Learning to Pick at Non-Zero-Velocity from Interactive Demonstrations

TL;DR

This paper presents a framework enabling non-expert users to teach a robot complex pick-and-place motions through interactive corrections, leveraging Gaussian Processes for reactive, adaptable, and efficient task learning from demonstrations.

Contribution

It introduces a Gaussian Process-based method for learning pick-and-place dynamics that supports online corrections and active disturbance rejection, improving ease of teaching and adaptability.

Findings

Effective learning of pick-and-place tasks demonstrated on a Franka-Emika Panda

Framework allows quick policy corrections for environmental changes

Non-expert users find the system usable and intuitive

Abstract

This work investigates how the intricate task of a continuous pick & place (P&P) motion may be learned from humans based on demonstrations and corrections. Due to the complexity of the task, these demonstrations are often slow and even slightly flawed, particularly at moments when multiple aspects (i.e., end-effector movement, orientation, and gripper width) have to be demonstrated at once. Rather than training a person to give better demonstrations, non-expert users are provided with the ability to interactively modify the dynamics of their initial demonstration through teleoperated corrective feedback. This in turn allows them to teach motions outside of their own physical capabilities. In the end, the goal is to obtain a faster but reliable execution of the task. The presented framework learns the desired movement dynamics based on the current Cartesian position with Gaussian Processes (GPs), resulting in a reactive, time-invariant policy. Using GPs also allows online interactive corrections and active disturbance rejection through epistemic uncertainty minimization. The experimental evaluation of the framework is carried out on a Franka-Emika Panda. Tests were performed to determine i) the framework's effectiveness in successfully learning how to quickly pick & place an object, ii) ease of policy correction to environmental changes (i.e., different object sizes and mass), and iii) the framework's usability for non-expert users.