Highlights Carbon-based gradient resistance element structure is proposed for the construction of multifunctional touch sensor, which will promote wide detection and recognition range of multiple mechanical stimulations. Multifunctional touch sensor with gradient resistance element and two electrodes is demonstrated to eliminate signals crosstalk and prevent interference during position sensing for human–machine interactions. Biological sensing interface based on a deep-learning-assisted all-in-one multipoint touch sensor enables users to efficiently interact with virtual world. Abstract Human–machine interactions using deep-learning methods are important in the research of virtual reality, augmented reality, and metaverse. Such research remains challenging as current interactive sensing interfaces for single-point or multipoint touch input are trapped by massive crossover electrodes, signal crosstalk, propagation delay, and demanding configuration requirements. Here, an all-in-one multipoint touch sensor (AIOM touch sensor) with only two electrodes is reported. The AIOM touch sensor is efficiently constructed by gradient resistance elements, which can highly adapt to diverse application-dependent configurations. Combined with deep learning method, the AIOM touch sensor can be utilized to recognize, learn, and memorize human–machine interactions. A biometric verification system is built based on the AIOM touch sensor, which achieves a high identification accuracy of over 98% and offers a promising hybrid cyber security against password leaking. Diversiform human–machine interactions, including freely playing piano music and programmatically controlling a drone, demonstrate the high stability, rapid response time, and excellent spatiotemporally dynamic resolution of the AIOM touch sensor, which will promote significant development of interactive sensing interfaces between fingertips and virtual objects.

Intuitive, efficient, and unconstrained interactions require human–machine interfaces (HMIs) to accurately recognize users' manipulation intents. Susceptibility to interference and conditional usage mode of HMIs will lead to poor experiences that limit their great interaction potential. Herein, a programmable and ultrasensitive haptic interface enabling closed‐loop human–machine interactions is reported. A cross‐scale architecture design strategy is proposed to fabricate the haptic interface, which optimizes the hierarchical contact process. The synergistic optimization of the cross‐scale architecture between carbon nanotubes and the multiscale sensing structure realizes a haptic interface with ultrahigh sensitivity and a wide detection range of 15.1 kPa−1 and 180 kPa, which are improved by more than 900% over the performance of the common interface. The rapid response time of <5 ms and the limit of detection of 8 Pa of the haptic interface far surpass the somatosensory perception of human skin, which enables the haptic interface to accurately recognize interactive intents. A wireless pressure‐data interactive glove (wireless PDI glove) is designed and realizes a round‐the‐clock operation, noise immunity, and efficient interactive control, which perfectly compensate for the flaws of typical vision and voice recognition modes.

Traditional information fusion model has the problem of low efficiency in urban landscape design. In addition, using the current method to design urban commercial landscape public facilities, there are problems of large regional space occupation and unsatisfactory design effect. This paper designs a new modular information fusion model for urban landscape design process in view of genetic back propagation. On the basis of preprocessing sensor images, a digital elevation model is created using an ordered numerical sequence. Then, the stereo orthophoto image pair is obtained through the artificial parallax assistance mechanism, and the 3D garden landscape is generated by combining with the ant colony algorithm. The positive feedback mechanism of the ant colony algorithm is used to make the processing process converge continuously, and the optimal 3D garden landscape is finally generated by obtaining stereo orthophoto pairs through the artificial parallax-assisted mechanism. At the same time, the strong robustness and fault tolerance of neural network and parallel processing mechanism are utilized for fast information fusion. The scale and resources of garden design are described by the process dimension and the context dimension, and a modular garden landscape with distinct main body is built. Finally, the initial weight is optimized in the genetic real number coding algorithm, and the appropriate learning factor is selected to train the neural network so as to make the information fusion task. Experimental results show that the above model fusion process has good stability and low energy consumption for information fusion, which can promote the efficient construction of garden landscapes.