Equipping micro‐/nanoscale colloidal robots with artificial intelligence (AI) such that they can efficiently navigate in unknown complex environments can dramatically impact their use in emerging applications such as precision surgery and targeted nanodrug delivery. Herein, a model‐free deep reinforcement learning algorithm is developed that trains colloidal robots to efficiently navigate in unknown environments with random obstacles. A deep neural network architecture is used that enables the colloidal robots to mimic animal navigation decision‐making by directly processing raw sensor input and decomposing long‐range navigations to short‐range ones. The trained robot agents learn to make navigation decisions regarding both obstacle avoidance and travel time minimization, based solely on local sensory inputs without prior knowledge of the global environment. Such agents with biologically inspired mechanisms can acquire competitive navigation capabilities in large‐scale, complex environments containing obstacles of diverse shapes, sizes, and configurations. Herein, the potential of AI to enable colloidal robots in extensive applications is illustrated.

Efficient navigation and precise localization of Brownian micro/nano self‐propelled motor particles within complex landscapes could enable future high‐tech applications involving for example drug delivery, precision surgery, oil recovery, and environmental remediation. Here, a model‐free deep reinforcement learning algorithm based on bio‐inspired neural networks is employed to enable different types of micro/nano motors to be continuously controlled to carry out complex navigation and localization tasks. Micro/nano motors with either tunable self‐propelling speeds or orientations or both, are found to exhibit strikingly different dynamics. In particular, distinct control strategies are required to achieve effective navigation in free space and obstacle environments, as well as under time constraints. The findings provide fundamental insights into active dynamics of Brownian particles controlled using artificial intelligence and could guide the design of motor and robot control systems to meet diverse application requirements.

Multiagent stochastic control enables self-propelled colloidal swarms to perform cooperative tasks as micromachines.

The ability to assemble nano- and micro- sized colloidal components into highly ordered configurations is often cited as the basis for developing advanced materials. However, the dynamics of stochastic grain boundary formation and motion have not been quantified, which limits the ability to control and anneal polycrystallinity in colloidal based materials. Here we use optical microscopy, Brownian Dynamic simulations, and a new dynamic analysis to study grain boundary motion in quasi-2D colloidal bicrystals formed within inhomogeneous AC electric fields. We introduce “low-dimensional” models using reaction coordinates for condensation and global order that capture first passage times between critical configurations at each applied voltage. The resulting models reveal that equal sized domains at a maximum misorientation angle show relaxation dominated by friction limited grain boundary diffusion; and in contrast, asymmetrically sized domains with less misorientation display much faster grain boundary migration due to significant thermodynamic driving forces. By quantifying such dynamics vs. compression (voltage), kinetic bottlenecks associated with slow grain boundary relaxation are understood, which can be used to guide the temporal assembly of defect-free single domain colloidal crystals.