Conventional artificial intelligence (AI) machine vision technology, based on the von Neumann architecture, uses separate sensing, computing, and storage units to process huge amounts of vision data generated in sensory terminals. The frequent movement of redundant data between sensors, processors and memory, however, results in high-power consumption and latency. A more efficient approach is to offload some of the memory and computational tasks to sensor elements that can perceive and process the optical signal simultaneously. Here, we proposed a non-volatile photomemristor, in which the reconfigurable responsivity can be modulated by the charge and/or photon flux through it and further stored in the device. The non-volatile photomemristor has a simple two-terminal architecture, in which photoexcited carriers and oxygen-related ions are coupled, leading to a displaced and pinched hysteresis in the current-voltage characteristics. For the first time, non-volatile photomemristors implement computationally complete logic with photoresponse-stateful operations, for which the same photomemristor serves as both a logic gate and memory, using photoresponse as a physical state variable instead of light, voltage and memresistance. The polarity reversal of photomemristors shows great potential for in-memory sensing and computing with feature extraction and image recognition for neuromorphic vision.

In autonomous driving, accurate 3D lane detection using monocular cameras is important for downstream tasks. Recent CNN and Transformer approaches usually apply a two-stage model design. The first stage transforms the image feature from a front image into a bird’s-eye-view (BEV) representation. Subsequently, a sub-network processes the BEV feature to generate the 3D detection results. However, these approaches heavily rely on a challenging image feature transformation module from a perspective view to a BEV representation. In our work, we present CurveFormer++, a single-stage Transformer-based method that does not require the view transform module and directly infers 3D lane results from the perspective image features. Specifically, our approach models the 3D lane detection task as a curve propagation problem, where each lane is represented by a curve query with a dynamic and ordered anchor point set. By employing a Transformer decoder, the model can iteratively refine the 3D lane results. A curve cross-attention module is introduced to calculate similarities between image features and curve queries. To handle varying lane lengths, we employ context sampling and anchor point restriction techniques to compute more relevant image features. Furthermore, we apply a temporal fusion module that incorporates selected informative sparse curve queries and their corresponding anchor point sets to leverage historical information. In the experiments, we evaluate our approach on two publicly real-world datasets. The results demonstrate that our method provides outstanding performance compared with both CNN and Transformer based methods. We also conduct ablation studies to analyze the impact of each component.

Humanoid robots can imitate human behaviour and provide interactive services to humans due to their humanoid form, especially humanoid wheeled robots that can perform more complex tasks with the additional mobility. With the development of robotics technology, humanoid robots have been used increasingly in the domestic environment where the robot needs to interact with unknown environments. This requires the robot to have both the ability to track with high accuracy and the ability to comply with complex environments. It is known that the robots with impedance control can have a superior performance in terms of compliance with unknown contact environments. However, the mobility of humanoid robots with wheels complicates the dynamic model of robots, which makes the development of impedance control challenging. In this letter, a whole-body impedance control approach for humanoid wheeled robots is proposed, with fuzzy adaptive systems to compensate for the uncertain dynamics of the controlled system. This approach realizes safe interaction and compliant operation with unknown environments including humans. Additionally, the experimental results conducted on a humanoid wheeled robot illustrate the effectiveness of the proposed controller.

Recently, programing by demonstration (PbD) becomes a white-hot research area with increasing demands in the robot manipulation area, especially in industrial applications. However, the key challenges of PbD, to date, has been the recognition of demonstrator's fine hand motions and the uncertainty of manipulation environments, which limit the efficiency and accuracy of PbD. In this study, inspired by humanoid manipulation, a novel PbD approach using the implicit muscular task planning strategy is presented to extract features from the arms' giant movement and the hands' fine motions during the demonstrator's operation. Furthermore, we integrate a deep reinforcement learning control method that further improves the manipulations' adaptive ability in the unknown or changeable environments. The experimental results show that our proposed approach can deal with relative complex assembly task from single demonstration with more than 67% success rate under about 4.2 mm fit tolerance.

Sport and game industry has grown rapidly in recent years due to the application of novel sensors and algorithms for quantitative analysis. For example, flying speed and spin estimation is essential to help players to improve their skills in table tennis. However, the spin estimation for a table tennis ball is challenging, as it is difficult to observe using cameras and model the aerodynamics of ball flight with spin. This article proposes a generalized aerodynamic model with variable aerodynamic coefficients to accurately represent the flying state of a table tennis ball. Analytical solutions for the aerodynamic coefficients and the acceleration due to the Magnus force are also developed for accurate ball spin estimation using pre- and postrebounding flight trajectories. The experimental results showed that compared to current state-of-the-art methods, the proposed method has achieved the best performance in angular velocity magnitude estimation for topspinning and backspinning balls. It also achieved an error of below 10° in angular velocity amplitude estimation. Using the proposed spin estimation method, our table tennis robot could strike balls with either topspin or backspin with a high success rate of up to 84.6 $%$ . Besides, the experimental results also demonstrated the potential of the proposed method in the area of table tennis training and sports-broadcasting.