Conditioned behavior in a robot controlled by a spiking neural network

Helgadottir, Lovisa Irpa; Haenicke, Joachim; Landgraf, Tim; Rojas, Raúl; Nawrot, Martin Paul

doi:10.1109/ner.2013.6696078

Cited by 25 publications

(22 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Milde et al (2017) performed obstacle avoidance and target acquisition tasks with a robotic vehicle, on which an SNN takes event-based vision sensor as the input and runs on a neuromorphic hardware. It is worth mentioning that some fixed SNN architectures aim at solving a problem by imitating parts of structures of natural neural networks found in living organisms such as the withdrawal circuit of the Aplysia—a marine snail organism—in Alnajjar et al (2008), olfactory learning observed in the fruit fly or honey bee in Helgadottir et al (2013), or the cerebellum in Carrillo et al (2008).…”

Section: Related Workmentioning

confidence: 99%

“…Each output neuron represented a different movement direction. In other approaches, such as Helgadottir et al (2013) or Spüler et al (2015), only a limited amount of synaptic connections employ synaptic plasticity while the majority of the synaptic strengths were fixed. Unfortunately, similar approaches only work for simple tasks rather than more complex tasks, which require precise tuning of many more degrees of freedom, e.g., one or more hidden layers, to solve the given task with satisfactory precision.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Supervised Learning in SNN via Reward-Modulated Spike-Timing-Dependent Plasticity for a Target Reaching Vehicle

et al. 2019

View full text Add to dashboard Cite

Spiking neural networks (SNNs) offer many advantages over traditional artificial neural networks (ANNs) such as biological plausibility, fast information processing, and energy efficiency. Although SNNs have been used to solve a variety of control tasks using the Spike-Timing-Dependent Plasticity (STDP) learning rule, existing solutions usually involve hard-coded network architectures solving specific tasks rather than solving different kinds of tasks generally. This results in neglecting one of the biggest advantages of ANNs, i.e., being general-purpose and easy-to-use due to their simple network architecture, which usually consists of an input layer, one or multiple hidden layers and an output layer. This paper addresses the problem by introducing an end-to-end learning approach of spiking neural networks constructed with one hidden layer and reward-modulated Spike-Timing-Dependent Plasticity (R-STDP) synapses in an all-to-all fashion. We use the supervised reward-modulated Spike-Timing-Dependent-Plasticity learning rule to train two different SNN-based sub-controllers to replicate a desired obstacle avoiding and goal approaching behavior, provided by pre-generated datasets. Together they make up a target-reaching controller, which is used to control a simulated mobile robot to reach a target area while avoiding obstacles in its path. We demonstrate the performance and effectiveness of our trained SNNs to achieve target reaching tasks in different unknown scenarios.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Supervised Learning in SNN via Reward-Modulated Spike-Timing-Dependent Plasticity for a Target Reaching Vehicle

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Non-evolutionary approaches to spiking robot control include dynamic learning of navigation behaviour via conditioning (Helgadottir et al, 2013) and real-time training of neuro-controllers based on resovoir computing (Burgsteiner, 2005). Wiles et al (2010) creates biologically plausible models of a rat's brain via self-organised learning for phototaxis.…”

Section: Background Spiking Neuro-controllersmentioning

confidence: 99%

Evolving Spiking Networks for Turbulence-Tolerant Quadrotor Control

Howard¹,

Elfes²

2014

Artificial Life 14: Proceedings of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems

View full text Add to dashboard Cite

We investigate the automatic development of robust quadrotor neurocontrollers based on spiking neural networks. A self-adaptive evolutionary algorithm is used to generate highutility topology/weight combinations in the networks, and a simple synaptic plasticity mechanism provides some degree of in-trial adaptation. Incremental evolution gradually increases the severity of environmental conditions that the agent can successfully handle. Results compare the spiking networks to tuned Proportional/Integral/Derivative controllers and feedforward neural networks for waypointholding experiments in varied atmospheric conditions. It is shown that the spiking controllers are able to maintain a closer distance to the waypoint than the comparative controllers, and more effectively deal with more challenging environmental conditions.

show abstract

“…Neuromorphic computing [1] is a novel paradigm that aims at emulating the naturalistic, flexible structure of animal brains on an analogous physical substrate with the potential to outperform von Neumann architectures in a range of real-world tasks [2, 3]. It can inspire novel AI solutions [4–6] and may support control of autonomous agents by spiking neural networks [7–9]. A major challenge for brain-inspired neuromorphic solutions is the identification of computational principles and circuit motifs in animal nervous systems that can be utilized on neuromorphic hardware to exploit its benefits.…”

Section: Introductionmentioning

confidence: 99%

A neuromorphic model of olfactory processing and sparse coding in the Drosophila larva brain

Jürgensen

Khalili

Chicca

et al. 2021

Preprint

View full text Add to dashboard Cite

Animal nervous systems are highly efficient in processing sensory input. The neuromorphic computing paradigm aims at the hardware implementation of similar mechanism to support novel solutions for building brain-inspired computing systems. Here, we take inspiration from sensory processing in the nervous system of the fruit fly larva. With its strongly limited computational resources of <200 neurons and <1.000 synapses the larval olfactory pathway employs fundamental computations to transform broadly tuned receptor input at the periphery into an energy efficient sparse code in the central brain. We show how this approach allows us to achieve sparse coding and increased separability of stimulus patterns in a spiking neural network, validated with both software simulation and hardware emulation on mixed-signal real-time neuromorphic hardware. We verify that feedback inhibition is the central motif to support sparseness in the spatial domain, across the neuron population, while the combination of spike frequency adaptation and feedback inhibition determines sparseness in the temporal domain. Our experiments demonstrate that such small-sized, biologically realistic neural networks, efficiently implemented on neuromorphic hardware, can achieve parallel processing and efficient encoding of sensory input at full temporal resolution.

show abstract

Conditioned behavior in a robot controlled by a spiking neural network

Cited by 25 publications

References 20 publications

Supervised Learning in SNN via Reward-Modulated Spike-Timing-Dependent Plasticity for a Target Reaching Vehicle

Supervised Learning in SNN via Reward-Modulated Spike-Timing-Dependent Plasticity for a Target Reaching Vehicle

Evolving Spiking Networks for Turbulence-Tolerant Quadrotor Control

A neuromorphic model of olfactory processing and sparse coding in the Drosophila larva brain

Contact Info

Product

Resources

About