Behavioral Learning in a Cognitive Neuromorphic Robot: An Integrative Approach

Abstract

We present here a learning system using the iCub humanoid robot and the SpiNNaker neuromorphic chip to solve the real-world task of object-specific attention. Integrating spiking neural networks with robots introduces considerable complexity for questionable benefit if the objective is simply task performance. But, we suggest, in a cognitive robotics context, where the goal is understanding how to compute, such an approach may yield useful insights to neural architecture as well as learned behavior, especially if dedicated neural hardware is available. Recent advances in cognitive robotics and neuromorphic processing now make such systems possible. Using a scalable, structured, modular approach, we build a spiking neural network where the effects and impact of learning can be predicted and tested, and the network can be scaled or extended to new tasks automatically. We introduce several enhancements to a basic network and show how they can be used to direct performance toward behaviorally relevant goals. Results show that using a simple classical spike-timing-dependent plasticity (STDP) rule on selected connections, we can get the robot (and network) to progress from poor task-specific performance to good performance. Behaviorally relevant STDP appears to contribute strongly to positive learning: "do this" but less to negative learning: "don't do that." In addition, we observe that the effect of structural enhancements tends to be cumulative. The overall system suggests that it is by being able to exploit combinations of effects, rather than any one effect or property in isolation, that spiking networks can achieve compelling, task-relevant behavior.

Neuromorphic Computing for Interactive Robotics: A Systematic Review

“…There are many examples of converting data directly from sensors [19][20][21], intelligent systems with controlling manipulators [11] [22], and robots [23][24] [25]. Moreover, performing detection and recognition tasks [26][27] [28], and processing numerical data with Neural Engineering Framework (NEF) [29][30] [31] can also be done with SNNs.…”

“…While much research has been conducted on vision-based identification, the combination of vision and non-vision sensors promise improvements in the speed of the recognition process. Rast et al [28], demonstrated the learning system using an iCub robot and a SpiNNaker system to solve object identification tasks. The SpiNNaker neuromorphic system [122] is a neural network simulation platform, designed for real-time simulations.…”

Embodied tactile perception and learning

“…A universal event‐driven neuromorphic robotic computing platform was established [150]. Chen et al [151] and Rast et al [152] recently introduced SpiNNaker on a snake‐shaped robot and an iCub humanoid platform, respectively, to realize perception processing.…”

SpiNNTools: The Execution Engine for the SpiNNaker Platform

“…A more detailed description of the framework for simulating neural networks is found in Rhodes et al (2018), but we examine here the application from the perspective of the tools. SpiNNTools has been part of the sPyNNaker software since conception and this release is successfully deployed as part of the EU Flagship Human Brain Project Collaboratory 6 , and has been used successfully in a number of simulations in previous works (e.g., Senk et al, 2017; Albada et al, 2018; Rast et al, 2018; Sen-bhattacharya et al, 2018).…”

“…The live output example described in the Conway's use case also works similarly well in the neural networks use case. Another extension more relevant here is the connection of an external device to the machine which will then be controlled by the network (e.g., a robotic device), as was the subject of Rast et al (2018). In this case an extension of the virtual application vertex is made to represent the device and added to the application graph.…”