field`¶

Potential Field of DMP¶

Visualization of DMP as potential field.

plot_potential_field_2d(ax, dmp, x_range, ...)

Plot 2D potential field of a DMP.

`movement_primitives.spring_damper`¶

Spring-Damper Based Attractors¶

Spring-damper based attractors are the basis of a DMP’s transformation system.

`SpringDamper`(n_dims[, dt, k, c, int_dt])	Spring-damper system.
`SpringDamperOrientation`([dt, k, c, int_dt])	Spring-damper system for quaternions.