To address partial node failures in unmanned aerial vehicle swarms, self-healing communication techniques are commonly employed to restore backbone connectivity while preserving area coverage. However, existing heuristic methods struggle to scale under large-scale failures and dynamic conditions, while learning-based approaches often suffer from spatial collapse, resulting in significant coverage loss. To overcome these limitations, we propose a resilient self-healing framework that enables rapid connectivity recovery and wide-area coverage through a divide-and-conquer strategy. First, we introduce a buffered dynamic virtual force expansion mechanism that categorizes pairwise distances into repulsive, neutral, and attractive zones, allowing nodes to disperse appropriately while preserving communication links and maintaining safety buffers. Subsequently, we design a multipartite graph convolution module to reason over subnetwork-level interactions and facilitate cross-subnetwork reconnection with global structural awareness. Finally, we develop an adaptive fusion strategy that combines both outputs with time-aware weighting to generate the final motion decisions. Experimental results in both random and uniform deployment scenarios demonstrate that our approach outperforms many state-of-the-art methods in terms of connectivity restoration speed and communication coverage.

During the transmission of Controller Area Network (CAN) data streams in intelligent connected vehicles, security risks such as non-compliant data reporting and cross-border data leakage inevitably arise. Traditional anomaly detection methods based on statistics and machine learning often fail to comprehensively identify irregularities in the content of transmitted data. To overcome the limitation, this paper proposes an anomaly detection approach for CAN data streams that integrates a heterogeneous Long Short-Term Memory (LSTM) model with an Attention Mechanism (AM). First, periodic characteristics at the byte level within CAN message fields are statistically analyzed, revealing distinctive inter-byte feature variations. Based on the periodicity of each byte-level data stream, a heterogeneous LSTM model incorporating varied parameters-such as time step size and network width-is designed. A corresponding detection framework leveraging heterogeneous LSTM with AM (LSTMAM) is introduced. Furthermore, a fusion strategy between LSTM and the attention mechanism is developed to weight the influence of different hidden states on prediction outcomes. Finally, comparative experiments under various attack scenarios were conducted utilizing publicly available and vehicle-collected CAN message datasets. Comparative results demonstrate that the proposed method significantly improves detection accuracy over existing approaches, validating its effectiveness at identifying anomalies in CAN data streams.

The wheel-legged quadruped robot, equipped with leg and end-wheel structures, possesses the capability to traverse continuous surfaces at relatively high speeds while also being able to navigate unstructured terrains. However, designing its controller using traditional methods presents significant challenges, particularly under conditions of limited or lost external environmental perception and highly variable terrain complexity. In light of this issue, this paper proposes a novel, concise, and effective reinforcement learning framework. The framework employs an asymmetric actor-critic structure incorporating a velocity estimation network and leverages multi-contact states generated by a central pattern generator for fusion, thereby training a single control policy to address the robust and flexible traversal of complex terrains by wheel-legged robots relying solely on an inertial measurement unit and joint sensors. Our method enables the modified Unitree Go1-based wheel-legged robot to traverse various challenging terrains, such as steps, high obstacles, rough terrain, and low-adhesion surfaces, while ensuring efficient locomotion performance on smooth and continuous surfaces. The effectiveness of the framework’s training results has been validated through testing in both simulation and real-world environments.

The security of cyber-physical systems (CPS) constitutes a crucial aspect in system design and control. This paper investigates the cyber security of an electric vehicle under a malicious cyber attack from a control design perspective. The work presented in this study focuses on addressing the problem of encountering a certain type of malicious attacks, false data injection (FDI), that can damage the system and prevent the actuators from working properly. First, the problem is formulated and a convergence analysis is carried out, then a risk-averse controller is derived for the unconstrained and constrained control input signal. Next, a statistical-based algorithm, using the z-score and cumulative sum, was devised to detect possible attacks that may affect the system. Computer-aided simulations were performed using a vehicle model for the regulation and tracking problems. The results have proven the efficacy of the proposed method to detect and counteract a specific type of cyber attacks.

A coordinated control method integrating emergency brake and direct yaw moment control (DYC) for distributed vehicles is established. The model predictive control (MPC) framework incorporates motor characteristics as constraint conditions, with the objective cost function solved using quadratic programming. The weighting of the emergency brake and DYC coordinated control is dynamically adjusted to accommodate various driving conditions. This strategy enables vehicles to achieve maximum braking torque while ensuring lateral stability and effective anti-lock braking. Simulation results demonstrate that the MPC-based coordinated control significantly improve lateral stability and brake performance. Vehicle brake in approximately 2.5 seconds with yaw rate error less than 0.05 rad/s during emergency braking while cornering.

In this paper, we propose an improved and effective control framework for wheel-legged vehicles. Our framework allows the vehicle to navigate uneven terrains while maintaining balance and tracking the trajectory of the center of mass (CoM). In detail, single rigid body dynamics (SRBD) and whole body dynamics (WBD) are introduced to describe the body motion at first. Then, based on the SRBD, by introducing the output of the longitudinal speed controller as a constraint, a body balance controller is designed, which can simultaneously optimize the wheel driving force and the support force required by the body. The joint controller is designed through a WBD model and the overall dynamics compensation is performed. Ultimately, by adjusting gain weights to coordinate different control computation results, whole vehicle control is achieved. Validation in simulation demonstrates that our wheel-legged vehicle can navigate uneven terrain at a maximum of 3.0m/s, showing the feasibility of this framework.

Heavy quadrupedal drives have great potential for overcoming obstacles, showing great possibilities for transportation industries in complex environments. Ground reaction force (GRF) is a crucial state variable for quadrupedal control. Most GRF observations are implemented in lightweight quadrupeds, with little consideration of the loading being static or slippery on the body. However, the load information is vital to the heavy-duty quadruped applied in transportation tasks. In this paper, we disassembled the whole-body dynamics into the body dynamics combined with the individual floating single-leg dynamics and completed observing the virtual coupling effects between the body and legs. Based on the observed coupling force and centroidal dynamics (CD), the GRF of a stance leg is obtained without the awareness of body weight, movement, and load information. Furthermore, we utilized the body dynamics and the observed virtual force to obtain the body's unknown payload. By reconstructing the moment balance equation, we obtained the payload's position concerning the body coordinate. Compared to conventional quadrupedal GRF observation methods, this framework achieves higher observation accuracy in heavy quadrupeds without load and body information. Additionally, it enables real-time calculation of load magnitude and position.

Accelerating regular expression (regex) matching, or equivalently finite automata processing, using FPGAs is widely adopted by many demanding regex-based applications to improve throughput and power efficiency. However, offloading a large regex rule set entirely into an FPGA is expensive, if not unaffordable, due to the limited on-chip resources. In this paper, we propose FRA-FPGA (Fast Reconfigurable Automata on FPGAs), a homogeneous NFA architecture on FPGAs which can be reconfigured within 1μs. Meanwhile, the reconfiguration time of FRA-FPGA is independent of the number of regex rules it accommodates. Because FRA-FPGA can be reloaded quickly, it is feasible to offload the small subset of activated regex rules into FRA-FPGA dynamically, as opposed to compiling the whole regex rule set into FPGA beforehand. We implemented FRA-FPGA on the Xilinx U200 card to accelerate Hyperscan. Our experimental results show that the FRA-FPGA can improve Hyperscan's throughput by about 15 times (stream mode) and 33 times (block mode), respectively, while consuming only 4.23% logic resources and 16.64% memory resources of the FPGA(VU9P).