The problem of adaptive estimation of constant parameters in the linear regressor model is studied without the hypothesis that regressor is Persistently Excited (PE). First, the initial vector estimation problem is transformed to a series of the scalar ones using the method of Dynamic Regressor Extension and Mixing (DREM). Second, several adaptive estimation algorithms are proposed for the scalar scenario. In such a case, if the regressor may be nullified asymptotically or in a finite time, then the problem of estimation is also posed on a finite interval of time. Robustness of the proposed algorithms with respect to measurement noise and exogenous disturbances is analyzed. The efficiency of the designed estimators is demonstrated in numeric experiments for academic examples.

Soft robotics is closely related to embodied intelligence in the joint exploration of the means to achieve more natural and effective robotic behaviors via physical forms and intelligent interactions. Embodied intelligence emphasizes that intelligence is affected by the synergy of the brain, body, and environment, focusing on the interaction between agents and the environment. Under this framework, the design and control strategies of soft robotics depend on their physical forms and material properties, as well as algorithms and data processing, which enable them to interact with the environment in a natural and adaptable manner. At present, embodied intelligence has comprehensively integrated related research results on the evolution, learning, perception, decision making in the field of intelligent algorithms, as well as on the behaviors and controls in the field of robotics. From this perspective, the relevant branches of the embodied intelligence in the context of soft robotics were studied, covering the computation of embodied morphology; the evolution of embodied AI; and the perception, control, and decision making of soft robotics. Moreover, on this basis, important research progress was summarized, and related scientific problems were discussed. This study can provide a reference for the research of embodied intelligence in the context of soft robotics.

Intelligent vehicles, including autonomous vehicles and vehicles equipped with ADAS systems, are single-agent systems that navigate solely on the information collected by themselves. However, despite rapid advancements in hardware and algorithms, many accidents still occur due to the limited sensing coverage from a single-agent perception angle. These tragedies raise a critical question of whether single-agent autonomous driving is safe. Preliminary investigations on this safety issue led us to create a C-V2X-enabled collaborative autonomous driving framework (CCAD) to observe the driving circumstance from multiple perception angles. Our framework uses C-V2X technology to connect infrastructure with vehicles and vehicles with vehicles to transmit safety-critical information and to add safety redundancies. By enabling these communication channels, we connect previously independent single-agent vehicles and existing infrastructure. This paper presents a prototype of our CCAD framework with RSU and OBU as communication devices and an edge-computing device for data processing. We also present a case study of successfully implementing an infrastructure-based collaborative lane-keeping with the CCAD framework. Our case study evaluations demonstrate that the CCAD framework can transmit, in real-time, personalized lane-keeping guidance information when the vehicle cannot find the lanes. The evaluations also indicate that the CCAD framework can drastically improve the safety of single-agent intelligent vehicles and open the doors to many more collaborative autonomous driving applications.

In order to increase the compatibility between underwater robots and the underwater environment and inspired by the coconut octopus’s underwater bipedal walking, a method was proposed for bipedal walking for an underwater soft robot based on a spring-loaded inverted pendulum (SLIP) model. Using the characteristics of octopus tentacles rolling on the ground, a wrist arm was designed using the cable-driven method, and an underwater SLIP bipedal walking model was established, which makes an underwater soft robot more suitable for moving on uneven ground. An underwater bipedal walking soft robot based on coconut octopus was then designed, and a machine vision algorithm was used to extract the motion information for analysis. Experimental analysis shows that the underwater bipedal walking robot can achieve an average speed of 6.48 cm s⁻¹, and the maximum instantaneous speed can reach 8.14 cm s⁻¹.

As shipping continues to play an increasingly important role in world trade, there are consequently a large number of ships at sea at any given time, posing a risk to maritime traffic safety. Therefore, the tracking and monitoring of ships at sea has gradually attracted the attention of scholars. Ship trajectory prediction comprises an important aspect of ship tracking and monitoring. Trajectory prediction describes the forecasting of a ship’s future trajectory over a period of time through use of historical trajectory information of the ship, so as to predict the sailing dynamics of the ship in advance. Accurate trajectory prediction can help maritime regulatory authorities improve supervision efficiency and reduce collisions between ships. Temporal Convolutional Network (TCN) offers good time memory ability and has shown better performance in time series prediction in recent years. Ship trajectory sequence belongs to the category of time series. Thus, in this paper, we introduce TCN into the field of ship trajectory prediction and improve on it, and propose Tiered-TCN (TTCN). The attention mechanism is a way to help neural networks learn data features by highlighting features that have a greater impact on predicted values. Gate Recurrent Unit (GRU) is an important variant of Recurrent Neural Networks (RNN), which bears a strong nonlinear fitting ability. In this paper, TTCN, attention mechanism and GRU network are integrated to construct a hybrid model for trajectory prediction, which is referred to as TTCN-Attention-GRU (TTAG). By optimizing the advantages of each module, the prediction effect is achieved with high precision. The experimental results show that the TTAG model is superior to all the baseline models presented in this paper.

With the widespread use of Internet of things(IoT) devices, it generates an enormous volume of data, and it is a challenge to mine the IoT data value while ensuring security and privacy. Federated learning is a decentralized approach for training data located on edge devices, such as mobile phones and IoT devices, while keeping privacy, efficiency, and security. However, the Non-IID (non-independent and identically distributed) data, always greatly impacts the performance of the global model. In this paper, we propose a FedDynamic algorithm to solve the statistical challenge of federated learning caused by Non-IID. As Non-IID data can lead to significant differences in model parameters between edge devices, we set different weights for different devices during model aggregation to get a high-performance global model. We analyze and exact key indices (local model accuracy, local data quality, and model difference between local models and the global model), which can reflect the quality of the model, and calculate the aggregation weight for edge devices based on the key indices. Furthermore, we dynamically adjust aggregation weight based on accuracy’s variety to solve weight staleness during the training process. Experiments on the MNIST, FMNIST, EMNIST, CINIC-10 and CIFAR-10 datasets show that the FedDynamic algorithm has better accuracy and convergence performance, compared to the FedAvg, FedProx and Scaffold algorithms.