Fast target prediction of human reaching motion for cooperative human-robot manipulation tasks using time series classification
Interest in human-robot coexistence, in which humans and robots share a common work volume, is increasing in manufacturing environments. Efficient work coordination requires both awareness of the human pose and a plan of action for both human and robot agents in order to compute robot motion traject...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2017
|
| Online Access: | http://hdl.handle.net/1721.1/106656 https://orcid.org/0000-0002-1999-7395 https://orcid.org/0000-0003-1338-8107 |
| _version_ | 1826216616210202624 |
|---|---|
| author | Perez D'Arpino, Claudia Shah, Julie A |
| author2 | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics |
| author_facet | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Perez D'Arpino, Claudia Shah, Julie A |
| author_sort | Perez D'Arpino, Claudia |
| collection | MIT |
| description | Interest in human-robot coexistence, in which humans and robots share a common work volume, is increasing in manufacturing environments. Efficient work coordination requires both awareness of the human pose and a plan of action for both human and robot agents in order to compute robot motion trajectories that synchronize naturally with human motion. In this paper, we present a data-driven approach that synthesizes anticipatory knowledge of both human motions and subsequent action steps in order to predict in real-time the intended target of a human performing a reaching motion. Motion-level anticipatory models are constructed using multiple demonstrations of human reaching motions. We produce a library of motions from human demonstrations, based on a statistical representation of the degrees of freedom of the human arm, using time series analysis, wherein each time step is encoded as a multivariate Gaussian distribution. We demonstrate the benefits of this approach through offline statistical analysis of human motion data. The results indicate a considerable improvement over prior techniques in early prediction, achieving 70% or higher correct classification on average for the first third of the trajectory (<; 500msec). We also indicate proof-of-concept through the demonstration of a human-robot cooperative manipulation task performed with a PR2 robot. Finally, we analyze the quality of task-level anticipatory knowledge required to improve prediction performance early in the human motion trajectory. |
| first_indexed | 2024-09-23T16:50:18Z |
| format | Article |
| id | mit-1721.1/106656 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:50:18Z |
| publishDate | 2017 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1066562022-09-29T21:52:53Z Fast target prediction of human reaching motion for cooperative human-robot manipulation tasks using time series classification Perez D'Arpino, Claudia Shah, Julie A Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Perez D'Arpino, Claudia Shah, Julie A Interest in human-robot coexistence, in which humans and robots share a common work volume, is increasing in manufacturing environments. Efficient work coordination requires both awareness of the human pose and a plan of action for both human and robot agents in order to compute robot motion trajectories that synchronize naturally with human motion. In this paper, we present a data-driven approach that synthesizes anticipatory knowledge of both human motions and subsequent action steps in order to predict in real-time the intended target of a human performing a reaching motion. Motion-level anticipatory models are constructed using multiple demonstrations of human reaching motions. We produce a library of motions from human demonstrations, based on a statistical representation of the degrees of freedom of the human arm, using time series analysis, wherein each time step is encoded as a multivariate Gaussian distribution. We demonstrate the benefits of this approach through offline statistical analysis of human motion data. The results indicate a considerable improvement over prior techniques in early prediction, achieving 70% or higher correct classification on average for the first third of the trajectory (<; 500msec). We also indicate proof-of-concept through the demonstration of a human-robot cooperative manipulation task performed with a PR2 robot. Finally, we analyze the quality of task-level anticipatory knowledge required to improve prediction performance early in the human motion trajectory. 2017-01-27T17:20:37Z 2017-01-27T17:20:37Z 2015-07 Article http://purl.org/eprint/type/ConferencePaper 978-1-4799-6923-4 1050-4729 http://hdl.handle.net/1721.1/106656 Perez-D’Arpino, Claudia, and Julie A. Shah. “Fast Target Prediction of Human Reaching Motion for Cooperative Human-Robot Manipulation Tasks Using Time Series Classification.” IEEE, 2015. 6175–6182. https://orcid.org/0000-0002-1999-7395 https://orcid.org/0000-0003-1338-8107 en_US http://dx.doi.org/10.1109/ICRA.2015.7140066 Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) Other repository |
| spellingShingle | Perez D'Arpino, Claudia Shah, Julie A Fast target prediction of human reaching motion for cooperative human-robot manipulation tasks using time series classification |
| title | Fast target prediction of human reaching motion for cooperative human-robot manipulation tasks using time series classification |
| title_full | Fast target prediction of human reaching motion for cooperative human-robot manipulation tasks using time series classification |
| title_fullStr | Fast target prediction of human reaching motion for cooperative human-robot manipulation tasks using time series classification |
| title_full_unstemmed | Fast target prediction of human reaching motion for cooperative human-robot manipulation tasks using time series classification |
| title_short | Fast target prediction of human reaching motion for cooperative human-robot manipulation tasks using time series classification |
| title_sort | fast target prediction of human reaching motion for cooperative human robot manipulation tasks using time series classification |
| url | http://hdl.handle.net/1721.1/106656 https://orcid.org/0000-0002-1999-7395 https://orcid.org/0000-0003-1338-8107 |
| work_keys_str_mv | AT perezdarpinoclaudia fasttargetpredictionofhumanreachingmotionforcooperativehumanrobotmanipulationtasksusingtimeseriesclassification AT shahjuliea fasttargetpredictionofhumanreachingmotionforcooperativehumanrobotmanipulationtasksusingtimeseriesclassification |