Echo State Networks for Estimating Exteroceptive Conditions From Proprioceptive States in Quadruped Robots.
Ontology highlight
ABSTRACT:
SUBMITTER: Calandra M
PROVIDER: S-EPMC8421012 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:As one of the most important paradigms of recurrent neural networks, the echo state network (ESN) has been applied to a wide range of fields, from robotics to medicine, finance, and language processing. A key feature of the ESN paradigm is its reservoir-a directed and weighted network of neurons that projects the input time series into a high-dimensional space where linear regression or classification can be applied. By analyzing the dynamics of the reservoir we show that the ensemble of eigenvalues of the network contributes to the ESN memory capacity. Moreover, we find that adding short loops to the reservoir network can tailor ESN for specific tasks and optimize learning. We validate our findings by applying ESN to forecast both synthetic and real benchmark time series. Our results provide a simple way to design task-specific ESN and offer deep insights for other recurrent neural networks.
| S-EPMC7452343 | biostudies-literature
Project description:Stability is a prerequisite for legged robots to execute tasks and traverse rough terrains. To guarantee the stability of quadruped locomotion and improve the terrain adaptability of quadruped robots, a stability-guaranteed and high terrain adaptability static gait for quadruped robots is addressed. Firstly, three chosen stability-guaranteed static gaits: intermittent gait 1&2 and coordinated gait are investigated. In addition, then the static gait: intermittent gait 1, which is with the biggest stability margin, is chosen to do a further research about quadruped robots walking on rough terrains. Secondly, a position/force based impedance control is employed to achieve a compliant behavior of quadruped robots on rough terrains. Thirdly, an exploratory gait planning method on uneven terrains with touch sensing and an attitude-position adjustment strategy with terrain estimation are proposed to improve the terrain adaptability of quadruped robots. Finally, the proposed methods are validated by simulations.
| S-EPMC7506578 | biostudies-literature
Project description:In the context of legged robotics, many criteria based on the control of the Center of Mass (CoM) have been developed to ensure a stable and safe robot locomotion. Defining a whole-body framework with the control of the CoM requires a planning strategy, often based on a specific type of gait and a reliable state-estimation. In a whole-body control approach, if the CoM task is not specified, the consequent redundancy can still be resolved by specifying a postural task that set references for all the joints. Therefore, the postural task can be exploited to keep a well-behaved, stable kinematic configuration. In this work, we propose a generic locomotion framework which is able to generate different kind of gaits, ranging from very dynamic gaits, such as the trot, to more static gaits like the crawl, without the need to plan the CoM trajectory. Consequently, the whole-body controller becomes planner-free and it does not require the estimation of the floating base state, which is often prone to drift. The framework is composed of a priority-based whole-body controller that works in synergy with a walking pattern generator. We show the effectiveness of the framework by presenting simulations on different types of simulated terrains, including rough terrain, using different quadruped platforms.
| S-EPMC7805836 | biostudies-literature
Project description:Quadruped robots require compliance to handle unexpected external forces, such as impulsive contact forces from rough terrain, or from physical human-robot interaction. This paper presents a locomotion controller using Cartesian impedance control to coordinate tracking performance and desired compliance, along with Quadratic Programming (QP) to satisfy friction cone constraints, unilateral constraints, and torque limits. First, we resort to projected inverse-dynamics to derive an analytical control law of Cartesian impedance control for constrained and underactuated systems (typically a quadruped robot). Second, we formulate a QP to compute the optimal torques that are as close as possible to the desired values resulting from Cartesian impedance control while satisfying all of the physical constraints. When the desired motion torques lead to violation of physical constraints, the QP will result in a trade-off solution that sacrifices motion performance to ensure physical constraints. The proposed algorithm gives us more insight into the system that benefits from an analytical derivation and more efficient computation compared to hierarchical QP (HQP) controllers that typically require a solution of three QPs or more. Experiments applied on the ANYmal robot with various challenging terrains show the efficiency and performance of our controller.
| S-EPMC7805892 | biostudies-literature
Project description:Recurrent cortical networks provide reservoirs of states that are thought to play a crucial role for sequential information processing in the brain. However, classical reservoir computing requires manual adjustments of global network parameters, particularly of the spectral radius of the recurrent synaptic weight matrix. It is hence not clear if the spectral radius is accessible to biological neural networks. Using random matrix theory, we show that the spectral radius is related to local properties of the neuronal dynamics whenever the overall dynamical state is only weakly correlated. This result allows us to introduce two local homeostatic synaptic scaling mechanisms, termed flow control and variance control, that implicitly drive the spectral radius toward the desired value. For both mechanisms the spectral radius is autonomously adapted while the network receives and processes inputs under working conditions. We demonstrate the effectiveness of the two adaptation mechanisms under different external input protocols. Moreover, we evaluated the network performance after adaptation by training the network to perform a time-delayed XOR operation on binary sequences. As our main result, we found that flow control reliably regulates the spectral radius for different types of input statistics. Precise tuning is however negatively affected when interneural correlations are substantial. Furthermore, we found a consistent task performance over a wide range of input strengths/variances. Variance control did however not yield the desired spectral radii with the same precision, being less consistent across different input strengths. Given the effectiveness and remarkably simple mathematical form of flow control, we conclude that self-consistent local control of the spectral radius via an implicit adaptation scheme is an interesting and biological plausible alternative to conventional methods using set point homeostatic feedback controls of neural firing.
