Bio-Inspired Embedded Vision System for Autonomous Micro-Robots: The LGMD Case

In this paper, we present a new bio-inspired vision system embedded for micro-robots. The vision system takes inspiration from locusts in detecting fast approaching objects. Neurophysiological research suggested that locusts use a wide-field visual neuron called lobula giant movement detector (LGMD) to respond to imminent collisions. In this paper, we present the implementation of the selected neuron model by a low-cost ARM processor as part of a composite vision module. As the first embedded LGMD vision module fits to a micro-robot, the developed system performs all image acquisition and processing independently. The vision module is placed on top of a micro-robot to initiate obstacle avoidance behavior autonomously. Both simulation and real-world experiments were carried out to test the reliability and robustness of the vision system. The results of the experiments with different scenarios demonstrated the potential of the bio-inspired vision system as a low-cost embedded module for autonomous robots.

[1]  R eid R. H arrison.  A Biologically Inspired Analog IC for Visual Collision Detection , .

[2]  R D Santer,et al.  Retinally-generated saccadic suppression of a locust looming-detector neuron: investigations using a robot locust , 2004, Journal of The Royal Society Interface.

[3]  José-Enrique Simó-Ten,et al.  Using infrared sensors for distance measurement in mobile robots , 2002, Robotics Auton. Syst..

[4]  Mandyam V. Srinivasan,et al.  Behavioral Lateralization and Optimal Route Choice in Flying Budgerigars , 2014, PLoS Comput. Biol..

[5]  Paul F. M. J. Verschure,et al.  Collision avoidance using a model of the locust LGMD neuron , 2000, Robotics Auton. Syst..

[6]  P. Simmons,et al.  Orthopteran DCMD neuron: a reevaluation of responses to moving objects. I. Selective responses to approaching objects. , 1992, Journal of neurophysiology.

[7]  Ali Emre Turgut,et al.  Cue-based aggregation with a mobile robot swarm: a novel fuzzy-based method , 2014, Adapt. Behav..

[8]  Youdan Kim,et al.  Stereo vision based collision avoidance of quadrotor UAV , 2012, 2012 12th International Conference on Control, Automation and Systems.

[9]  A. Borst,et al.  Neural networks in the cockpit of the fly , 2002, Journal of Comparative Physiology A.

[10]  Shigang Yue,et al.  Reactive direction control for a mobile robot: a locust-like control of escape direction emerges when a bilateral pair of model locust visual neurons are integrated , 2010, Auton. Robots.

[11]  Paul F. M. J. Verschure,et al.  A fly-locust based neuronal control system applied to an unmanned aerial vehicle: the invertebrate neuronal principles for course stabilization, altitude control and collision avoidance , 2007, Int. J. Robotics Res..

[12]  P. Simmons,et al.  Gliding behaviour elicited by lateral looming stimuli in flying locusts , 2004, Journal of Comparative Physiology A.

[13]  Shigang Yue,et al.  Collision detection in complex dynamic scenes using an LGMD-based visual neural network with feature enhancement , 2006, IEEE Transactions on Neural Networks.

[14]  Georg von Wichert.  Can robots learn to see , 1999 .

[15]  Shigang Yue,et al.  Redundant Neural Vision Systems—Competing for Collision Recognition Roles , 2013, IEEE Transactions on Autonomous Mental Development.

[16]  Roberto Manduchi,et al.  Obstacle Detection and Terrain Classification for Autonomous Off-Road Navigation , 2005, Auton. Robots.

[17]  Hobart R. Everett,et al.  Sensors for Mobile Robots: Theory and Application , 1995 .

[18]  Mandyam V. Srinivasan,et al.  From biology to engineering: insect vision and applications to robotics , 2012 .

[19]  Libor Preucil,et al.  A Practical Multirobot Localization System , 2014, J. Intell. Robotic Syst..

[20]  Qijun Chen,et al.  Adaptive walking control of quadruped robots based on central pattern generator (CPG) and reflex , 2013 .

[21]  F. Claire Rind,et al.  A DIRECTIONALLY SELECTIVE MOTION-DETECTING NEURONE IN THE BRAIN OF THE LOCUST: PHYSIOLOGICAL AND MORPHOLOGICAL CHARACTERIZATION , 1990 .

[22]  Ali Emre Turgut,et al.  Investigation of cue-based aggregation in static and dynamic environments with a mobile robot swarm , 2016, Adapt. Behav..

[23]  Abdul Rahman Ramli,et al.  Development of IR-based short-range communication techniques for swarm robot applications , 2010 .

[24]  Shigang Yue,et al.  Postsynaptic organisations of directional selective visual neural networks for collision detection , 2013, Neurocomputing.

