Probabilistic progress prediction and sequencing of concurrent movement primitives

Abstract

Abstract-Classical approaches towards learning coordinated movement tasks often represent a movement in a sequential and exclusive fashion. Introducing concurrency allows to decompose such tasks into a number of separate sequences, for instance for two different end-effectors. While this results in a compact and generic representation of the individual movement primitives (MPs), it is a hard problem to learn their temporal and causal organization. This paper presents a concept for learning movement tasks that require the coordination of several controlled effectors of a robot. We firstly introduce a concept to learn and estimate the progress of individual MPs from a low number of demonstrations. Secondly, we propose a representation of the task that incorporates several concurrent sequences of MPs. Combining these two elements allows to learn and reproduce coordinated bi-manual movement tasks robustly. The synchronization of the concurrent MPs is achieved implicitly using the progress prediction. The approach is evaluated in two simulation studies with a 25 degrees of freedom two-arm robot performing a pick-and-place task.

Interactive Imitation Learning of Bimanual Movement Primitives

“…The advantage of such approaches is that the sequencing provides an implicit synchronization on a higher level, making the lower level problem easier. A common approach for this scheme is to learn policies for performing predefined subtasks, and a higher level policy that creates a sequence from demonstrations [20], [21]. Alternatively, the task can have a predefined structure of subtasks based on heuristics, and synchrony is achieved with a subtask scheduler [22].…”

Incremental Learning Robot Task Representation and Identification

“…Compared to the traditional robot control scheme [18,23], robots Learning from human demonstrations has become mainstream for complex task descriptions [1,3]. Generally, in order to effectively learn and generalize the robot's manipulation tasks, the tasks are often divided into multiple segments of movement primitives for learning [4,6], and thereafter the tasks are described by stitching or serializing different movement primitives [7][8][9]. Therefore, the learning methods of robot movement primitives mainly include the following four categories [12,13]: Probabilistic movement primitives, dynamic movement primitives (DMPs), and probabilistic movements based on a Guassian Mixture Model (GMM).…”

“…The classifier constituted by the target, and finally selects the motion primitive to be executed next in the way of classification. Manschitz et al [4,9,30,32] proposed a method for learning task manipulation graphs from Kinesthetic Teaching, and learned the conversion probability between various motion primitives from the experience of multiple teachings. The method is successfully applied to the task of unscrewing a light bulb by a multi-step robot.…”

One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks

“…Like these prior works, we build upon the notion that each primitive has its own policy, aiming to construct a sequence of policies, each with a learned termination condition. Similar to Manschitz et al [29], we learn the termination condition by predicting the phase of a primitive skill. Unlike these approaches, we consider the problem of learning an end-toend visuomotor policy (pixels to end-effector velocities) from a single video of a human performing a task, while leveraging visual demonstration data from primitives performed with previous objects.…”