End-effector force and joint torque estimation of a 7-DoF robotic manipulator using deep learning

Kružić, Stanko (avtor), Musić, Josip (avtor), Kamnik, Roman (avtor), Papić, Vladan (avtor)

When a mobile robotic manipulator interacts with other robots, people, or the environment in general, the end-effector forces need to be measured to assess if a task has been completed successfully. Traditionally used force or torque estimation methods are usually based on observers, which require knowledge of the robot dynamics. Contrary to this, our approach involves two methods based on deep neural networks: robot end-effector force estimation and joint torque estimation. These methods require no knowledge of robot dynamics and are computationally effective but require a force sensor under the robot base. Several different architectures were considered for the tasks, and the best ones were identified among those tested. First, the data for training the networks were obtained in simulation. The trained networks showed reasonably good performance, especially using the LSTM architecture (with a root mean squared error (RMSE) of 0.1533 N for end-effector force estimation and 0.5115 Nm for joint torque estimation). Afterward, data were collected on a real Franka Emika Panda robot and then used to train the same networks for joint torque estimation. The obtained results are slightly worse than in simulation (0.5115 Nm vs. 0.6189 Nm, according to the RMSE metric) but still reasonably good, showing the validity of the proposed approach.

• Jezik: Angleški jezik
• Ključne besede: robotic manipulator, force estimation, deep learning, neural networks
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FE - Fakulteta za elektrotehniko
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2021
• Št. strani: 18 str.
• Številčenje: Vol. 10, iss. 23, art. 2963
• PID: 20.500.12556/RUL-136699
• UDK: 007.52
• ISSN pri članku: 2079-9292
• DOI: 10.3390/electronics10232963
• COBISS.SI-ID: 87856643
• Datum objave v RUL: 16.05.2022

Gradivo je del revije

• Naslov: Electronics
• Skrajšan naslov: Electronics
• Založnik: MDPI
• ISSN: 2079-9292
• COBISS.SI-ID: 523068953

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.
• Začetek licenciranja: 01.12.2021

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: robotski manipulator, ocena sile interakcije, globoko učenje, nevronske mreže