Full-state tracking control of a mobile robot using neural networks

In this paper a nonholonomic mobile robot with completely unknown dynamics is discussed. A mathematical model has been considered and an efficient neural network is developed, which ensures guaranteed tracking performance leading to stability of the system. The neural network assumes a single layer structure, by taking advantage of the robot regressor dynamics that expresses the highly nonlinear robot dynamics in a linear form in terms of the known and unknown robot dynamic parameters. No assumptions relating to the boundedness is placed on the unmodeled disturbances. It is capable of generating real-time smooth and continuous velocity control signals that drive the mobile robot to follow the desired trajectories. The proposed approach resolves speed jump problem existing in some previous tracking controllers. Further, this neural network does not require offline training procedures. Lyapunov theory has been used to prove system stability. The practicality and effectiveness of the proposed tracking controller are demonstrated by simulation and comparison results.     

Analysis and implementation of a neural extended Kalman filter for target tracking

Having a better motion model in the state estimator is one way to improve target tracking performance. Since the motion model of the target is not known a priori, either robust modeling techniques or adaptive modeling techniques are required. The neural extended Kalman filter is a technique that learns unmodeled dynamics while performing state estimation in the feedback loop of a control system. This coupled system performs the standard estimation of the states of the plant while estimating a function to approximate the difference between the given state-coupling function model and the behavior of the true plant dynamics. At each sample step, this new model is added to the existing model to improve the state estimate. The neural extended Kalman filter has also been investigated as a target tracking estimation routine. Implementation issues for this adaptive modeling technique, including neural network training parameters, were investigated and an analysis was made of the quality of performance that the technique can have for tracking maneuvering targets.     

Resonant hopping of a robot controlled by an artificial neural oscillator

The bouncing gaits of terrestrial animals (hopping, running, trotting) can be modeled as a hybrid dynamic system, with spring-mass dynamics during stance and ballistic motion during the aerial phase. We used a simple hopping robot controlled by an artificial neural oscillator to test the ability of the neural oscillator to adaptively drive this hybrid dynamic system. The robot had a single joint, actuated by an artificial pneumatic muscle in series with a tendon spring. We examined how the oscillator-robot system responded to variation in two neural control parameters: descending neural drive and neuromuscular gain. We also tested the ability of the oscillator-robot system to adapt to variations in mechanical properties by changing the series and parallel spring stiffnesses. Across a 100-fold variation in both supraspinal gain and muscle gain, hopping frequency changed by less than 10%. The neural oscillator consistently drove the system at the resonant half-period for the stance phase, and adapted to a new resonant half-period when the muscle series and parallel stiffnesses were altered. Passive cycling of elastic energy in the tendon accounted for 70-79% of the mechanical work done during each hop cycle. Our results demonstrate that hopping dynamics were largely determined by the intrinsic properties of the mechanical system, not the specific choice of neural oscillator parameters. The findings provide the first evidence that an artificial neural oscillator will drive a hybrid dynamic system at partial resonance.     

Application of chaotic dynamics in a recurrent neural network to control: hardware implementation into a novel autonomous roving robot

Originating from a viewpoint that complex/chaotic dynamics would play an important role in biological system including brains, chaotic dynamics introduced in a recurrent neural network was applied to control. The results of computer experiment was successfully implemented into a novel autonomous roving robot, which can only catch rough target information with uncertainty by a few sensors. It was employed to solve practical two-dimensional mazes using adaptive neural dynamics generated by the recurrent neural network in which four prototype simple motions are embedded. Adaptive switching of a system parameter in the neural network results in stationary motion or chaotic motion depending on dynamical situations. The results of hardware implementation and practical experiment using it show that, in given two-dimensional mazes, the robot can successfully avoid obstacles and reach the target. Therefore, we believe that chaotic dynamics has novel potential capability in controlling, and could be utilized to practical engineering application.     

