Related papers: Tailoring interactions between active nematic defe…

We use continuum simulations to study the impact of anisotropic hydrodynamic friction on the emergent flows of active nematics. We show that, depending on whether the active particles align with or tumble in their collectively self-induced…

Urban autonomous driving decision making is challenging due to complex road geometry and multi-agent interactions. Current decision making methods are mostly manually designing the driving policy, which might result in sub-optimal solutions…

Efficient exploration has presented a long-standing challenge in reinforcement learning, especially when rewards are sparse. A developmental system can overcome this difficulty by learning from both demonstrations and self-exploration.…

Fluid-structure interactions between active and passive components are important for many biological systems to function. A particular example is chromatin in the cell nucleus, where ATP-powered processes drive coherent motions of the…

Active forces occurring within cells can drive crucial biological processes that involve spontaneous organization and shape change, such as cell division. Motivated by recent in vitro experiments of nematic droplets of cytoskeletal…

In practical applications, we can rarely assume full observability of a system's environment, despite such knowledge being important for determining a reactive control system's precise interaction with its environment. Therefore, we propose…

Training sophisticated agents for optimal decision-making under uncertainty has been key to the rapid development of modern autonomous systems across fields. Notably, model-free reinforcement learning (RL) has enabled decision-making agents…

Despite the growing interest in robot control utilizing the computation of biological neurons, context-dependent behavior by neuron-connected robots remains a challenge. Context-dependent behavior here is defined as behavior that is not the…

This paper presents a novel model-reference reinforcement learning algorithm for the intelligent tracking control of uncertain autonomous surface vehicles with collision avoidance. The proposed control algorithm combines a conventional…

In this paper, a new reinforcement learning approach is proposed which is based on a powerful concept named Active Learning Method (ALM) in modeling. ALM expresses any multi-input-single-output system as a fuzzy combination of some…

Active processes drive and guide biological dynamics across scales -- from subcellular cytoskeletal remodelling, through tissue development in embryogenesis, to population-level bacterial colonies expansion. In each of these, biological…

This paper presents a reinforcement learning-based neuroadaptive control framework for robotic manipulators operating under deferred constraints. The proposed approach improves traditional barrier Lyapunov functions by introducing a smooth…

Active learning is a decision-making process. In both abstract and physical settings, active learning demands both analysis and action. This is a review of active learning in robotics, focusing on methods amenable to the demands of embodied…

Many high-performance human activities are executed with little or no external feedback: think of a figure skater landing a triple jump, a pitcher throwing a curveball for a strike, or a barista pouring latte art. To study the process of…

Machine-learning force fields enable an accurate and universal description of the potential energy surface of molecules and materials on the basis of a training set of ab initio data. However, large-scale applications of these methods rest…

Variable impedance control in operation-space is a promising approach to learning contact-rich manipulation behaviors. One of the main challenges with this approach is producing a manipulation behavior that ensures the safety of the arm and…

Cellular reprogramming can be used for both the prevention and cure of different diseases. However, the efficiency of discovering reprogramming strategies with classical wet-lab experiments is hindered by lengthy time commitments and high…

This study investigates a method to guide and control fish schools using virtual fish trained with reinforcement learning. We utilize 2D virtual fish displayed on a screen to overcome technical challenges such as durability and movement…

Model-based reinforcement learning attempts to use an available or learned model to improve the data efficiency of reinforcement learning. This work proposes a one-step lookback approach that jointly learns the deep incremental model and…

Navigation problems under unknown varying conditions are among the most important and well-studied problems in the control field. Classic model-based adaptive control methods can be applied only when a convenient model of the plant or…