Jose Hugo Barron-Zambrano

2013 Special Issue: FPGA implementation of a configurable neuromorphic CPG-based locomotion controller

Neuromorphic engineering is a discipline devoted to the design and development of computational hardware that mimics the characteristics and capabilities of neuro-biological systems. In recent years, neuromorphic hardware systems have been implemented using a hybrid approach incorporating digital hardware so as to provide flexibility and scalability at the cost of power efficiency and some biological realism. This paper proposes an FPGA-based neuromorphic-like embedded system on a chip to generate locomotion patterns of periodic rhythmic movements inspired by Central Pattern Generators (CPGs). The proposed implementation follows a top-down approach where modularity and hierarchy are two desirable features. The locomotion controller is based on CPG models to produce rhythmic locomotion patterns or gaits for legged robots such as quadrupeds and hexapods. The architecture is configurable and scalable for robots with either different morphologies or different degrees of freedom (DOFs). Experiments performed on a real robot are presented and discussed. The obtained results demonstrate that the CPG-based controller provides the necessary flexibility to generate different rhythmic patterns at run-time suitable for adaptable locomotion.

Hardware implementation of a CPG-based locomotion control for quadruped robots

This paper presents a hardware implementation of a controller to generate adaptive gait patterns for quadruped robots inspired by biological Central Pattern Generators (CPGs). The basic CPGs are modeled as non-linear oscillators which are connected one to each other through coupling parameters that can be modified for different gaits. The proposed implementation is based on an specific digital module for CPGs attached to a soft-core processor so as to provide an integrated and flexible embedded system. The system is implemented on a Field Programmable Gate Array (FPGA) device providing a compact and low power consumption solution for generating periodic rhythmic patterns in robot control applications. Experimental results show that the proposed implementation is able to generate suitable gait patterns, such as walking, trotting, and galloping.

Configurable Embedded CPG-Based Control for Robot Locomotion

Recently, the development of intelligent robots has benefited from a deeper understanding of the biomechanics and neurology of biological systems. Researchers have proposed the concept of Central Pattern Generators (CPGs) as a mechanism for generating an efficient control strategy for legged robots based on biological locomotion principles. Although many studies have aimed to develop robust legged locomotion controllers, relatively few of them have focused on adopting the technology for fully practical embedded hardware implementations. In this contribution, a reconfigurable hardware implementation of a CPG-based controller which is able to generate several gaits for quadruped and hexapod robots is presented. The proposed implementation is modular and configurable in order to scale up to legged robots with different degrees of freedom. Experimental results for embedded Field Programmable Gate Array (FPGA) implementations for quadruped and hexapod robot controllers are presented and analysed.

CPG Implementations for Robot Locomotion: Analysis and Design

The ability to efficiently move in a complex environment is a key property of animals. It is central to their survival, i.e. to avoid predators, to look for food, and to find mates for reproduction (Ijspeert, 2008). Nature has found different solutions for the problem of legged locomotion. For example, the vertebrate animals have a spinal column and one or two pairs of limbs that are used for walking. Arthropoda animals are characterized by a segmented body that is covered by a jointed external skeleton (exoskeleton), with paired jointed limbs on each segment and they can have a high number of limbs (Carbone & Ceccarelli, 2005). The biological mechanisms underlaying locomotion have therefore been extensively studied by neurobiologists, and in recent years there has been an increase in the use of computer simulations for testing and investigating models of locomotor circuits based on neurobiological observations (Ijspeert, 2001). However, the mechanisms generating the complex motion patterns performed by animals are still not well understood (Manoonpong, 2007). Animal locomotion, for instance, requires multi-dimensional coordinated rhythmic patterns that need to be correctly tuned so as to satisfy multiple constraints: the capacity to generate forward motion, with low energy, without falling over, while adapting to possibly complex terrain (uneven ground, obstacles), and while allowing the modulation of speed and direction (Ijspeert & Crespi, 2007). In vertebrate animals, an essential building block of the locomotion controller is the Central Pattern Generator (CPG) located in the spinal cord. The CPG is a neural circuit capable of producing coordinated patterns of rhythmic activity in open loop, i.e. without any rhythmic inputs from sensory feedback or from higher control centers (Delcomyn, 1980; Grillner, 1985). Interestingly, very simple input signals are sufficient to modulate the produced patterns. Furthermore, CPG can adapt to various environments by changing the periodic rhythmic patterns. For instance, the cats and horses are able to change their locomotor patterns depending on the situation. This relevance of locomotion both for biology and for robotics has led to multiple interesting interactions between the two fields. The interactions have mainly been in one direction, with robotics taking inspiration from biology in terms of morphologies, modes of locomotion, and/or control mechanisms. In particular, many robot structures are directly inspired by animal morphologies, from snake robots, quadruped robots, to humanoid robots. Increasingly, robotics is now providing something back to biology, with robots being used 9

