The increasingly serious electromagnetic radiation and electronic waste pose a significant threat to public health and the operation of electronic devices. Despite the enormous potential of highly conductive Ti3C2Tx MXenebased electromagnetic interference (EMI) shielding materials, significant challenges persist in terms of mechanical flexibility and antioxidation. In this study, it was firstly proposed for a scalable method to prepare MXene Ti3C2Tx/gelatin/sodium lignosulphonate (MXene/GEL/SL) films with good biodegradability, and Fe3+ ions were introduced to enhance cross-linking degree and stabilize the gelatin matrixes, which endowed the films with mechanical flexibility and durability. The film (MXene content: 30 wt%) has a thickness of merely 0.08 mm, exhibiting a high SE/d value of 432 dB/mm and maintaining its good EMI shielding performance even after being soaked in water for 15 days. Additionally, the film-based triboelectric nanogenerator (TENG) even in 85 % humidity manifest excellent open-circuit voltage (230 V), short-circuit current (28 mu A) and power density (2.9 W/m2), respectively. Also, the TENG demonstrates good utility as a self-powered sensor when attached to different parts of human body to monitor human health. Therefore, the as-developed MXene/GEL/SL film presents good application prospects in the fields of both electromagnetic shielding and self-powered sensing for wearable electronics.

Simultaneous Localization and Mapping (SLAM) is a cornerstone capability for intelligent mobile robots, enabling them to accurately estimate their positions in unknown environments. However, most of the state-of-the-art visual SLAM systems rely on the assumption of static scenes, leading to significantly reduced accuracy and robustness in dynamic environments. In this paper, a novel RGB-D SLAM system termed Inpainting SLAM is proposed in the ORB-SLAM2 framework. Our Inpainting SLAM defines two new modules: one is the dynamic objects detection module, which combines segmentation and depth information to segment dynamic objects. Additionally, a new method is also proposed to determine whether movable objects are classified as dynamic. The other is an image inpainting module to restore static regions that are occluded by dynamic objects, with a new rectified approach introduced to determine the inpainting regions that can enhance the performance of the SLAM system. With these two modules, the accuracy and robustness of the SLAM system in dynamic scenes are expected to be improved. Our method is tested on the public TUM dataset, demonstrating its effectiveness and reliability. The improvements on ORB-SLAM2 in RTE, RRE, and ATE are 97.45

Reinforcement learning holds promise in enabling robotic tasks as it can learn optimal policies via trial and error. However, the practical deployment of reinforcement learning usually requires human intervention to provide episodic resets when a failure occurs. Since manual resets are generally unavailable in autonomous robots, we propose a reset-free reinforcement learning algorithm based on multi-state recovery and failure prevention to avoid failure-induced resets. The multi-state recovery provides robots with the capability of recovering from failures by self-correcting its behavior in the problematic state and, more importantly, deciding which previous state is the best to return to for efficient re-learning. The failure prevention reduces potential failures by predicting and excluding possible unsafe actions in specific states. Both simulations and real-world experiments are used to validate our algorithm with the results showing a significant reduction in the number of resets and failures during the learning.

Reinforcement learning theoretically needs to keep re-learning new optimal policies for autonomous robot navigation when the environment is dynamic. Given no reinforcement learning is failure-free, however, the practical deployment of reinforcement learning raises a new but fundamental question: when to re-learn and when not to be safer in the long-term robot navigation? An early re-learning could encounter more failures due to unnecessary and unsafe explorations in the learning process while a late re-learning cannot avoid failures caused by the deteriorating policy. To determine the optimal timing of learning with minimal failures, we propose a Value of Learning approach that maximizes the difference between the learning gain and the learning cost. The learning gain estimates the performance improvement with respect to time and the learning cost evaluates the learning-induced failure risk, which is assumed to relate to environment changes and exploration strategies. A dynamic maze experiment validates that our approach can find an optimal re-learning timing with significantly fewer failures if compared with “always learning” and “no learning”, which are two representative cases of the early and late learning.

Although particle swarm optimization has shown great potentials in solving the complex elevator group scheduling problem, it still suffers from the issue of local optimum. In order to improve the capability of finding the global optimum, a multi-strategy enhanced particle swarm optimization algorithm has been proposed for elevator group scheduling in this work. For the initialization of particle position, Tent map is used to generate a diverse position distribution for faster and more effective explorations in the entire solution space. Spiral flight strategy is then utilized to update the position and velocity of particles in a more flexible way with exploring more spaces. Once an optimum is obtained, a local search strategy is finally employed to search the nearby solution spaces to further avoid local optimum. Simulation results have demonstrated that the proposed algorithm can achieve a shorter passenger waiting time than traditional particle swarm optimization.

