Explore the vast range of titles available.

First-person view (FPV) drone racing is a televised sport in which professional competitors pilot high-speed aircraft through a 3D circuit. Each pilot sees the environment from the perspective of their drone by means of video streamed from an onboard camera. Reaching the level of professional pilots with an autonomous drone is challenging because the robot needs to fly at its physical limits while estimating its speed and location in the circuit exclusively from onboard sensors 1 . Here we introduce Swift, an autonomous system that can race physical vehicles at the level of the human world champions. The system combines deep reinforcement learning (RL) in simulation with data collected in the physical world. Swift competed against three human champions, including the world champions of two international leagues, in real-world head-to-head races. Swift won several races against each of the human champions and demonstrated the fastest recorded race time. This work represents a milestone for mobile robotics and machine intelligence 2 , which may inspire the deployment of hybrid learning-based solutions in other physical systems. An autonomous system is described that combines deep reinforcement learning with onboard sensors collecting data from the physical world, enabling it to fly faster than human world champion drone pilots around a race track.

Lithium-ion batteries with nickel-rich layered oxide cathodes and graphite anodes have reached specific energies of 250–300 Wh kg −1 (refs. 1 , 2 ), and it is now possible to build a 90 kWh electric vehicle (EV) pack with a 300-mile cruise range. Unfortunately, using such massive batteries to alleviate range anxiety is ineffective for mainstream EV adoption owing to the limited raw resource supply and prohibitively high cost. Ten-minute fast charging enables downsizing of EV batteries for both affordability and sustainability, without causing range anxiety. However, fast charging of energy-dense batteries (more than 250 Wh kg − 1 or higher than 4 mAh cm − 2 ) remains a great challenge 3 , 4 . Here we combine a material-agnostic approach based on asymmetric temperature modulation with a thermally stable dual-salt electrolyte to achieve charging of a 265 Wh kg − 1 battery to 75% (or 70%) state of charge in 12 (or 11) minutes for more than 900 (or 2,000) cycles. This is equivalent to a half million mile range in which every charge is a fast charge. Further, we build a digital twin of such a battery pack to assess its cooling and safety and demonstrate that thermally modulated 4C charging only requires air convection. This offers a compact and intrinsically safe route to cell-to-pack development. The rapid thermal modulation method to yield highly active electrochemical interfaces only during fast charging has important potential to realize both stability and fast charging of next-generation materials, including anodes like silicon and lithium metal. A new approach to charging energy-dense electric vehicle batteries, using temperature modulation with a dual-salt electrolyte, promises a range in excess of 500,000 miles using only rapid (under 12 minute) charges.

Among kinds of flexible tactile sensors, piezoelectric tactile sensor has the advantage of fast response for dynamic force detection. However, it suffers from low sensitivity at high-frequency dynamic stimuli. Here, inspired by finger structure—rigid skeleton embedded in muscle, we report a piezoelectric tactile sensor using a rigid-soft hybrid force-transmission-layer in combination with a soft bottom substrate, which not only greatly enhances the force transmission, but also triggers a significantly magnified effect in d 31 working mode of the piezoelectric sensory layer, instead of conventional d 33 mode. Experiments show that this sensor exhibits a super-high sensitivity of 346.5 pC N −1 (@ 30 Hz), wide bandwidth of 5–600 Hz and a linear force detection range of 0.009–4.3 N, which is ~17 times the theoretical sensitivity of d 33 mode. Furthermore, the sensor is able to detect multiple force directions with high reliability, and shows great potential in robotic dynamic tactile sensing. Designing efficient tactile sensors under high-frequency dynamic stimuli remains a challenge. Here, the authors demonstrate piezoelectric tactile sensor with sensitivity of 346.5 pCN−1, wide bandwidth of 5–600 Hz and a linear force detection range of 0.009–4.3 N using a rigid-soft hybrid force-transmission-layer in combination with a soft bottom substrate.

Sea animals such as leptocephali develop tissues and organs composed of active transparent hydrogels to achieve agile motions and natural camouflage in water. Hydrogel-based actuators that can imitate the capabilities of leptocephali will enable new applications in diverse fields. However, existing hydrogel actuators, mostly osmotic-driven, are intrinsically low-speed and/or low-force; and their camouflage capabilities have not been explored. Here we show that hydraulic actuations of hydrogels with designed structures and properties can give soft actuators and robots that are high-speed, high-force, and optically and sonically camouflaged in water. The hydrogel actuators and robots can maintain their robustness and functionality over multiple cycles of actuations, owing to the anti-fatigue property of the hydrogel under moderate stresses. We further demonstrate that the agile and transparent hydrogel actuators and robots perform extraordinary functions including swimming, kicking rubber-balls and even catching a live fish in water. Hydrogel actuators have been widely developed to be osmotic-driven but many are in fact only capable of producing low forces. Here, the authors developed high speed and high force hydrogel actuators capable of camouflage optically and sonically with low fatigue over multiple cycles.

