相关论文: Recurrent Control Nets for Deep Reinforcement Lear…

Neuromorphic computing systems, where information is transmitted through action potentials in a bio-plausible fashion, is gaining increasing interest due to its promise of low-power event-driven computing. Application of neuromorphic…

This paper introduces a new generative deep learning network for human motion synthesis and control. Our key idea is to combine recurrent neural networks (RNNs) and adversarial training for human motion modeling. We first describe an…

Recurrent Neural Networks (RNNs) are popular models of brain function. The typical training strategy is to adjust their input-output behavior so that it matches that of the biological circuit of interest. Even though this strategy ensures…

Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable…

It is widely accepted that the complex dynamics characteristic of recurrent neural circuits contributes in a fundamental manner to brain function. Progress has been slow in understanding and exploiting the computational power of recurrent…

This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data. Precisely, GCRN is a generalization of classical recurrent neural networks (RNN) to data structured by…

Inspired by biological motion generation, central pattern generators (CPGs) is frequently employed in legged robot locomotion control to produce natural gait pattern with low-dimensional control signals. However, the limited adaptability…

Owing to their superior modeling capabilities, gated Recurrent Neural Networks, such as Gated Recurrent Units (GRUs) and Long Short-Term Memory networks (LSTMs), have become popular tools for learning dynamical systems. This paper aims to…

In this letter, we present a method for integrating central pattern generators (CPGs), i.e. systems of coupled oscillators, into the deep reinforcement learning (DRL) framework to produce robust and omnidirectional quadruped locomotion. The…

Animals possess a remarkable ability to navigate challenging terrains, achieved through the interplay of various pathways between the brain, central pattern generators (CPGs) in the spinal cord, and musculoskeletal system. Traditional…

Neural circuits in the brain perform a variety of essential functions, including input classification, pattern completion, and the generation of rhythms and oscillations that support processes such as breathing and locomotion. There is also…

Recurrent Neural Networks (RNNs) are among the most successful machine learning models for sequence modelling, but tend to suffer from an exponential increase in the number of parameters when dealing with large multidimensional data. To…

Learning to walk -- i.e., learning locomotion under performance and energy constraints continues to be a challenge in legged robotics. Methods such as stochastic gradient, deep reinforcement learning (RL) have been explored for bipeds,…

Temporal models based on recurrent neural networks have proven to be quite powerful in a wide variety of applications. However, training these models often relies on back-propagation through time, which entails unfolding the network over…

The pharmaceutical industry has witnessed exponential growth in transforming operations towards continuous manufacturing to effectively achieve increased profitability, reduced waste, and extended product range. Model Predictive Control…

Legged locomotion is a challenging task in the field of robotics but a rather simple one in nature. This motivates the use of biological methodologies as solutions to this problem. Central pattern generators are neural networks that are…

Central Pattern Generators (CPGs) in invertebrates are comprised of networks of neurons in which every neuron has reciprocal connections to other members of the CPG. This is a ``closed'' network topology. An ``open'' topology, where one or…

We propose a framework based on Recurrent Neural Networks (RNNs) to determine an optimal control strategy for a discrete-time system that is required to satisfy specifications given as Signal Temporal Logic (STL) formulae. RNNs can store…

Recurrent neural networks (RNNs) for reinforcement learning (RL) have shown distinct advantages, e.g., solving memory-dependent tasks and meta-learning. However, little effort has been spent on improving RNN architectures and on…

We present a model of the central pattern generator (CPG) network that can control gait transitions in hexapod robots in a simple manner based on phase reduction. The CPG network consists of six weakly coupled limit-cycle oscillators, whose…