It is essential for human-robot interaction to accurate joint torque value estimation of industrial robots without force/torque (F/T) sensors. The most common method to estimate the value of robot joint torque is based on dynamic model parameter identification. However, no matter how elaborate the modeling methods are used, there are always uncertainty errors when robot’s joint rotation direction changes. In this paper, an identification framework is proposed to estimate optimal model parameters, and a deep learning network is proposed to compensate for the uncertainty errors caused by the unmodeled dynamics part. At first, the dynamic parameters are estimated during the Least Squares (LS) identification process considering the noise influence and data outliers, and the nonlinear friction model is unified into the identification framework. Secondly, based on Long-Short Term Memory (LSTM) network, an error compensation model (ECM) is proposed to establish the mapping relationship between the joint motion and the identification errors. Finally, a 6-DOF robot is used for parameter identification and ECM validation. Experimental results show that the proposed identification method is better than the LS method. Compared with the torque value estimated by the identification method, the proposed ECM can compensate for the uncertainty errors and improve the torque estimation accuracy.
JiangSJiangMCaoY, et al. A typical dynamic parameter identification method of 6-degree-of-freedom industrial robot. Proc IMechE, Part I: J Systems and Control Engineering2017; 231(9): 740–752.
2.
WuJWangJYouZ. An overview of dynamic parameter identification of robots. Robot Comput Integr Manuf2010; 26(5): 414–419.
3.
RadkhahKKulicDCroftE. Dynamic parameter identification for the CRS A460 robot. In: IEEE/RSJ international conference on intelligent robots and systems, San Diego, CA, October 29–November 2 2007, pp.3842–3847. New York, NY: IEEE.
4.
AzeddienKTahaZ. Robust least square estimation of the CRS A465 robot arm’s dynamic model parameters. J Mech Eng Res2012; 4(3): 89–99.
5.
WuJLiWXiongZ. Identification of robot dynamic model and joint frictions using a baseplate force sensor. Sci China Technol Sci2021; 65(1): 30–40.
6.
BonnetVFraissePCrosnierA, et al. Optimal exciting dance for identifying inertial parameters of an anthropomorphic structure. IEEE Trans Robot2016; 32(4): 823–836.
7.
SweversJGansemanCTukelDB, et al. Optimal robot excitation and identification. IEEE Trans Robot Autom1997; 13(5): 730–740.
8.
JinJGansN. Parameter identification for industrial robots with a fast and robust trajectory design approach. Robot Comput Integr Manuf2015; 31: 21–29.
9.
GautierMKhalilW. Exciting trajectories for the identification of base inertial parameters of robots. Int J Rob Res1992; 11(4): 362–375.
10.
UrreaCPascalJ. Design, simulation, comparison and evaluation of parameter identification methods for an industrial robot. Comput Electr Eng2018; 67: 791–806.
11.
XiaojunDJinHHaoyuanY, et al. Dynamic parameter identification of a 6-DOF industrial manipulator considering friction model. In: IEEE international conference on robotics and biomimetics, Dali, China, 6–8 December 2019, pp.802–807. Piscataway, NJ: IEEE.
12.
JanotAVandanjonPOGautierM. A generic instrumental variable approach for industrial robot identification. IEEE Trans Control Syst Technol2014; 22(1): 132–145.
13.
JanotAVandanjonPGautierM. Using robust regressions and residual analysis to verify the reliability of LS estimation: application in robotics. In: IEEE RSJ international conference on intelligent robots and systems, St Louis, MO, 10–15 October 2009, pp.1962–1967. New York, NY: IEEE.
14.
HanYWuJLiuC, et al. An iterative approach for accurate dynamic model identification of Industrial Robots. IEEE Trans Robot2020; 36(5): 1577–1594.
15.
SweversJVerdonckWDe SchutterJ. Dynamic model identification for industrial robots - integrated experiment design and parameter estimation. IEEE Control Syst Mag2007; 27(5): 58–71.
16.
VolkmannBKaczorDTantauM, et al. Sensitivity-based model reduction for in-process identification of industrial robots inverse dynamics. In: IEEE international conference on mechatronics and automation, Beijing, China, 13–16 October 2020, pp.912–919. Piscataway, NJ: IEEE.
