An Adaptive Framework for Manipulator Skill Reproduction in Dynamic Environments

Robot skill learning and execution in uncertain and dynamic environments is a challenging task. This paper proposes an adaptive framework that combines Learning from Demonstration (LfD), environment state prediction, and high-level decision making. Proactive adaptation prevents the need for reactive...

Full description

Saved in:
Bibliographic Details
Published in2024 21st International Conference on Ubiquitous Robots (UR) pp. 498 - 503
Main Authors Donald, Ryan, Hertel, Brendan, Misenti, Stephen, Yan, G., Azadeh, Reza
Format Conference Proceeding
LanguageEnglish
Published IEEE 24.06.2024
Subjects
Decision making
Hidden Markov models
Kalman filters
Manipulator dynamics
Shape
Task analysis
Trajectory
Online AccessGet full text

Cover

More Information
Summary:Robot skill learning and execution in uncertain and dynamic environments is a challenging task. This paper proposes an adaptive framework that combines Learning from Demonstration (LfD), environment state prediction, and high-level decision making. Proactive adaptation prevents the need for reactive adaptation, which lags behind changes in the environment rather than anticipating them. We propose a novel LfD representation, Elastic-Laplacian Trajectory Editing (ELTE), which continuously adapts the trajectory shape to predictions of future states. Then, a high-level reactive system using an Unscented Kalman Filter (UKF) and Hidden Markov Model (HMM) prevents unsafe execution in the current state of the dynamic environment based on a discrete set of decisions. We first validate our LfD representation in simulation, then experimentally assess the entire framework using a legged mobile manipulator in 36 real-world scenarios. We show the ef-fectiveness of the proposed framework under different dynamic changes in the environment. Our results show that the proposed framework produces robust and stable adaptive behaviors.
DOI:10.1109/UR61395.2024.10597445