Generalizable Motion Policies through Keypoint Parameterization and Transportation Maps

TL;DR

This paper introduces a novel method for robot policy generalization using keypoint parameterization and transportation maps, enabling robots to adapt learned tasks to new situations with minimal demonstrations.

Contribution

It proposes a new task parameterization technique that tracks keypoints and employs nonlinear transformations with Gaussian Processes for effective policy transfer and uncertainty estimation.

Findings

Outperforms state-of-the-art task parameterization methods.

Successfully applied to various robot manipulation tasks.

Provides uncertainty estimates for policy generalization.

Abstract

Learning from Interactive Demonstrations has revolutionized the way non-expert humans teach robots. It is enough to kinesthetically move the robot around to teach pick-and-place, dressing, or cleaning policies. However, the main challenge is correctly generalizing to novel situations, e.g., different surfaces to clean or different arm postures to dress. This article proposes a novel task parameterization and generalization to transport the original robot policy, i.e., position, velocity, orientation, and stiffness. Unlike the state of the art, only a set of keypoints is tracked during the demonstration and the execution, e.g., a point cloud of the surface to clean. We then propose to fit a nonlinear transformation that would deform the space and then the original policy using the paired source and target point sets. The use of function approximators like Gaussian Processes allows us to generalize, or transport, the policy from every space location while estimating the uncertainty of the resulting policy due to the limited task keypoints and the reduced number of demonstrations. We compare the algorithm's performance with state-of-the-art task parameterization alternatives and analyze the effect of different function approximators. We also validated the algorithm on robot manipulation tasks, i.e., different posture arm dressing, different location product reshelving, and different shape surface cleaning.