Biomimetics Micro Robot with Active Hardware Neural Networks Locomotion Control and Insect-Like Switching Behaviour

Saito, Ken; Takato, Minami; Sekine, Yoshifumi; Uchikoba, Fumio

doi:10.5772/54129

Cited by 33 publications

(18 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We are studying about neural networks using pulse-type hardware neuron models (P-HNM) (Matsuoka et al, 2002;Nakabora et al, 2004;Saito et al, 2011Saito et al, , 2012. The P-HNM has the same basic features of biological neurons such as threshold, refractory period, and spatiotemporal summation characteristics and enables the generation of continuous action potentials.…”

Section: Introductionmentioning

confidence: 99%

Locomotion rhythm generation using pulse-type hardware neural networks for quadruped robots

Saito¹,

Ikeda²,

Takato³

et al. 2015

Biomimetic Technologies

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Locomotion rhythm generation using pulse-type hardware neural networks for quadruped robots

Saito¹,

Ikeda²,

Takato³

et al. 2015

Biomimetic Technologies

View full text Add to dashboard Cite

“…The artificial muscle wire is BMX50 (BioMetal ® Helix, available online at http://www.toki.co.jp [32]). The mechanical components of the hexapod robot are detailed in previous works [27,29]. Figure 4 shows the leg motions of the hexapod robot.…”

Section: Hexapod Robotmentioning

confidence: 99%

“…The structure and stepping motion of the robot mimic those of an ant. The antlike stepping motion is a series of tripod configurations in which two groups of three legs alternate between swing and stance phases (see Figure 5 in [29]). The hexapod robot comprises the frame parts, small-sized actuators, and link mechanisms.…”

Section: Hexapod Robotmentioning

confidence: 99%

“…In our multilegged robots, the number of actuators is reduced by a link mechanism, and the gait is controlled by a hardware ANN. The hardware ANN consists of 4 excitatory synaptic models, 16 inhibitory synaptic models, and 8 cell body models for the quadruped robot [26], and 12 inhibitory synaptic models and 4 cell body models for the hexapod robot [27][28][29].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Gait Generation of Multilegged Robots by using Hardware Artificial Neural Networks

Saito¹,

Ohara²,

Abe³

et al. 2018

Advanced Applications for Artificial Neural Networks

Self Cite

View full text Add to dashboard Cite

Living organisms can act autonomously because biological neural networks process the environmental information in continuous time. Therefore, living organisms have inspired many applications of autonomous control to small-sized robots. In this chapter, a small-sized robot is controlled by a hardware artificial neural network (ANN) without software programs. Previously, the authors constructed a multilegged walking robot. The link mechanism of the limbs was designed to reduce the number of actuators. The current paper describes the basic characteristics of hardware ANNs that generate the gait for multilegged robots. The pulses emitted by the hardware ANN generate oscillating patterns of electrical activity. The pulse-type hardware ANN model has the basic features of a class II neuron model, which behaves like a resonator. Thus, gait generation by the hardware ANNs mimics the synchronization phenomena in biological neural networks. Consequently, our constructed hardware ANNs can generate multilegged robot gaits without requiring software programs.

show abstract

“…We have previously used MEMS technology to fabricate insect-type micro-robots [18,19]. These robots were equipped with SMA-based artificial muscle wires.…”

Section: Introductionmentioning

confidence: 99%

A Millimetre-Sized Robot Realized by a Piezoelectric Impact-Type Rotary Actuator and a Hardware Neuron Model

Takato

Tatani

Oku

et al. 2014

International Journal of Advanced Robotic Systems

Self Cite

View full text Add to dashboard Cite

Micro-robotic systems are increasingly used in medicine and other fields requiring precision engineering. This paper proposes a piezoelectric impacttype rotary actuator and applies it to a millimetre-size robot controlled by a hardware neuron model. The rotary actuator and robot are fabricated by micro-electromechanical systems (MEMS) technology. The actuator is composed of multilayer piezoelectric elements. The rotational motion of the rotor is generated by the impact head attached to the piezoelectric element. The millimetre-size robot is fitted with six legs, three on either side of the developed actuator, and can walk on uneven surfaces like an insect. The three leg parts on each side are connected by a linking mechanism. The control system is a hardware neuron model constructed from analogue electronic circuits that mimic the behaviour of biological neurons. The output signal ports of the controller are connected to the multilayer piezoelectric element. This robot system requires no specialized software programs or A/D converters. The rotation speed of the rotary actuator reaches 60 rpm at an applied neuron frequency of 25 kHz during the walking motion. The width, length and height of the robot are 4.0, 4.6 and 3.6 mm, respectively. The motion speed is 180 mm/min.

show abstract

Biomimetics Micro Robot with Active Hardware Neural Networks Locomotion Control and Insect-Like Switching Behaviour

Cited by 33 publications

References 19 publications

Locomotion rhythm generation using pulse-type hardware neural networks for quadruped robots

Locomotion rhythm generation using pulse-type hardware neural networks for quadruped robots

Gait Generation of Multilegged Robots by using Hardware Artificial Neural Networks

A Millimetre-Sized Robot Realized by a Piezoelectric Impact-Type Rotary Actuator and a Hardware Neuron Model

Contact Info

Product

Resources

About