Si chiplet-controlled 3D modular microrobots with smart communication in natural aqueous environments.

Modular microrobotics can potentially address many information-intensive microtasks in medicine, manufacturing, and the environment. However, surface area has limited the natural powering, communication, functional integration, and self-assembly of smart mass-fabricated modular robotic devices at small scales. We demonstrate the integrated self-folding and self-rolling of functionalized patterned interior and exterior membrane surfaces resulting in programmable, self-assembling, intercommunicating, and self-locomoting micromodules (smartlets ≤ 1 cubic millimeter) with interior chambers for onboard buoyancy control.

Photocatalytic microrobots for treating bacterial infections deep within sinuses.

Microrobotic techniques are promising for treating biofilm infections located deep within the human body. However, the presence of highly viscous pus presents a formidable biological barrier, severely restricting targeted and minimally invasive treatments. In addition, conventional antibacterial agents exhibit limited payload integration with microrobotic systems, further compromising therapeutic efficiency.

Multimodal information structuring with single-layer soft skins and high-density electrical impedance tomography.

The human skin can reliably capture a wide range of multimodal data over a large surface while providing a soft interface. Artificial technologies using microelectromechanical systems (MEMS) can emulate these biological functions but present numerous challenges in fabrication, delamination due to soft-rigid interfaces, and electrical interference. To address these difficulties, we present a single-layer multimodal sensory skin made using only a highly sensitive hydrogel membrane.

Learning coordinated badminton skills for legged manipulators.

Coordinating the motion between lower and upper limbs and aligning limb control with perception are substantial challenges in robotics, particularly in dynamic environments. To this end, we introduce an approach for enabling legged mobile manipulators to play badminton, a task that requires precise coordination of perception, locomotion, and arm swinging. We propose a unified reinforcement learning-based control policy for whole-body visuomotor skills involving all degrees of freedom to achieve effective shuttlecock tracking and striking.

Bridging hard and soft: Mechanical metamaterials enable rigid torque transmission in soft robots.

Torque and continuous rotation are fundamental methods of actuation and manipulation in rigid robots. Soft robot arms use soft materials and structures to mimic the passive compliance of biological arms that bend and extend. This use of compliance prevents soft arms from continuously transmitting and exerting torques to interact with their environment.

Robotic locomotion through active and passive morphological adaptation in extreme outdoor environments.

Robotic locomotion has shown substantial advancements, yet robots still lack the versatility and agility shown by animals navigating complex terrains. This limits their applicability in complex environments where they could be highly beneficial. Unlike existing robots that rely on intricate perception systems to construct models of both themselves and their surroundings, a more bioinspired approach leverages reconfiguration to adapt a robot's morphology to its environment.

Highly agile flat swimming robot.

Navigating and exploring the surfaces of bodies of water allow swimming robots to perform a range of measurements while efficiently communicating and harvesting energy from the Sun. Such environments are often highly unstructured and cluttered with plant matter, animals, and debris, which require robots to move swiftly. We report a fast (5.

Bird-inspired reflexive morphing enables rudderless flight.

Gliding birds lack a vertical tail, yet they fly stably rudderless in turbulence without needing discrete flaps to steer. In contrast, nearly all airplanes need vertical tails to damp Dutch roll oscillations and to control yaw. The few exceptions that lack a vertical tail either leverage differential drag-based yaw actuators or their fixed planforms are carefully tuned for passively stable Dutch roll and proverse yaw.

Self-organizing nervous systems for robot swarms.

We present the self-organizing nervous system (SoNS), a robot swarm architecture based on self-organized hierarchy. The SoNS approach enables robots to autonomously establish, maintain, and reconfigure dynamic multilevel system architectures. For example, a robot swarm consisting of independent robots could transform into a single -robot SoNS and then into several independent smaller SoNSs, where each SoNS uses a temporary and dynamic hierarchy.

Hexagonal electrohydraulic modules for rapidly reconfigurable high-speed robots.

Robots made from reconfigurable modular units feature versatility, cost efficiency, and improved sustainability compared with fixed designs. Reconfigurable modules driven by soft actuators provide adaptable actuation, safe interaction, and wide design freedom, but existing soft modules would benefit from high-speed and high-strain actuation, as well as driving methods well-suited to untethered operation. Here, we introduce a class of electrically actuated robotic modules that provide high-speed (a peak contractile strain rate of 4618% per second, 15.

Stretchable Arduinos embedded in soft robots.

To achieve real-world functionality, robots must have the ability to carry out decision-making computations. However, soft robots stretch and therefore need a solution other than rigid computers. Examples of embedding computing capacity into soft robots currently include appending rigid printed circuit boards to the robot, integrating soft logic gates, and exploiting material responses for material-embedded computation.

Bistable soft jumper capable of fast response and high takeoff velocity.