Advancements of virtual reality technology pave the way for developing wearable devices to enable somatosensory sensation, which can bring more comprehensive perception and feedback in the metaverse-based virtual society. Here, we propose augmented tactile-perception and haptic-feedback rings with multimodal sensing and feedback capabilities. This highly integrated ring consists of triboelectric and pyroelectric sensors for tactile and temperature perception, and vibrators and nichrome heaters for vibro- and thermo-haptic feedback. All these components integrated on the ring can be directly driven by a custom wireless platform of low power consumption for wearable/portable scenarios. With voltage integration processing, high-resolution continuous finger motion tracking is achieved via the triboelectric tactile sensor, which also contributes to superior performance in gesture/object recognition with artificial intelligence analysis. By fusing the multimodal sensing and feedback functions, an interactive metaverse platform with cross-space perception capability is successfully achieved, giving people a face-to-face like immersive virtual social experience. Current wearable solutions for Virtual Reality (VR) have limitations of complicated structures and large driven power. Here, the authors report a highly integrated ring consisting of multimodal sensing and feedback units for augmented interactions in metaverse.

Holograms for sound waves, encoded in a 3D printed plate, are used to shape sound fields that can be used for the contactless manipulation of objects. Acoustic holograms on a plate Sound, especially ultrasound, can be used for contactless manipulation of objects in liquid and air, a phenomenon with applications in medical imaging, non-destructive testing and metrology. Usually, the desired sound field is shaped with arrays of transducers that must be carefully connected and controlled. Here Peer Fischer and colleagues describe a relatively simple technique for creating acoustic holograms and demonstrate their potential for use in matter manipulation. The acoustic holograms are encoded in a polymer plate by 3D printing and then used to shape a sound field that can be used for contactless manipulation of objects. The method can produce complex fields with reconstruction degrees of freedom two orders of magnitude greater than existing approaches. Because the holograms are inexpensive and fast to make, the method could be widely adopted to enable new applications with ultrasound manipulation. Holographic techniques are fundamental to applications such as volumetric displays 1 , high-density data storage and optical tweezers that require spatial control of intricate optical 2 or acoustic fields 3 , 4 within a three-dimensional volume. The basis of holography is spatial storage of the phase and/or amplitude profile of the desired wavefront 5 , 6 in a manner that allows that wavefront to be reconstructed by interference when the hologram is illuminated with a suitable coherent source. Modern computer-generated holography 7 skips the process of recording a hologram from a physical scene, and instead calculates the required phase profile before rendering it for reconstruction. In ultrasound applications, the phase profile is typically generated by discrete and independently driven ultrasound sources 3 , 4 , 8 , 9 , 10 , 11 , 12 ; however, these can only be used in small numbers, which limits the complexity or degrees of freedom that can be attained in the wavefront. Here we introduce monolithic acoustic holograms, which can reconstruct diffraction-limited acoustic pressure fields and thus arbitrary ultrasound beams. We use rapid fabrication to craft the holograms and achieve reconstruction degrees of freedom two orders of magnitude higher than commercial phased array sources. The technique is inexpensive, appropriate for both transmission and reflection elements, and scales well to higher information content, larger aperture size and higher power. The complex three-dimensional pressure and phase distributions produced by these acoustic holograms allow us to demonstrate new approaches to controlled ultrasonic manipulation of solids in water, and of liquids and solids in air. We expect that acoustic holograms will enable new capabilities in beam-steering and the contactless transfer of power, improve medical imaging, and drive new applications of ultrasound.

