Safely Imitating Predictive Control Policies for Real-Time Human-Aware Manipulator Motion Planning: A Dataset Aggregation Approach
This paper proposes a dataset-aggregation approach for imitating a nonlinear model predictive control law via deep neural networks, to safely allow a robot manipulator to share its workspace with a human operator. As the robot approaches the human, its speed is gradually reduced using the ȁ...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10819386/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554059574640640 |
|---|---|
| author | Aigerim Nurbayeva Matteo Rubagotti |
| author_facet | Aigerim Nurbayeva Matteo Rubagotti |
| author_sort | Aigerim Nurbayeva |
| collection | DOAJ |
| description | This paper proposes a dataset-aggregation approach for imitating a nonlinear model predictive control law via deep neural networks, to safely allow a robot manipulator to share its workspace with a human operator. As the robot approaches the human, its speed is gradually reduced using the “speed and separation monitoring” framework. Specific time-varying upper bounds are explicitly imposed on the control input generated by the deep neural network through a “safety filter” based on real-time numerical optimization. The proposed method is experimentally tested on a UR5 manipulator, comparing the performance of different neural network structures and types of training. As a result, it is shown that the dataset-aggregation approach provides better performance with respect to a “naive” approach to training, and that the presence of the safety filter is indeed needed to avoid the violation of the speed-and-separation-monitoring constraints. |
| format | Article |
| id | doaj-art-b0d80e013d6840cfa0ea66c4a7c5da05 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-b0d80e013d6840cfa0ea66c4a7c5da052025-01-09T00:01:42ZengIEEEIEEE Access2169-35362025-01-01133204321410.1109/ACCESS.2024.352494610819386Safely Imitating Predictive Control Policies for Real-Time Human-Aware Manipulator Motion Planning: A Dataset Aggregation ApproachAigerim Nurbayeva0Matteo Rubagotti1https://orcid.org/0000-0002-3674-1455Department of Robotics, School of Engineering and Digital Sciences, Nazarbayev University, Astana, KazakhstanDepartment of Robotics, School of Engineering and Digital Sciences, Nazarbayev University, Astana, KazakhstanThis paper proposes a dataset-aggregation approach for imitating a nonlinear model predictive control law via deep neural networks, to safely allow a robot manipulator to share its workspace with a human operator. As the robot approaches the human, its speed is gradually reduced using the “speed and separation monitoring” framework. Specific time-varying upper bounds are explicitly imposed on the control input generated by the deep neural network through a “safety filter” based on real-time numerical optimization. The proposed method is experimentally tested on a UR5 manipulator, comparing the performance of different neural network structures and types of training. As a result, it is shown that the dataset-aggregation approach provides better performance with respect to a “naive” approach to training, and that the presence of the safety filter is indeed needed to avoid the violation of the speed-and-separation-monitoring constraints.https://ieeexplore.ieee.org/document/10819386/Industrial roboticsphysical human-robot interactionmodel predictive controlneural networks |
| spellingShingle | Aigerim Nurbayeva Matteo Rubagotti Safely Imitating Predictive Control Policies for Real-Time Human-Aware Manipulator Motion Planning: A Dataset Aggregation Approach IEEE Access Industrial robotics physical human-robot interaction model predictive control neural networks |
| title | Safely Imitating Predictive Control Policies for Real-Time Human-Aware Manipulator Motion Planning: A Dataset Aggregation Approach |
| title_full | Safely Imitating Predictive Control Policies for Real-Time Human-Aware Manipulator Motion Planning: A Dataset Aggregation Approach |
| title_fullStr | Safely Imitating Predictive Control Policies for Real-Time Human-Aware Manipulator Motion Planning: A Dataset Aggregation Approach |
| title_full_unstemmed | Safely Imitating Predictive Control Policies for Real-Time Human-Aware Manipulator Motion Planning: A Dataset Aggregation Approach |
| title_short | Safely Imitating Predictive Control Policies for Real-Time Human-Aware Manipulator Motion Planning: A Dataset Aggregation Approach |
| title_sort | safely imitating predictive control policies for real time human aware manipulator motion planning a dataset aggregation approach |
| topic | Industrial robotics physical human-robot interaction model predictive control neural networks |
| url | https://ieeexplore.ieee.org/document/10819386/ |
| work_keys_str_mv | AT aigerimnurbayeva safelyimitatingpredictivecontrolpoliciesforrealtimehumanawaremanipulatormotionplanningadatasetaggregationapproach AT matteorubagotti safelyimitatingpredictivecontrolpoliciesforrealtimehumanawaremanipulatormotionplanningadatasetaggregationapproach |