In contrast with jumping robots made from rigid materials, soft jumpers composed of compliant and elastically deformable materials exhibit superior impact resistance and mechanically robust functionality. However, recent efforts to create stimuli-responsive jumpers from soft materials were limited in their response speed, takeoff velocity, and travel distance. Here, we report a magnetic-driven, ultrafast bistable soft jumper that exhibits good jumping capability (jumping more than 108 body heights with a takeoff velocity of more than 2 meters per second) and fast response time (less than 15 milliseconds) compared with previous soft jumping robots.

Variable-stiffness-morphing wheel inspired by the surface tension of a liquid droplet.

Wheels have been commonly used for locomotion in mobile robots and transportation systems because of their simple structure and energy efficiency. However, the performance of wheels in overcoming obstacles is limited compared with their advantages in driving on normal flat ground. Here, we present a variable-stiffness wheel inspired by the surface tension of a liquid droplet.

Crawling, climbing, perching, and flying by FiBa soft robots.

This paper introduces an approach to fabricating lightweight, untethered soft robots capable of diverse biomimetic locomotion. Untethering soft robotics from electrical or pneumatic power remains one of the prominent challenges within the field. The development of functional untethered soft robotic systems hinges heavily on mitigating their weight; however, the conventional weight of pneumatic network actuators (pneu-nets) in soft robots has hindered untethered operations.

Learning agile soccer skills for a bipedal robot with deep reinforcement learning.

We investigated whether deep reinforcement learning (deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be composed into complex behavioral strategies. We used deep RL to train a humanoid robot to play a simplified one-versus-one soccer game. The resulting agent exhibits robust and dynamic movement skills, such as rapid fall recovery, walking, turning, and kicking, and it transitions between them in a smooth and efficient manner.

ANYmal parkour: Learning agile navigation for quadrupedal robots.

Performing agile navigation with four-legged robots is a challenging task because of the highly dynamic motions, contacts with various parts of the robot, and the limited field of view of the perception sensors. Here, we propose a fully learned approach to training such robots and conquer scenarios that are reminiscent of parkour challenges. The method involves training advanced locomotion skills for several types of obstacles, such as walking, jumping, climbing, and crouching, and then using a high-level policy to select and control those skills across the terrain.

A growing soft robot with climbing plant-inspired adaptive behaviors for navigation in unstructured environments.

Self-growing robots are an emerging solution in soft robotics for navigating, exploring, and colonizing unstructured environments. However, their ability to grow and move in heterogeneous three-dimensional (3D) spaces, comparable with real-world conditions, is still developing. We present an autonomous growing robot that draws inspiration from the behavioral adaptive strategies of climbing plants to navigate unstructured environments.

Versatile multicontact planning and control for legged loco-manipulation.

Loco-manipulation planning skills are pivotal for expanding the utility of robots in everyday environments. These skills can be assessed on the basis of a system's ability to coordinate complex holistic movements and multiple contact interactions when solving different tasks. However, existing approaches have been merely able to shape such behaviors with hand-crafted state machines, densely engineered rewards, or prerecorded expert demonstrations.

Desktop fabrication of monolithic soft robotic devices with embedded fluidic control circuits.

Most soft robots are pneumatically actuated and fabricated by molding and assembling processes that typically require many manual operations and limit complexity. Furthermore, complex control components (for example, electronic pumps and microcontrollers) must be added to achieve even simple functions. Desktop fused filament fabrication (FFF) three-dimensional printing provides an accessible alternative with less manual work and the capability of generating more complex structures.

Exoskeletons need to react faster than physiological responses to improve standing balance.

Maintaining balance throughout daily activities is challenging because of the unstable nature of the human body. For instance, a person's delayed reaction times limit their ability to restore balance after disturbances. Wearable exoskeletons have the potential to enhance user balance after a disturbance by reacting faster than physiologically possible.

3D-printed biomimetic artificial muscles using soft actuators that contract and elongate.

Biomimetic machines able to integrate with natural and social environments will find ubiquitous applications, from biodiversity conservation to elderly daily care. Although artificial actuators have reached the contraction performances of muscles, the versatility and grace of the movements realized by the complex arrangements of muscles remain largely unmatched. Here, we present a class of pneumatic artificial muscles, named GeometRy-based Actuators that Contract and Elongate (GRACE).

Neuromorphic computing chip with spatiotemporal elasticity for multi-intelligent-tasking robots.

Recent advances in artificial intelligence have enhanced the abilities of mobile robots in dealing with complex and dynamic scenarios. However, to enable computationally intensive algorithms to be executed locally in multitask robots with low latency and high efficiency, innovations in computing hardware are required. Here, we report TianjicX, a neuromorphic computing hardware that can support true concurrent execution of multiple cross-computing-paradigm neural network (NN) models with various coordination manners for robotics.