Year-end Sale % OFF 
Abstract
Neuromorphic implementation of robotic control has been shown to outperform conventional control paradigms in terms of robustness to perturbations and adaptation to varying conditions. Two main ingredients of robotics are inverse kinematic and Proportional–Integral–Derivative (PID) control. Inverse kinematics is used to compute an appropriate state in a robot's configuration space, given a target position in task space. PID control applies responsive correction signals to a robot's actuators, allowing it to reach its target accurately. The Neural Engineering Framework (NEF) offers a theoretical framework for a neuromorphic encoding of mathematical constructs with spiking neurons for the implementation of functional large-scale neural networks. In this work, we developed NEF-based neuromorphic algorithms for inverse kinematics and PID control, which we used to manipulate 6 degrees of freedom robotic arm. We used online learning for inverse kinematics and signal integration and differentiation for PID, offering high performing and energy-efficient neuromorphic control. Algorithms were evaluated in simulation as well as on Intel's Loihi neuromorphic hardware.
Highlights
While computational motion planning and sensing have emerged as focal points for countless state-of-the-art robotic systems, in many ways, they are inadequate when compared with biological systems, in terms of energy efficiency, robustness, versatility, and adaptivity (DeWolf et al, 2016)
IK was implemented with Neural Engineering Framework (NEF) using Nengo and tested on our robotic arm
While IK allows for defining trajectories in task space and implementing it in configuration space, PID provides a canonical way of efficiently approaching a target
Summary
While computational motion planning and sensing have emerged as focal points for countless state-of-the-art robotic systems, in many ways, they are inadequate when compared with biological systems, in terms of energy efficiency, robustness, versatility, and adaptivity (DeWolf et al, 2016). Designing algorithms with spiking neurons is a challenging endeavor, as it requires the encoding, decoding, and transformation of mathematical constructs without a central processing unit nor addressbased memory. NEF is one of the most utilized theoretical frameworks in neuromorphic computing, and it was used to design neuromorphic systems capable of perception, memory, and motor control (DeWolf et al, 2020). It serves as the foundation for Nengo, a Pythonbased “neural compiler,” which translates high-level descriptions to low-level neural models (Bekolay et al, 2014). A version of NEF was compiled to work on the most prominent neuromorphic hardware architectures available, including the TrueNorth (Fischl et al, 2018), Neuromorphic Inverse Kinematics and PID Control developed by IBM research, the Loihi (Lin et al, 2018), developed by Intel Labs, the NeuroGrid (Boahen, 2017), developed at Stanford University and the SpiNNaker (Mundy et al, 2015), developed at the University of Manchester
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