| S-EPMC7958921 | biostudies-literature
Project description:Optimizing a neural network's topology is a difficult problem for at least two reasons: the topology space is discrete, and the quality of any given topology must be assessed by assigning many different sets of weights to its connections. These two characteristics tend to cause very "rough." objective functions. Here we demonstrate how self-assembly (SA) and particle swarm optimization (PSO) can be integrated to provide a novel and effective means of concurrently optimizing a neural network's weights and topology. Combining SA and PSO addresses two key challenges. First, it creates a more integrated representation of neural network weights and topology so that we have just a single, continuous search domain that permits "smoother" objective functions. Second, it extends the traditional focus of self-assembly, from the growth of predefined target structures, to functional self-assembly, in which growth is driven by optimality criteria defined in terms of the performance of emerging structures on predefined computational problems. Our model incorporates a new way of viewing PSO that involves a population of growing, interacting networks, as opposed to particles. The effectiveness of our method for optimizing echo state network weights and topologies is demonstrated through its performance on a number of challenging benchmark problems.
| S-EPMC4539438 | biostudies-literature
Project description:Modifying weights within a recurrent network to improve performance on a task has proven to be difficult. Echo-state networks in which modification is restricted to the weights of connections onto network outputs provide an easier alternative, but at the expense of modifying the typically sparse architecture of the network by including feedback from the output back into the network. We derive methods for using the values of the output weights from a trained echo-state network to set recurrent weights within the network. The result of this "transfer of learning" is a recurrent network that performs the task without requiring the output feedback present in the original network. We also discuss a hybrid version in which online learning is applied to both output and recurrent weights. Both approaches provide efficient ways of training recurrent networks to perform complex tasks. Through an analysis of the conditions required to make transfer of learning work, we define the concept of a "self-sensing" network state, and we compare and contrast this with compressed sensing.
| S-EPMC3360031 | biostudies-literature
Project description:We here used the technology of RNA interference and cDNA microarrays to reconstruct a network between genes known to be disregulated in ER-positive breast cancer diseases. Therefor single genes of high importance were silenced and the effect of this pertubation was measured with cDNA microarrays Keywords: network_reconstruction_RNAi human ER-positive breast cancer cell line was cultivated as described and transfection with chemically synthesized siRNAs was performed according to standard HiPerFect transfection protocol by Qiagen (Hilden, Germany) At least 4 cDNA-microarrays were hybridized in dye-swap method for the silencing of every gene of interest. To minimize off-target effects we used at least two different siRNAs per gene.
2009-01-28 | E-GEOD-7033 | biostudies-arrayexpress
Project description:One of the principal functions of human language is to allow people to coordinate joint action. This includes the description of events, requests for action, and their organization in time. A crucial component of language acquisition is learning the grammatical structures that allow the expression of such complex meaning related to physical events. The current research investigates the learning of grammatical constructions and their temporal organization in the context of human-robot physical interaction with the embodied sensorimotor humanoid platform, the iCub. We demonstrate three noteworthy phenomena. First, a recurrent network model is used in conjunction with this robotic platform to learn the mappings between grammatical forms and predicate-argument representations of meanings related to events, and the robot's execution of these events in time. Second, this learning mechanism functions in the inverse sense, i.e., in a language production mode, where rather than executing commanded actions, the robot will describe the results of human generated actions. Finally, we collect data from naïve subjects who interact with the robot via spoken language, and demonstrate significant learning and generalization results. This allows us to conclude that such a neural language learning system not only helps to characterize and understand some aspects of human language acquisition, but also that it can be useful in adaptive human-robot interaction.
| S-EPMC4018555 | biostudies-literature
Project description:Although deep learning has recently increased in popularity, it suffers from various problems including high computational complexity, energy greedy computation, and lack of scalability, to mention a few. In this paper, we investigate an alternative brain-inspired method for data analysis that circumvents the deep learning drawbacks by taking the actual dynamical behavior of biological neural networks into account. For this purpose, we develop a general framework for dynamical systems that can evolve and model a variety of substrates that possess computational capacity. Therefore, dynamical systems can be exploited in the reservoir computing paradigm, i.e., an untrained recurrent nonlinear network with a trained linear readout layer. Moreover, our general framework, called EvoDynamic, is based on an optimized deep neural network library. Hence, generalization and performance can be balanced. The EvoDynamic framework contains three kinds of dynamical systems already implemented, namely cellular automata, random Boolean networks, and echo state networks. The evolution of such systems towards a dynamical behavior, called criticality, is investigated because systems with such behavior may be better suited to do useful computation. The implemented dynamical systems are stochastic and their evolution with genetic algorithm mutates their update rules or network initialization. The obtained results are promising and demonstrate that criticality is achieved. In addition to the presented results, our framework can also be utilized to evolve the dynamical systems connectivity, update and learning rules to improve the quality of the reservoir used for solving computational tasks and physical substrate modeling.
| S-EPMC7501380 | biostudies-literature