Novel tracking function of moving target using chaotic dynamics in a recurrent neural network model

Chaotic dynamics introduced in a recurrent neural network model is applied to controlling an object to track a moving target in two-dimensional space, which is set as an ill-posed problem. The motion increments of the object are determined by a group of motion functions calculated in real time with firing states of the neurons in the network. Several cyclic memory attractors that correspond to several simple motions of the object in two-dimensional space are embedded. Chaotic dynamics introduced in the network causes corresponding complex motions of the object in two-dimensional space. Adaptively real-time switching of control parameter results in constrained chaos (chaotic itinerancy) in the state space of the network and enables the object to track a moving target along a certain trajectory successfully. The performance of tracking is evaluated by calculating the success rate over 100 trials with respect to nine kinds of trajectories along which the target moves respectively. Computer experiments show that chaotic dynamics is useful to track a moving target. To understand the relations between these cases and chaotic dynamics, dynamical structure of chaotic dynamics is investigated from dynamical viewpoint.     

A Bio-Inspired Hopping Kangaroo Robot with an Active Tail

Inspired by kangaroo＇s locomotion, we report on developing a kangaroo-style hopping robot. Unlike bipeds, quadrupeds, or hexapods which altemate the legs for forward locomotion, the kangaroo uses both legs synchronously and generates the forward locomotion by continuous hopping behavior, and the tail actively balances the unwanted angular momentum generated by the leg motion. In this work, we generate the Center of Mass （CoM） locomotion of the robot based on the reduced-order Rolling Spring Loaded Inverted Pendulum （R-SLIP） model, for matching the dynamic behavior of the empirical robot legs. In order to compensate the possible body pitch variation, the robot is equipped with an active tail for pitch variation compensation, emulating the balance mechanism of a kangaroo. The robot is empirically built, and various design issues and strategies are addressed. Finally, the experimental evaluation is executed to validate the performance of the kangaroo-style robot with hopping locomotion.     

Supervised Neural Q_learning based Motion Control for Bionic Underwater Robots

Bionic underwater robots have been a hot research area in recent years. The motion control methods for a kind of bionic underwater robot with two undulating fins are discussed in this paper. The equations of motion for the bionic underwater robot are described. To apply the reinforcement learning to the actual robot control, a Supervised Neural Q_learning (SNQL) algorithm is put forward. This algorithm is based on conventional Q_learning algorithm, but has three remarkable distinctions: (1) using a feedforward neural network to approximate the Q_function table; (2) adopting a learning sample database to speed up learning and improve the stability of learning system; (3) introducing a supervised control in the earlier stage of learning for safety and to speed up learning again. Experiments of swimming straightforward are carried out with SNQL algorithm. Results indicate that the SNQL algorithm is more effective than pure neural Q_learning or supervised control. It is a feasible approach to figure out the motion control for bionic underwater robots.     

Mantisbot is a robotic model of visually guided motion in the praying mantis

Insects use highly distributed nervous systems to process exteroception from head sensors, compare that information with state-based goals, and direct posture or locomotion toward those goals. To study how descending commands from brain centers produce coordinated, goal-directed motion in distributed nervous systems, we have constructed a conductance-based neural system for our robot MantisBot, a 29 degree-of-freedom, 13.3:1 scale praying mantis robot. Using the literature on mantis prey tracking and insect locomotion, we designed a hierarchical, distributed neural controller that establishes the goal, coordinates different joints, and executes prey-tracking motion. In our controller, brain networks perceive the location of prey and predict its future location, store this location in memory, and formulate descending commands for ballistic saccades like those seen in the animal. The descending commands are simple, indicating only 1) whether the robot should walk or stand still, and 2) the intended direction of motion. Each joint's controller uses the descending commands differently to alter sensory-motor interactions, changing the sensory pathways that coordinate the joints' central pattern generators into one cohesive motion. Experiments with one leg of MantisBot show that visual input produces simple descending commands that alter walking kinematics, change the walking direction in a predictable manner, enact reflex reversals when necessary, and can control both static posture and locomotion with the same network.     

A biologically plausible acoustic motion detection neural network

In this paper we present an acoustic motion detection system to be used in a small mobile robot. While the first purpose of the system has been to be a reliable computational implementation, cheap enough to be built in hardware, effort has also been taken to construct a biologically plausible solution. The motion detector consists of a neural network composed of motion-direction sensitive neurons with a preferred direction and a preferred region of the azimuth. The system was designed to produce a higher response when stimulated by motion in the preferred direction than in the null direction and that is in fact what the system does, which means that, as desired, the system can detect motion and distinguish its direction.     

