Many-Joint Robot Arm Control with Recurrent Spiking Neural Networks

被引:1
|
作者
Traub, Manuel [1 ]
Legenstein, Robert [2 ]
Otte, Sebastian [1 ]
机构
[1] Univ Tubingen, Neurocognit Modeling Grp, Comp Sci Dept, Sand 14, D-72076 Tubingen, Germany
[2] Graz Univ Technol, Fac Comp Sci & Biomed Engn, Inffeldgasse 16b, A-8010 Graz, Austria
基金
奥地利科学基金会;
关键词
KINEMATICS;
D O I
10.1109/IROS51168.2021.9636001
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In the paper, we show how scalable, low-cost trunk-like robotic arms can be constructed using only basic 3D-printing equipment and simple electronics. The design is based on uniform, stackable joint modules with three degrees of freedom each. Moreover, we present an approach for controlling these robots with recurrent spiking neural networks. At first, a spiking forward model learns motor-pose correlations from movement observations. After training, intentions can be projected back through unrolled spike trains of the forward model essentially routing the intention-driven motor gradients towards the respective joints, which unfolds goal-direction navigation. We demonstrate that spiking neural networks can thus effectively control trunk-like robotic arms with up to 75 articulated degrees of freedom with near millimeter accuracy.
引用
收藏
页码:4918 / 4925
页数:8
相关论文
共 50 条
  • [1] Inverse Recurrent Models - An Application Scenario for Many-Joint Robot Arm Control
    Otte, Sebastian
    Zwiener, Adrian
    Hanten, Richard
    Zell, Andreas
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT I, 2016, 9886 : 149 - 157
  • [2] Inherently Constraint-Aware Control of Many-Joint Robot Arms with Inverse Recurrent Models
    Otte, Sebastian
    Zwiener, Adrian
    Butz, Martin V.
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2017, PT I, 2017, 10613 : 262 - 270
  • [3] Evolving spiking neural networks for robot control
    Batllori, R.
    Laramee, C. B.
    Land, W.
    Schaffer, J. D.
    [J]. COMPLEX ADAPTIVE SYSTEMS, 2011, 6
  • [4] THE APPLICATION OF SPIKING NEURAL NETWORKS IN AUTONOMOUS ROBOT CONTROL
    Trhan, Peter
    [J]. COMPUTING AND INFORMATICS, 2010, 29 (05) : 823 - 847
  • [5] Information Bottleneck in Control Tasks with Recurrent Spiking Neural Networks
    Vasu, Madhavun Candadai
    Izquierdo, Eduardo J.
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2017, PT I, 2017, 10613 : 236 - 244
  • [6] Integrative Collision Avoidance Within RNN-Driven Many-Joint Robot Arms
    Otte, Sebastian
    Hofmaier, Lea
    Butz, Martin V.
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2018, PT III, 2018, 11141 : 748 - 758
  • [7] Dynamic control of a robot arm using CMAC neural networks
    Cembrano, G
    Wells, G
    Sarda, J
    Ruggeri, A
    [J]. CONTROL ENGINEERING PRACTICE, 1997, 5 (04) : 485 - 492
  • [8] Intelligent control of robot arm using artificial neural networks
    Yamada, Y
    Kermanshahi, B
    Tagawa, N
    Moriya, T
    [J]. MELECON '96 - 8TH MEDITERRANEAN ELECTROTECHNICAL CONFERENCE, PROCEEDINGS, VOLS I-III: INDUSTRIAL APPLICATIONS IN POWER SYSTEMS, COMPUTER SCIENCE AND TELECOMMUNICATIONS, 1996, : 1164 - 1167
  • [9] Image Classification with Recurrent Spiking Neural Networks
    Cureno Ramirez, Andres
    Garcia Morgado, Balam
    Gerardo de la Fraga, Luis
    [J]. PATTERN RECOGNITION, MCPR 2024, 2024, 14755 : 368 - 376
  • [10] A spiking neural model of adaptive arm control
    DeWolf, Travis
    Stewart, Terrence C.
    Slotine, Jean-Jacques
    Eliasmith, Chris
    [J]. PROCEEDINGS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES, 2016, 283 (1843)