[25]  Yongtae Do,et al.  Moving obstacle avoidance of a mobile robot using a single camera , 2012 .

[26]  Sofiane Boucenna,et al.  Learning of Social Signatures Through Imitation Game Between a Robot and a Human Partner , 2014, IEEE Transactions on Autonomous Mental Development.

[27]  Jianwei Zhang,et al.  An approach for adaptive limbless locomotion using a cpg-based reflex mechanism , 2014 .

[28]  Dimitri Ognibene,et al.  Ecological Active Vision: Four Bioinspired Principles to Integrate Bottom–Up and Adaptive Top–Down Attention Tested With a Simple Camera-Arm Robot , 2015, IEEE Transactions on Autonomous Mental Development.

[29]  Cristina P. Santos,et al.  LGMD based Neural Network for Automatic Collision Detection , 2012, ICINCO.

[30]  Michael O'Shea,et al.  The Anatomy of a Locust Visual Interneurone; the Descending Contralateral Movement Detector , 1974 .

[31]  Andrew Hunter,et al.  A modified model for the Lobula Giant Movement Detector and its FPGA implementation , 2010, Comput. Vis. Image Underst..

[32]  Paul F. M. J. Verschure,et al.  Using a Mobile Robot to Study Locust Collision Avoidance Responses , 1999, Int. J. Neural Syst..

[33]  Paul F. M. J. Verschure,et al.  Non-Linear Neuronal Responses as an Emergent Property of Afferent Networks: A Case Study of the Locust Lobula Giant Movement Detector , 2010, PLoS Comput. Biol..

[34]  Rind,et al.  The locust DCMD, a movement-detecting neurone tightly tuned to collision trajectories , 1997, The Journal of experimental biology.

[35]  Michael Knight,et al.  Vision and Navigation in Insects, and Applications to Aircraft Guidance , 2014 .

[36]  J. A. Stacey,et al.  Selective attention in the honeybee optic lobes precedes behavioral choices , 2014, Proceedings of the National Academy of Sciences.

[37]  Ashutosh Saxena,et al.  Low-power parallel algorithms for single image based obstacle avoidance in aerial robots , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[38]  Seung-Eun Yu,et al.  Burrow-centric distance-estimation methods inspired by surveillance behavior of fiddler crabs , 2012, Adapt. Behav..

[39]  F. Claire Rind,et al.  IDENTIFICATION OF DIRECTIONALLY SELECTIVE MOTION-DETECTING NEURONES IN THE LOCUST LOBULA AND THEIR SYNAPTIC CONNECTIONS WITH AN IDENTIFIED DESCENDING NEURONE , 1990 .

[40]  P. Simmons,et al.  Seeing what is coming: building collision-sensitive neurones , 1999, Trends in Neurosciences.

[41]  Chun Zhang,et al.  Colias: An Autonomous Micro Robot for Swarm Robotic Applications , 2014 .

[42]  H. D. Taghirad,et al.  A new method for mobile robot navigation in dynamic environment: Escaping algorithm , 2013, 2013 First RSI/ISM International Conference on Robotics and Mechatronics (ICRoM).

[43]  Tetsuya Yagi,et al.  A visually guided collision warning system with a neuromorphic architecture , 2008, Neural Networks.

[44]  Farshad Arvin,et al.  Encoderless position estimation and error correction techniques for miniature mobile robots , 2013 .

[45]  Ashutosh Natraj,et al.  A real-time monocular vision-based frontal obstacle detection and avoidance for low cost UAVs in GPS denied environment , 2014, 2014 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology.

[46]  Shigang Yue,et al.  Near range path navigation using LGMD visual neural networks , 2009, 2009 2nd IEEE International Conference on Computer Science and Information Technology.

[47]  Stéphane Viollet,et al.  Optic Flow Based Visual Guidance: From Flying Insects to Miniature Aerial Vehicles , 2009 .

[48]  Shigang Yue,et al.  A Synthetic Vision System Using Directionally Selective Motion Detectors to Recognize Collision , 2007, Artificial Life.

[49]  Richard H Masland,et al.  Functional inhibition in direction-selective retinal ganglion cells: spatiotemporal extent and intralaminar interactions. , 2002, Journal of neurophysiology.

[50]  Zhuhong Zhang,et al.  Fly visual system inspired artificial neural network for collision detection , 2015, Neurocomputing.

[51]  Pierre-Yves Oudeyer,et al.  Object Learning Through Active Exploration , 2014, IEEE Transactions on Autonomous Mental Development.

[52]  F. Rind,et al.  Neural network based on the input organization of an identified neuron signaling impending collision. , 1996, Journal of neurophysiology.

[53]  Hilary Buxton,et al.  Learning and understanding dynamic scene activity: a review , 2003, Image Vis. Comput..