Nonlinear torque and air-to-fuel ratio control of spark ignition engines using neuro-sliding mode techniques

This paper presents a new approach for the calibration and control of spark ignition engines using a combination of neural networks and sliding mode control technique. Two parallel neural networks are utilized to realize a neuro-sliding mode control (NSLMC) for self-learning control of automotive engines. The equivalent control and the corrective control terms are the outputs of the neural networks. Instead of using error backpropagation algorithm, the network weights of equivalent control are updated using the Levenberg-Marquardt algorithm. Moreover, a new approach is utilized to update the gain of corrective control. Both modifications of the NSLMC are aimed at improving the transient performance and speed of convergence. Using the data from a test vehicle with a V8 engine, we built neural network models for the engine torque (TRQ) and the air-to-fuel ratio (AFR) dynamics and developed NSLMC controllers to achieve tracking control. The goal of TRQ control and AFR control is to track the commanded values under various operating conditions. From simulation studies, the feasibility and efficiency of the approach are illustrated. For both control problems, excellent tracking performance has been achieved.     

Bionic Mechanism and Kinematics Analysis of Hopping Robot Inspired by Locust Jumping

A flexible-rigid hopping mechanism which is inspired by the locust jumping was proposed,and its kinematic characteristics were analyzed.A series of experiments were conducted to observe locust morphology and jumping process.According to classic mechanics,the jumping process analysis was conducted to build the relationship of the locust jumping parameters.The take-off phase was divided into four stages in detail.Based on the biological observation and kinematics analysis,a mechanical model was proposed to simulate locust jumping.The forces of the flexible-rigid hopping mechanism at each stage were analyzed.The kinematic analysis using pseudo-rigid-body model was described by D-H method.It is confirmed that the proposed bionic mechanism has the similar performance as the locust hind leg in hopping.Moreover,the jumping angle which decides the jumping process was discussed,and its relation with other parameters was established.A calculation case analysis corroborated the method.The results of this paper show that the proposed bionic mechanism which is inspired by the locust hind limb has an excellent kinematics performance,which can provide a foundation for design and motion planning of the hopping robot.     

Chaotic neural network applied to two-dimensional motion control

Chaotic dynamics generated in a chaotic neural network model are applied to 2-dimensional (2-D) motion control. The change of position of a moving object in each control time step is determined by a motion function which is calculated from the firing activity of the chaotic neural network. Prototype attractors which correspond to simple motions of the object toward four directions in 2-D space are embedded in the neural network model by designing synaptic connection strengths. Chaotic dynamics introduced by changing system parameters sample intermediate points in the high-dimensional state space between the embedded attractors, resulting in motion in various directions. By means of adaptive switching of the system parameters between a chaotic regime and an attractor regime, the object is able to reach a target in a 2-D maze. In computer experiments, the success rate of this method over many trials not only shows better performance than that of stochastic random pattern generators but also shows that chaotic dynamics can be useful for realizing robust, adaptive and complex control function with simple rules.     

Motion planning with complete knowledge using a colored SOM

The motion planning problem requires that a collision-free path be determined for a robot moving amidst a fixed set of obstacles. Most neural network approaches to this problem are for the situation in which only local knowledge about the configuration space is available. The main goal of the paper is to show that neural networks are also suitable tools in situations with complete knowledge of the configuration space. In this paper we present an approach that combines a neural network and deterministic techniques. We define a colored version of Kohonen's self-organizing map that consists of two different classes of nodes. The network is presented with random configurations of the robot and, from this information, it constructs a road map of possible motions in the work space. The map is a growing network, and different nodes are used to approximate boundaries of obstacles and the Voronoi diagram of the obstacles, respectively. In a second phase, the positions of the two kinds of nodes are combined to obtain the road map. In this way a number of typical problems with small obstacles and passages are avoided, and the required number of nodes for a given accuracy is within reasonable limits. This road map is searched to find a motion connecting the given source and goal configurations of the robot. The algorithm is simple and general; the only specific computation that is required is a check for intersection of two polygons. We implemented the algorithm for planar robots allowing both translation and rotation and experiments show that compared to conventional techniques it performs well, even for difficult motion planning scenes.     