Unsafe explorations in the training phase hinder the practical deployment of reinforcement learning (RL) on autonomous robots. Some safe RL methods use safety constraints from prior or external knowledge to reduce or avoid unsafe explorations, but such knowledge is usually unavailable in practice, especially in unknown environments. In this work, we propose a few-shot reasoning-based safe reinforcement learning framework that includes a new few-shot learning method with dynamic support set to reason the safety of unexplored actions and hence guide safer action selection. Additionally, it endows robots with the capability of reverting to previous safe states and reflecting on failures to update the dynamic support set and further improve the accuracy of safety reasoning. Experimental results show that our new few-shot learning method is more accurate, and our proposed framework can significantly reduce the number of failures in the learning phase, especially for long-term autonomy.

Effective detection of abnormal behaviors within elevator cabins is critical to ensure elevator safety. While existing deep learning based anomaly detection methods mainly focus on convolutional neural networks for spatial feature extraction and recurrent networks for temporal feature learning, recent advancements in the Transformer architecture have demonstrated its power in time series predictions, and extended its capabilities to vision detection tasks. In this study, we present a duel transformer-based framework that can proficiently detect falling and fighting events in elevator cabs. The proposed solution leverages the vision transformer (ViT) to extract frame-level spatial features, followed by a temporal Transformer to identify abnormalities in surveillance videos. A comprehensive comparison between the proposed transformer-based method and other traditional recurrent neural network variants is carried out to validate the effectiveness of the method.

Simultaneous localization and mapping (SLAM) is crucial for intelligent mobile robots to move autonomously in unknown environments. However, many current visual SLAM systems heavily rely on static scene assumptions, which severely limit their applicability in dynamic environments. Additionally, many SLAM systems based on semantic segmentation are unable to operate in real time, rendering them impractical for robotic applications. In this paper, we propose a real-time semantic RGB-D visualization SLAM system within the ORB-SLAM3 framework. Firstly, we add two modules, a real-time semantic information acquisition module and a fast dynamic feature point removal module that integrates semantic information and depth information. Subsequently, the dynamic feature point removal module is incorporated into the tracking thread of ORB-SLAM3. We conduct experimental evaluations on the TUM dataset and real environments. The results demonstrate that our algorithm is one of the most accurate robust and real-time systems in dynamic scenes.

Reinforcement learning (RL) holds the promise of autonomous robots because it can adapt to dynamic or unknown environments by automatically learning optimal control policies from the interactions between robots and environments. However, the interactions can be unsafe to both robots and environments during the learning phase, which hinders the practical deployment of RL. Some safe RL methods have been proposed to improve the learning safety by using external or prior knowledge to guide safe actions, but it is difficult to assume having this knowledge in practical applications, especially in unknown environments. More importantly, considering failures are unavoidable in practice, current safe RL lacks the capability of recovering to safe states from failures so that the learning cannot be continued and finished. To solve these problems, we propose a safe and self-recoverable reinforcement learning framework that can predict and prohibit other unsafe actions based on known, explored unsafe actions during the exploration process, and can self-recover to a safe state when a failure occurs. The maze navigation simulation results show that our approach can not only significantly reduce the number of failures but also accelerate the convergence of reinforcement learning.

Reinforcement learning (RL) has been widely used for robot autonomy because it can adapt to dynamic or unknown environments by automatically learning optimal control policies from the interactions between robots and environments. However, the practical deployment of RL can endanger the safety of both robots and environments because many RL methods must experience failures during the training phase. These failures can be reduced or avoided by assuming knowing prior knowledge about the states and environments in the training phase, but this assumption is easily invalid in practical applications, especially with unknown environments. In addition, restarting a training episode could be difficult in practice because the robot may be stuck in the failures. To solve these problems, we propose an operational safe control framework that can automatically recover from failures and reduce failure risks without any prior knowledge. Our framework consists of three steps: (1) detect failures and revert to safe actions, (2) collect correction samples to learn a potential that provides internal environment information to robots, (3) use the potential to shape a safe reward that biases safe explorations. A maze navigation example is used to demonstrate that our method outperforms the traditional reinforcement learning with significantly less failures.

Abstract Autonomous aerial manipulators have great potentials to assist humans or even fully automate manual labor-intensive tasks such as aerial cleaning, aerial transportation, infrastructure repair, and agricultural inspection and sampling. Reinforcement learning holds the promise of enabling persistent autonomy of aerial manipulators because it can adapt to different situations by automatically learning optimal policies from the interactions between the aerial manipulator and environments. However, the learning process itself could experience failures that can practically endanger the safety of aerial manipulators and hence hinder persistent autonomy. In order to solve this problem, we propose for the aerial manipulator a self-reflective learning strategy that can smartly and safely finding optimal policies for different new situations. This self-reflective manner consists of three steps: identifying the appearance of new situations, re-seeking the optimal policy with reinforcement learning, and evaluating the termination of self-reflection. Numerical simulations demonstrate, compared with conventional learning-based autonomy, our strategy can significantly reduce failures while still can finish the given task.