Two-phase GA parameter tunning method of CPGs for quadruped gaits

Nowadays, the locomotion control research field has been pretty active and has produced different approaches for legged robots. From biological studies, it is known that fundamental rhythmic periodical signals for locomotion are produced by Central Pattern Generator (CPG) and the main part of the coordination takes place in the central nervous system. In spite of the CPG-utility, there are few training methodologies to generate the rhythmic signals based in CPG models. In this paper, an automatic method to find the synaptic weights to generate three basic gaits using Genetic Algorithms (GA) is presented. The method is based on the analysis of the oscillator behavior and its interactions with other oscillators, in a network. The oscillator model used in this work is the proposed by Van Der Pol (VDP). A two-phase GA is adapted: (i) to find the parameter values to produce oscillations and (ii) to generate the weight values of the interconnections between oscillators. The results show the feasibility of the presented method to find the parameters to generate different gaits. The implementation takes advantage that the fitness function works directly with the oscillator and the network. So, knowledge about the robot dynamic is not necessary. The GA based approach uses small population and limited numbers of generations, ideal to be processed on either computers with reduced resources or hardware implementations.

Perception-driven adaptive CPG-based locomotion for hexapod robots

According to neurobiological studies, rhythmic motion in animals is controlled by neural circuits known as central pattern generators (CPGs), which are robust against transient perturbations. Yet, CPGs can integrate sensory feedback that potentially enables adaptive locomotion solutions. Despite previous works, the construction of practical embedded neuromorphic locomotion systems exhibiting similar properties and organization observed in CPGs is still reduced. In this paper a CPG-based control strategy able to modulate motion speed and manage smoothly gait transitions in hexapod robots according to visual information is proposed. Fuzzy logic and finite state machines are the base of the proposed integration mechanism used to map perception into locomotion parameters according to a sensed situation. A vision sensor is integrated in the CPG-based control loop to provide feedback in obstacle avoidance and target tracking behaviors within simplified experimental environments. Experimental results using an hexapod robot confirm both the effectiveness of the proposed control strategy and its use as an experimental embedded platform to investigate further adaptive locomotion, particularly about ways that biological systems fuse information from visual cues to adapt locomotion.

FPGA-based CPG Robot Locomotion Modulation Using a Fuzzy Scheme and Visual Information

Locomotion and visual information have been treated as separated problems in the field of robotics. However the locomotion and vision should be connected or interact as suggested by biological evidence, i.e., to change from visual information domain to locomotion domain. Mathematically, this problem consists in finding the function that maps from the visual information to locomotion parameters. Some authors consider creating a direct coupling of visual perception to action, and others have proposed to use map planing. These implementations require a huge knowledge base or the solution is computationally intense and too slow for real-time. From these necessities, a feasible function based on fuzzy logic (FL) to be implemented in field programmable gate array (FPGA) is proposed. The presented function is composed by blocks that compute the basic arithmetic operations that use fixed point arithmetic and are configurable. This advantage let to have a multi precision fixed point arithmetic in each stage of the function. As a result, the function based on FL requires few FPGA resources and is able to map between the different maps. Also, it is possible to be used in autonomous robots with size and power consumption restrictions.

Versatile FPGA-based locomotion platform for legged robots

Usually, most mobile robots have been equipped with wheels because they are easy to control but they require a flat surface on which to operate. Walking machines have been proposed to overpass the limits of wheeled systems by looking at legged solutions in nature. Legged systems can be slow and more difficult to design and operate with respect to wheeled machines. These robots present dozens of degrees of freedom that must be controlled with ability, flexibility and energy efficiency. Under this scenario, a versatile FPGA platform for legged robot is presented. The platform is able to control servomotors through pulse-width modulation (PWM) signals that are usually used to control these kind of motors. The proposed platform is powerful in terms of locomotion capabilities, concurrency and coordination. The platform modules work in parallel and will be synchronized by a soft-processor through a C-based application. Physical testing based on Phoenix hexapod robot and CPG-based locomotion control has confirmed the locomotion hardware platform functionality. The implementation provides flexibility to add more custom modules for different kind of sensors, suitable for autonomous locomotion and the implementation is feasible to be used in different robots.

An FPGA-based approach for parameter estimation in spiking neural networks

We present an FPGA-based approach for estimating the delayed synaptic weights of spiking neural networks. Our approach makes explicit use of the fact that reverse engineering of a spiking neural network can be cast as a linear programming problem, whereby the objective function is based on the network spiking activity. The solution is obtained by employing the widely used simplex algorithm. Numerical results on a Xilinx Spartan 3 FPGA board show that the present approach can be used to reproduce a desired output from the observed network spiking activity.

Reaction diffusion and chemotaxis for decentralized gathering on FPGAs

We consider here the feasibility of gathering multiple computational resources by means of decentralized and simple local rules. We study such decentralized gathering by means of a stochastic model inspired from biology: the aggregation of the Dictyostelium discoideum cellular slime mold. The environment transmits information according to a reaction-diffusion mechanism and the agents move by following excitation fronts. Despite its simplicity this model exhibits interesting properties of self-organization and robustness to obstacles. We first describe the FPGA implementation of the environment alone, to perform large scale and rapid simulations of the complex dynamics of this reaction-diffusion model. Then we describe the FPGA implementation of the environment together with the agents, to study the major challenges that must be solved when designing a fast embedded implementation of the decentralized gathering model. We analyze the results according to the different goals of these hardware implementations.