Learning from demonstration (LfD) enables a robot to emulate natural human movement instead of merely executing preprogrammed behaviors. This article presents a hierarchical LfD structure of task-parameterized models for object movement tasks, which are ubiquitous in everyday life and could benefit from robotic support. Our approach uses the task-parameterized Gaussian mixture model (TP-GMM) algorithm to encode sets of demonstrations in separate models that each correspond to a different task situation. The robot then maximizes its expected performance in a new situation by either selecting a good existing model or requesting new demonstrations. Compared to a standard implementation that encodes all demonstrations together for all test situations, the proposed approach offers four advantages. First, a simply defined distance function can be used to estimate test performance by calculating the similarity between a test situation and the existing models. Second, the proposed approach can improve generalization, e.g., better satisfying the demonstrated task constraints and speeding up task execution. Third, because the hierarchical structure encodes each demonstrated situation individually, a wider range of task situations can be modeled in the same framework without deteriorating performance. Last, adding or removing demonstrations incurs low computational load, and thus, the robot's skill library can be built incrementally. We first instantiate the proposed approach in a simulated task to validate these advantages. We then show that the advantages transfer to real hardware for a task where naive participants collaborated with a Willow Garage PR2 robot to move a handheld object. For most tested scenarios, our hierarchical method achieved significantly better task performance and subjective ratings than both a passive model with only gravity compensation and a single TP-GMM encoding all demonstrations.
This paper introduces a new device for gait rehabilitation, the gait propulsion trainer (GPT). It consists of two main components (a stationary device and a wearable system) that work together to apply periodic stance-phase resistance as the user walks overground. The stationary device provides the resistance forces via a cable that tethers the user’s pelvis to a magnetic-particle brake. The wearable system detects gait events via foot switches to control the timing of the resistance forces. A hardware verification test confirmed that the GPT functions as intended. We conducted a pilot study in which one healthy adult and one stroke survivor walked with the GPT with increasing resistance levels. As hypothesized, the periodic stance-phase resistance caused the healthy participant to walk asymmetrically, with greatly reduced propulsion impulse symmetry; as GPT resistance increased, the walking speed also decreased, and the propulsion impulse appeared to increase for both legs. In contrast, the stroke participant responded to GPT resistance by walking faster and more symmetrically in terms of both propulsion impulse and step length. Thus, this paper shows promising results of short-term training with the GPT, and more studies will follow to explore its long-term effects on hemiparetic gait.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.