Related papers: A numerical simulation method of fish adaption beh…
Reproducing the diverse and agile locomotion skills of animals has been a longstanding challenge in robotics. While manually-designed controllers have been able to emulate many complex behaviors, building such controllers involves a…
We present an online model-based reinforcement learning algorithm suitable for controlling complex robotic systems directly in the real world. Unlike prevailing sim-to-real pipelines that rely on extensive offline simulation and model-free…
Soft robots are intrinsically capable of adapting to different environments by changing their shape in response to interaction forces with the environment. However, sensing and feedback are still required for higher level decisions and…
Training neural networks with large batch is of fundamental significance to deep learning. Large batch training remarkably reduces the amount of training time but has difficulties in maintaining accuracy. Recent works have put forward…
Computational Fluid Dynamics (CFD) is a hugely important subject with applications in almost every engineering field, however, fluid simulations are extremely computationally and memory demanding. Towards this end, we present Lat-Net, a…
Bayesian inference promises to ground and improve the performance of deep neural networks. It promises to be robust to overfitting, to simplify the training procedure and the space of hyperparameters, and to provide a calibrated measure of…
Navigating human-filled spaces is crucial for the interactive social robots to support advanced services, such as cooperative carrying, which enables service provision in complex and crowded environments while adapting behavior based on…
Computational scientists have investigated swimming performance across a multitude of different systems for decades. Most models depend on numerous model parameters and performance is sensitive to those parameters. In this paper, parameter…
Linear dynamical systems that obey stochastic differential equations are canonical models. While optimal control of known systems has a rich literature, the problem is technically hard under model uncertainty and there are hardly any…
Machine learning algorithms, and more in particular neural networks, arguably experience a revolution in terms of performance. Currently, the best systems we have for speech recognition, computer vision and similar problems are based on…
Researchers have long debated which spatial arrangements and swimming synchronizations are beneficial for the hydrodynamic performance of fish in schools. In our previous work (Seo and Mittal, Bioinsp. Biomim., Vol. 17, 066020, 2022), we…
Nature has always inspired scientists and engineers to understand the underlying mechanism leading to optimal design in bio-inspired dynamics. This study presents a computational framework for optimizing undulatory swimming profiles using a…
In recent years, deep reinforcement learning has emerged as a technique to solve closed-loop flow control problems. Employing simulation-based environments in reinforcement learning enables a priori end-to-end optimization of the control…
We address the problem of estimating the inputs of a dynamical system from measurements of the system's outputs. To this end, we introduce a novel estimation algorithm that explicitly trades off bias and variance to optimally reduce the…
High-precision displacement control for water-hydraulic artificial muscles is a challenging issue due to its strong hysteresis characteristics that is hard to be modelled precisely, and many control methods have been proposed. Recently,…
Adversarial Imitation Learning (AIL) is a broad family of imitation learning methods designed to mimic expert behaviors from demonstrations. While AIL has shown state-of-the-art performance on imitation learning with only small number of…
Domain-adaptive trajectory imitation is a skill that some predators learn for survival, by mapping dynamic information from one domain (their speed and steering direction) to a different domain (current position of the moving prey). An…
Multi-armed bandit (MAB) is a class of online learning problems where a learning agent aims to maximize its expected cumulative reward while repeatedly selecting to pull arms with unknown reward distributions. We consider a scenario where…
Symbolic task representation is a powerful tool for encoding human instructions and domain knowledge. Such instructions guide robots to accomplish diverse objectives and meet constraints through reinforcement learning (RL). Most existing…
We introduce Flickering Multi-Armed Bandits (FMAB) to model sequential decision-making in environments with changing action availability, where accessibility of the next action is restricted to a subset dependent on the agent's current…