Neuromorphic force-control in an industrial task: validating energy and latency benefits

TL;DR

This paper demonstrates that neuromorphic computing hardware can effectively control industrial robots, offering significant energy savings and low latency, thus advancing sustainable and efficient robotic control systems.

Contribution

It presents the first real-world application of neuromorphic computing for industrial robot control, validating energy and latency benefits in a practical setting.

Findings

Neuromorphic controller achieves low latency comparable to CPUs/GPUs.

Energy consumption is an order of magnitude lower than traditional hardware.

Successful deployment on the Intel Loihi chip with a KUKA robot.

Abstract

As robots become smarter and more ubiquitous, optimizing the power consumption of intelligent compute becomes imperative towards ensuring the sustainability of technological advancements. Neuromorphic computing hardware makes use of biologically inspired neural architectures to achieve energy and latency improvements compared to conventional von Neumann computing architecture. Applying these benefits to robots has been demonstrated in several works in the field of neurorobotics, typically on relatively simple control tasks. Here, we introduce an example of neuromorphic computing applied to the real-world industrial task of object insertion. We trained a spiking neural network (SNN) to perform force-torque feedback control using a reinforcement learning approach in simulation. We then ported the SNN to the Intel neuromorphic research chip Loihi interfaced with a KUKA robotic arm. At inference time we show latency competitive with current CPU/GPU architectures, and one order of magnitude less energy usage in comparison to state-of-the-art low-energy edge-hardware. We offer this example as a proof of concept implementation of a neuromoprhic controller in real-world robotic setting, highlighting the benefits of neuromorphic hardware for the development of intelligent controllers for robots.