CPG Control for Biped Hopping Robot in Unpredictable Environment

A CPG control mechanism is proposed for hopping motion control of biped robot in unpredictable environment.Based on analysis of robot motion and biological observation of animal's control mechanism,the motion control task is divided into two simple parts:motion sequence control and output force control.Inspired by a two-level CPG model,a two-level CPG control mechanism is constructed to coordinate the drivers of robot joint,while various feedback information are introduced into the control mechanism.Interneurons within the control mechanism are modeled to generate motion rhythm and pattern promptly for motion sequence control; motoneurons are modeled to control output forces of joint drivers in real time according to feedbacks.The control system can perceive changes caused by unknown perturbations and environment changes according to feedback information,and adapt to unpredictable environment by adjusting outputs of neurons.The control mechanism is applied to a biped hopping robot in unpredictable environment on simulation platform,and stable adaptive motions are obtained.     

A Novel Robot System Integrating Biological and Mechanical Intelligence Based on Dissociated Neural Network-Controlled Closed-Loop Environment

We propose the architecture of a novel robot system merging biological and artificial intelligence based on a neural controller connected to an external agent. We initially built a framework that connected the dissociated neural network to a mobile robot system to implement a realistic vehicle. The mobile robot system characterized by a camera and two-wheeled robot was designed to execute the target-searching task. We modified a software architecture and developed a home-made stimulation generator to build a bi-directional connection between the biological and the artificial components via simple binomial coding/decoding schemes. In this paper, we utilized a specific hierarchical dissociated neural network for the first time as the neural controller. Based on our work, neural cultures were successfully employed to control an artificial agent resulting in high performance. Surprisingly, under the tetanus stimulus training, the robot performed better and better with the increasement of training cycle because of the short-term plasticity of neural network (a kind of reinforced learning). Comparing to the work previously reported, we adopted an effective experimental proposal (i.e. increasing the training cycle) to make sure of the occurrence of the short-term plasticity, and preliminarily demonstrated that the improvement of the robot’s performance could be caused independently by the plasticity development of dissociated neural network. This new framework may provide some possible solutions for the learning abilities of intelligent robots by the engineering application of the plasticity processing of neural networks, also for the development of theoretical inspiration for the next generation neuro-prostheses on the basis of the bi-directional exchange of information within the hierarchical neural networks.     

Real-time tumor tracking with an artificial neural networks-based method: A feasibility study

The purpose of this study was to develop and assess the performance of a tumor tracking method designed for application in radiation therapy. This motion compensation strategy is currently applied clinically only in conventional photon radiotherapy but not in particle therapy, as greater accuracy in dose delivery is required.We proposed a tracking method that exploits artificial neural networks to estimate the internal tumor trajectory as a function of external surrogate signals. The developed algorithm was tested by means of a retrospective clinical data analysis in 20 patients, who were treated with state of the art infra-red motion tracking for photon radiotherapy, which is used as a benchmark. Integration into a hardware platform for motion tracking in particle therapy was performed and then tested on a moving phantom, specifically developed for this purpose.Clinical data show that a median tracking error reduction up to 0.7 mm can be achieved with respect to state of the art technologies. The phantom study demonstrates that a real-time tumor position estimation is feasible when the external signals are acquired at 60 Hz.The results of this work show that neural networks can be considered a valuable tool for the implementation of high accuracy real-time tumor tracking methodologies.     

From 1D to 2D via 3D: dynamics of surface motion segmentation for ocular tracking in primates.

In primates, tracking eye movements help vision by stabilising onto the retinas the images of a moving object of interest. This sensorimotor transformation involves several stages of motion processing, from the local measurement of one-dimensional luminance changes up to the integration of first and higher-order local motion cues into a global two-dimensional motion immune to antagonistic motions arising from the surrounding. The dynamics of this surface motion segmentation is reflected into the various components of the tracking responses and its underlying neural mechanisms can be correlated with behaviour at both single-cell and population levels. I review a series of behavioural studies which demonstrate that the neural representation driving eye movements evolves over time from a fast vector average of the outputs of linear and non-linear spatio-temporal filtering to a progressive and slower accurate solution for global motion. Because of the sensitivity of earliest ocular following to binocular disparity, antagonistic visual motion from surfaces located at different depths are filtered out. Thus, global motion integration is restricted within the depth plane of the object to be tracked. Similar dynamics were found at the level of monkey extra-striate areas MT and MST and I suggest that several parallel pathways along the motion stream are involved albeit with different latencies to build-up this accurate surface motion representation. After 200-300 ms, most of the computational problems of early motion processing (aperture problem, motion integration, motion segmentation) are solved and the eye velocity matches the global object velocity to maintain a clear and steady retinal image.     