17.
HamonPGautierMGarrecP, et al. Dynamic modeling and identification of joint drive with load-dependent friction model. In: IEEE/ASME international conference on advanced intelligent mechatronics, Montreal, QC, Canada, 6–9 July 2010, pp.902–907. Piscataway, NJ: IEEE.
18.
HamonPGautierMGarrecP. New dry friction model with load- and velocity-dependence and dynamic identification of multi-DOF robots. In: IEEE international conference on robotics and automation, Shanghai, China, 9–13 May 2011, pp.1077–1084. New York, NY: IEEE.
19.
WolfSIskandarM. Extending a dynamic friction model with nonlinear viscous and thermal dependency for a motor and harmonic drive gear. In: IEEE international conference on robotics and automation, Brisbane, Australia, 21–25 May 2018, pp.783–790. Los Alamitos, CA: IEEE.
20.
LiangBLiTChenZ, et al. Robot arm dynamics control based on deep learning and physical simulation. In: 37th Chinese control conference, Wuhan, China, 25–27 July 2018, pp.2921–2925. New York, NY: IEEE.
21.
LiuNLiLHaoB, et al. Modeling and simulation of robot inverse dynamics using LSTM-based deep learning algorithm for smart cities and factories. IEEE Access2019; 7: 173989–173998.
22.
LiuNLiLHaoB, et al. Semiparametric deep learning manipulator inverse dynamics modeling method for smart city and industrial applications. Complexity2020; 2020: 1–11.
23.
HochreiterSSchmidhuberJ. Long short-term memory. Neural Comput1997; 9(8): 1735–1780.
24.
RueckertENakatenusMTosattoS, et al. Learning inverse dynamics models in o(n) time with LSTM networks. In: IEEE-RAS 17th international conference on humanoid robotics (Humanoids), Birmingham, England, 15–17 November 2017, pp.811–-816. New York, NY: IEEE.
25.
WangSShaoXYangL, et al. Deep learning aided dynamic parameter identification of 6-DOF robot manipulators. IEEE Access2020; 8: 138102–138116.
26.
MayedaHYoshidaKOsukaK. Base parameters of manipulator dynamic models. IEEE Trans Robot Autom1990; 6(3): 312–321.
27.
GautierMKhalilW. Identification of the minimum inertial parameters of robots. In: IEEE international conference on robotics and automation, Scottsdale, AZ, USA, 14–19 May 1989, pp.1529–1534. Washington, DC: IEEE.
28.
GautierMKhalilW. Direct calculation of minimum set of inertial parameters of serial robots. IEEE Trans Robot Autom1990; 6(3): 368–373.
29.
KhatounianFMoreauSMonmassonE, et al. Parameters estimation of the actuator used in haptic interfaces: comparison of two identification methods. In: IEEE international symposium on industrial electronics, Montreal, QC, Canada, 09–13 July 2006, pp.211–216.
30.
KhalilWGautierMLemoineP. Identification of the payload inertial parameters of industrial manipulators. In: IEEE international conference on robotics and automation, Rome, Italy, 10–14 April 2007, pp.4943–4948.
31.
GautierMJanotAVandanjonP. DIDIM: a new method for the dynamic identification of robots from only torque data. In: IEEE international conference on robotics and automation, Pasadena, CA, USA, 19–23 May 2008, pp.2122–2127.
32.
GautierM. Dynamic identification of robots with power model. In: IEEE international conference on robotics and automation, Albuquerque, NM, USA, 20–25 April 1997, pp.1922–1927. New York, NY: IEEE.
33.
HollandPWWelschRE. Robust regression using iteratively reweighted least-squares. Commun Stat Theory Methods1977; 6(9): 813–827.
34.
FarhatNMataVPageA, et al. Dynamic simulation of a parallel robot: Coulomb friction and stick–slip in robot joints. Robotica2010; 28(1): 35–45.
35.
FarhatNRodríguezMMataV. Dynamic parameter identification of parallel robots considering physical feasibility and nonlinear friction models. In: 12th IFToMM world congress, Besancon, Francia, 18–21 June 2007, pp.1–6.
