Biological intelligence processes information using impulses or spikes, which makes those living creatures able to perceive and act in the real world exceptionally well and outperform state-of-the-art robots in almost every aspect of life. To make up the deficit, emerging hardware technologies and software knowledge in the fields of neuroscience, electronics, and computer science have made it possible to design biologically realistic robots controlled by spiking neural networks (SNNs), inspired by the mechanism of brains. However, a comprehensive review on controlling robots based on SNNs is still missing. In this paper, we survey the developments of the past decade in the field of spiking neural networks for control tasks, with particular focus on the fast emerging robotics-related applications. We first highlight the primary impetuses of SNN-based robotics tasks in terms of speed, energy efficiency, and computation capabilities. We then classify those SNN-based robotic applications according to different learning rules and explicate those learning rules with their corresponding robotic applications. We also briefly present some existing platforms that offer an interaction between SNNs and robotics simulations for exploration and exploitation. Finally, we conclude our survey with a forecast of future challenges and some associated potential research topics in terms of controlling robots based on SNNs.

/pdf/a-survey-of-robotics-control-based-on-learning-inspired-kl98nojupm.pdf

A Survey of Robotics Control Based on Learning-Inspired Spiking Neural Networks.

In this paper, a target tracking controller based on spiking neural network is proposed for autonomous robots. This controller encodes the preprocessed environmental and target information provided by CCD cameras, encoders and ultrasonic sensors into spike trains, which are integrated by a three-layer spiking neural network (SNN). The outputs of SNN are generated based on the competition between the forward/backward neuron pair corresponding to each motor, with the weights evolved by the Hebbian learning. The application to target tracking of a mobile robot in unknown environment verifies the validity of the proposed controller.

Spiking neural network-based target tracking control for autonomous mobile robots

How complex is the memory structure that honeybees use to navigate? Recently, an insect-inspired parsimonious spiking neural network model was proposed that enabled simulated ground-moving agents to follow learned routes. We adapted this model to flying insects and evaluate the route following performance in three different worlds with gradually decreasing object density. In addition, we propose an extension to the model to enable the model to associate sensory input with a behavioral context, such as foraging or homing. The spiking neural network model makes use of a sparse stimulus representation in the mushroom body and reward-based synaptic plasticity at its output synapses. In our experiments, simulated bees were able to navigate correctly even when panoramic cues were missing. The context extension we propose enabled agents to successfully discriminate partly overlapping routes. The structure of the visual environment, however, crucially determines the success rate. We find that the model fails more often in visually rich environments due to the overlap of features represented by the Kenyon cell layer. Reducing the landmark density improves the agents route following performance. In very sparse environments, we find that extended landmarks, such as roads or field edges, may help the agent stay on its route, but often act as strong distractors yielding poor route following performance. We conclude that the presented model is valid for simple route following tasks and may represent one component of insect navigation. Additional components might still be necessary for guidance and action selection while navigating along different memorized routes in complex natural environments.

A Neural Network Model for Familiarity and Context Learning During Honeybee Foraging Flights

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.

/pdf/supervised-learning-in-snn-via-reward-modulated-spike-timing-4tena0w6bn.pdf

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

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.

Evolving Spiking Networks for Turbulence-Tolerant Quadrotor Control

Insects show a rich repertoire of goal-directed and adaptive behaviors that are still beyond the capabilities of today's artificial systems. Fast progress in our comprehension of the underlying neural computations make the insect a favorable model system for neurally inspired computing paradigms in autonomous robots. Here, we present a robotic platform designed for implementing and testing spiking neural network control architectures. We demonstrate a neuromorphic realtime approach to sensory processing, reward-based associative plasticity and behavioral control. This is inspired by the biological mechanisms underlying rapid associative learning and the formation of distributed memories in the insect.

/pdf/conditioned-behavior-in-a-robot-controlled-by-a-spiking-il0nr4yz39.pdf

Conditioned behavior in a robot controlled by a spiking neural network

The navigation capabilities of honeybees are surprisingly complex. Experimental evidence suggests that honeybees rely on a map-like neuronal representation of the environment. Intriguingly, a honeybee brain exhibits approximately one million neurons only. In an interdisciplinary enterprise, we are investigating models of high-level processing in the nervous system of insects such as spatial mapping and decision making. We use a robotic platform termed NeuroCopter that is controlled by a set of functional modules. Each of these modules initially represents a conventional control method and, in an iterative process, will be replaced by a neural control architecture. This paper describes the neuromorphic extraction of the copter's ego motion from sparse optical flow fields. We will first introduce the reader to the system's architecture and then present a detailed description of the structure of the neural model followed by simulated and real-world results.

/pdf/neurocopter-neuromorphic-computation-of-6d-ego-motion-of-a-3y6uj3x9fk.pdf

NeuroCopter: neuromorphic computation of 6D ego-motion of a quadcopter

In this paper we introduce a shape based method to globally detect the ball in a RoboCup soccer scenario. The method can be used for any round object with detectable edges. The concept of integral images presented in Viola & Jones 2001, is used, however the integration is applied to a vector representation of the gradient orientation histogram of each pixel. The method takes advantage from the fact that large areas of the image can be filtered out, as these are only covered by straight edges. An overlapped binary search quickly reduces the search area and locates ball candidates in the image. The candidates are finally selected using an outlier elimination technique.

/pdf/shape-based-round-object-detection-using-edge-orientation-302fv963zv.pdf

Lovisa Irpa Helgadottir

Papers

Conditioned behavior in a robot controlled by a spiking neural network

NeuroCopter: neuromorphic computation of 6D ego-motion of a quadcopter

Shape Based Round Object Detection Using Edge Orientation Histogram