One critical bottleneck that impedes the development and deployment of autonomous vehicles is the prohibitively high economic and time costs required to validate their safety in a naturalistic driving environment, owing to the rarity of safety-critical events 1 . Here we report the development of an intelligent testing environment, where artificial-intelligence-based background agents are trained to validate the safety performances of autonomous vehicles in an accelerated mode, without loss of unbiasedness. From naturalistic driving data, the background agents learn what adversarial manoeuvre to execute through a dense deep-reinforcement-learning (D2RL) approach, in which Markov decision processes are edited by removing non-safety-critical states and reconnecting critical ones so that the information in the training data is densified. D2RL enables neural networks to learn from densified information with safety-critical events and achieves tasks that are intractable for traditional deep-reinforcement-learning approaches. We demonstrate the effectiveness of our approach by testing a highly automated vehicle in both highway and urban test tracks with an augmented-reality environment, combining simulated background vehicles with physical road infrastructure and a real autonomous test vehicle. Our results show that the D2RL-trained agents can accelerate the evaluation process by multiple orders of magnitude (10 3 to 10 5 times faster). In addition, D2RL will enable accelerated testing and training with other safety-critical autonomous systems. An intelligent environment has been developed for testing the safety performance of autonomous vehicles and its effectiveness has been demonstrated for highway and urban test tracks in an augmented-reality environment.

Designing and printing metamaterials with customizable architectures enables the realization of unprecedented mechanical behaviors that transcend those of their constituent materials. These behaviors are recorded in the form of response curves, with stress-strain curves describing their quasi-static footprint. However, existing inverse design approaches are yet matured to capture the full desired behaviors due to challenges stemmed from multiple design objectives, nonlinear behavior, and process-dependent manufacturing errors. Here, we report a rapid inverse design methodology, leveraging generative machine learning and desktop additive manufacturing, which enables the creation of nearly all possible uniaxial compressive stress‒strain curve cases while accounting for process-dependent errors from printing. Results show that mechanical behavior with full tailorability can be achieved with nearly 90% fidelity between target and experimentally measured results. Our approach represents a starting point to inverse design materials that meet prescribed yet complex behaviors and potentially bypasses iterative design-manufacturing cycles. Mechanical behavior of a material is captured by a measured stress-strain curve upon loading. Here, the authors report a rapid inverse design methodology via machine learning and 3D printing to create metamaterials with mechanical behavior that replicates a user-prescribed stress-strain curve.

Keyhole porosity is a key concern in laser powder-bed fusion (LPBF), potentially impacting component fatigue life. However, some keyhole porosity formation mechanisms, e.g., keyhole fluctuation, collapse and bubble growth and shrinkage, remain unclear. Using synchrotron X-ray imaging we reveal keyhole and bubble behaviour, quantifying their formation dynamics. The findings support the hypotheses that: (i) keyhole porosity can initiate not only in unstable, but also in the transition keyhole regimes created by high laser power-velocity conditions, causing fast radial keyhole fluctuations (2.5–10 kHz); (ii) transition regime collapse tends to occur part way up the rear-wall; and (iii) immediately after keyhole collapse, bubbles undergo rapid growth due to pressure equilibration, then shrink due to metal-vapour condensation. Concurrent with condensation, hydrogen diffusion into the bubble slows the shrinkage and stabilises the bubble size. The keyhole fluctuation and bubble evolution mechanisms revealed here may guide the development of control systems for minimising porosity. Understanding the keyhole porosity formation is important in laser powder bed fusion. Here the authors reveal the dynamics of keyhole fluctuation, and collapse that induces bubble formation with three main stages of evolution; growth, shrinkage, and being captured by the solidification front.

Sensitivity is a crucial parameter for flexible pressure sensors and electronic skins. While introducing microstructures (e.g., micro-pyramids) can effectively improve the sensitivity, it in turn leads to a limited pressure-response range due to the poor structural compressibility. Here, we report a strategy of engineering intrafillable microstructures that can significantly boost the sensitivity while simultaneously broadening the pressure responding range. Such intrafillable microstructures feature undercuts and grooves that accommodate deformed surface microstructures, effectively enhancing the structural compressibility and the pressure-response range. The intrafillable iontronic sensor exhibits an unprecedentedly high sensitivity ( S min   >  220 kPa −1 ) over a broad pressure regime (0.08 Pa-360 kPa), and an ultrahigh pressure resolution (18 Pa or 0.0056%) over the full pressure range, together with remarkable mechanical stability. The intrafillable structure is a general design expected to be applied to other types of sensors to achieve a broader pressure-response range and a higher sensitivity. Though flexible pressure sensors are attractive for next-generation applications, limitations in its performance hinder widespread adoption. Here, the authors report an iontronic flexible pressure sensor with graded intrafillable architecture that shows high sensitivity over a broad pressure range.