Toward Fast and Efficient Mobility in Aquatic Environment: A Robot with Compliant Swimming Appendages Inspired by a Water Beetle

Water beetles are proficient drag-powered swimmers,with oar-like legs.Inspired by this mechamsm,here we propose a miniature robot,with mobility provided by a pair of legs with swimming appendages.The robot has optimized linkage structure to maximize the stroke angle,which is actuated by a single DC motor with a series of gears and a spring.A simplified swimming appendage model is proposed to calculate the deflection due to the applied drag force,and is compared with simulated data using COMSOL Multiphysics.Also,the swimming appendages are optimized by considering their locations on the legs using two fitness functions,and six different configurations are selected.We investigate the performance of the robot with various types of appendage using a high-speed camera,and motion capture cameras.The robot with the proposed configuration exhibits fast and efficient movement compared with other robots.In addition,the locomotion of the robot is analyzed by considering its dynamics,and compared with that of a water boatman (Corixidae).     

Motion-based prediction explains the role of tracking in motion extrapolation

During normal viewing, the continuous stream of visual input is regularly interrupted, for instance by blinks of the eye. Despite these frequents blanks (that is the transient absence of a raw sensory source), the visual system is most often able to maintain a continuous representation of motion. For instance, it maintains the movement of the eye such as to stabilize the image of an object. This ability suggests the existence of a generic neural mechanism of motion extrapolation to deal with fragmented inputs. In this paper, we have modeled how the visual system may extrapolate the trajectory of an object during a blank using motion-based prediction. This implies that using a prior on the coherency of motion, the system may integrate previous motion information even in the absence of a stimulus. In order to compare with experimental results, we simulated tracking velocity responses. We found that the response of the motion integration process to a blanked trajectory pauses at the onset of the blank, but that it quickly recovers the information on the trajectory after reappearance. This is compatible with behavioral and neural observations on motion extrapolation. To understand these mechanisms, we have recorded the response of the model to a noisy stimulus. Crucially, we found that motion-based prediction acted at the global level as a gain control mechanism and that we could switch from a smooth regime to a binary tracking behavior where the dot is tracked or lost. Our results imply that a local prior implementing motion-based prediction is sufficient to explain a large range of neural and behavioral results at a more global level. We show that the tracking behavior deteriorates for sensory noise levels higher than a certain value, where motion coherency and predictability fail to hold longer. In particular, we found that motion-based prediction leads to the emergence of a tracking behavior only when enough information from the trajectory has been accumulated. Then, during tracking, trajectory estimation is robust to blanks even in the presence of relatively high levels of noise. Moreover, we found that tracking is necessary for motion extrapolation, this calls for further experimental work exploring the role of noise in motion extrapolation.     

A neurodynamic account of spontaneous behaviour

The current article suggests that deterministic chaos self-organized in cortical dynamics could be responsible for the generation of spontaneous action sequences. Recently, various psychological observations have suggested that humans and primates can learn to extract statistical structures hidden in perceptual sequences experienced during active environmental interactions. Although it has been suggested that such statistical structures involve chunking or compositional primitives, their neuronal implementations in brains have not yet been clarified. Therefore, to reconstruct the phenomena, synthetic neuro-robotics experiments were conducted by using a neural network model, which is characterized by a generative model with intentional states and its multiple timescales dynamics. The experimental results showed that the robot successfully learned to imitate tutored behavioral sequence patterns by extracting the underlying transition probability among primitive actions. An analysis revealed that a set of primitive action patterns was embedded in the fast dynamics part, and the chaotic dynamics of spontaneously sequencing these action primitive patterns was structured in the slow dynamics part, provided that the timescale was adequately set for each part. It was also shown that self-organization of this type of functional hierarchy ensured robust action generation by the robot in its interactions with a noisy environment. This article discusses the correspondence of the synthetic experiments with the known hierarchy of the prefrontal cortex, the supplementary motor area, and the primary motor cortex for action generation. We speculate that deterministic dynamical structures organized in the prefrontal cortex could be essential because they can account for the generation of both intentional behaviors of fixed action sequences and spontaneous behaviors of pseudo-stochastic action sequences by the same mechanism.