TrueAdapt: Learning Smooth Online Trajectory Adaptation with Bounded Jerk, Acceleration and Velocity in Joint Space

Jonas C. Kiemel* (Corresponding Author), Robin Weitemeyer, Pascal Meißner, Torsten Kröger

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

Abstract

We present TrueAdapt, a model-free method to learn online adaptations of robot trajectories based on their effects on the environment. Given sensory feedback and future waypoints of the original trajectory, a neural network is trained to predict joint accelerations at regular intervals. The adapted trajectory is generated by linear interpolation of the predicted accelerations, leading to continuously differentiable joint velocities and positions. Bounded jerks, accelerations and velocities are guaranteed by calculating the valid acceleration range at each decision step and clipping the network's output accordingly. A deviation penalty during the training process causes the adapted trajectory to follow the original one. Smooth movements are encouraged by penalizing high accelerations and jerks. We evaluate our approach by training a simulated KUKA iiwa robot to balance a ball on a plate while moving and demonstrate that the balancing policy can be directly transferred to a real robot with little impact on performance.
Original languageEnglish
Title of host publicationIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages5387-5394
Number of pages8
ISBN (Electronic)978-1-7281-6212-6
ISBN (Print)978-1-7281-6213-3
DOIs
Publication statusPublished - 1 Mar 2021
Event2020 IEEE/RSJ International
Conference on Intelligent Robots
and Systems (IROS 2020)
- Las Vegas, United States
Duration: 25 Oct 202029 Oct 2020

Publication series

NameProceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems
PublisherIEEE
ISSN (Print)2153-0858
ISSN (Electronic)2153-0858

Conference

Conference2020 IEEE/RSJ International
Conference on Intelligent Robots
and Systems (IROS 2020)
Abbreviated titleIROS 2020
Country/TerritoryUnited States
CityLas Vegas
Period25/10/2029/10/20

Keywords

  • cs.RO

Fingerprint

Dive into the research topics of 'TrueAdapt: Learning Smooth Online Trajectory Adaptation with Bounded Jerk, Acceleration and Velocity in Joint Space'. Together they form a unique fingerprint.

Cite this