Controlling articulated robots in task-space with spiking silicon neurons

Menon, Samir; Fok, Sam; Neckar, Alex; Khatib, Oussama; Boahen, Kwabena

doi:10.1109/biorob.2014.6913773

Cited by 29 publications

(15 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the design choice to use linear synapses in the system excluded the possibility to implement synaptic plasticity mechanisms at each synapse, and therefore the ability of NeuroGrid to model on-line learning or adaptive algorithms without the aid of additional external computing resources. NeuroGrid has been designed to implement cortical models of computation that run in real-time, and has been used in a closed-loop brain-machine application [74] and to control articulated robotic agents [75]. In this system time represents itself [9], and data is processed on the fly, as it arrives.…”

Section: Neurogridmentioning

confidence: 99%

Memory and Information Processing in Neuromorphic Systems

2015

View full text Add to dashboard Cite

Abstract-A striking difference between brain-inspired neuromorphic processors and current von Neumann processors architectures is the way in which memory and processing is organized. As Information and Communication Technologies continue to address the need for increased computational power through the increase of cores within a digital processor, neuromorphic engineers and scientists can complement this need by building processor architectures where memory is distributed with the processing. In this paper we present a survey of brain-inspired processor architectures that support models of cortical networks and deep neural networks. These architectures range from serial clocked implementations of multi-neuron systems to massively parallel asynchronous ones and from purely digital systems to mixed analog/digital systems which implement more biologicallike models of neurons and synapses together with a suite of adaptation and learning mechanisms analogous to the ones found in biological nervous systems. We describe the advantages of the different approaches being pursued and present the challenges that need to be addressed for building artificial neural processing systems that can display the richness of behaviors seen in biological systems.

show abstract

Section: Neurogridmentioning

confidence: 99%

Memory and Information Processing in Neuromorphic Systems

2015

View full text Add to dashboard Cite

show abstract

“…As it turned out, this comes at the price of less flexibility since maximum performance is only achieved for layered neural network architectures. In a recent publication by Menon, Fok, Neckar, Khatib, and Boahen (2014), Neurogrid was used to implement a robot controller. The HRL SyNAPSE chip uses memristors to store synaptic weights.…”

Section: Discussionmentioning

confidence: 99%

Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks

2015

View full text Add to dashboard Cite

a b s t r a c tThe application of biologically inspired methods in design and control has a long tradition in robotics. Unlike previous approaches in this direction, the emerging field of neurorobotics not only mimics biological mechanisms at a relatively high level of abstraction but employs highly realistic simulations of actual biological nervous systems. Even today, carrying out these simulations efficiently at appropriate timescales is challenging. Neuromorphic chip designs specially tailored to this task therefore offer an interesting perspective for neurorobotics. Unlike Von Neumann CPUs, these chips cannot be simply programmed with a standard programming language. Like real brains, their functionality is determined by the structure of neural connectivity and synaptic efficacies. Enabling higher cognitive functions for neurorobotics consequently requires the application of neurobiological learning algorithms to adjust synaptic weights in a biologically plausible way. In this paper, we therefore investigate how to program neuromorphic chips by means of learning. First, we provide an overview over selected neuromorphic chip designs and analyze them in terms of neural computation, communication systems and software infrastructure. On the theoretical side, we review neurobiological learning techniques. Based on this overview, we then examine on-die implementations of these learning algorithms on the considered neuromorphic chips. A final discussion puts the findings of this work into context and highlights how neuromorphic hardware can potentially advance the field of autonomous robot systems. The paper thus gives an in-depth overview of neuromorphic implementations of basic mechanisms of synaptic plasticity which are required to realize advanced cognitive capabilities with spiking neural networks.

show abstract

“…While the controller, presented here, was implemented on a small prototype device, following our approach, controllers for multiple motors and objectives could be easily realised on a larger neuromorphic system, such as SpiNNacker [11], TrueNorth [21], or Loihi [6]. Using adaptivity of the neural circuits, powerful adaptive controllers can be developed using this paradigm in the future, using well-known neural control methods, such as [13], [20]. Such neuronal controllers can be more naturally integrated with perceptual systems, for which neuronal networks, including their neuromorphic realisations, are increasingly and successfully used.…”

Section: B Perturbations and Learning Movement Goalsmentioning

confidence: 99%

“…Larger neuromorphic devices became available recently [6], [21] and scaling up our model is straightforward due to the locality of connectivity leading to inherent parallellism of the computing architecture. The controller can easily be extended to control of effectors with several degrees of freedom, based on methods of spike-based motor control developed recently [30], [31], [7], [20].…”

Section: Introductionmentioning

confidence: 99%

Adaptive motor control and learning in a spiking neural network realised on a mixed-signal neuromorphic processor

Glatz

Martel

Kreiser

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Neuromorphic computing is a new paradigm for design of both the computing hardware and algorithms inspired by biological neural networks. The event-based nature and the inherent parallelism make neuromorphic computing a promising paradigm for building efficient neural network based architectures for control of fast and agile robots. In this paper, we present a spiking neural network architecture that uses sensory feedback to control rotational velocity of a robotic vehicle. When the velocity reaches the target value, the mapping from the target velocity of the vehicle to the correct motor command, both represented in the spiking neural network on the neuromorphic device, is autonomously stored on the device using on-chip plastic synaptic weights. We validate the controller using a wheel motor of a miniature mobile vehicle and inertia measurement unit as the sensory feedback and demonstrate online learning of a simple "inverse model" in a two-layer spiking neural network on the neuromorphic chip. The prototype neuromorphic device that features 256 spiking neurons allows us to realise a simple proof of concept architecture for the purely neuromorphic motor control and learning. The architecture can be easily scaled-up if a larger neuromorphic device is available.

show abstract

Controlling articulated robots in task-space with spiking silicon neurons

Cited by 29 publications

References 15 publications

Memory and Information Processing in Neuromorphic Systems

Memory and Information Processing in Neuromorphic Systems

Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks

Adaptive motor control and learning in a spiking neural network realised on a mixed-signal neuromorphic processor

Contact Info

Product

Resources

About