This article deals with fully distributed data-driven bipartite formation control for nonlinear discrete-time multi-input-multi-output multiagent systems (MASs) with unknown dynamics models and quantized information. Initially, a distributed combined measurement error function (DCMEF) is developed for MASs characterized by cooperative and competitive interactions. This function is designed to transform bipartite formation challenges into traditional consensus problems. Subsequently, a distributed compact form dynamic linearization model is established based on the designed DCMEF and input-output data of the MASs, eliminating the need for a strongly connected communication topology. Following this, a logarithmic quantization scheme and a dynamic event-triggered communication mechanism are devised to reduce the communication burden and enhance convergence speed. Finally, a data-driven fully distributed dynamic event-triggered bipartite formation control method is proposed, and its convergence is rigorously proven. Simulation studies and hardware experiments are conducted to validate the effectiveness of the proposed method.

This article studies the secure formation tracking problems for leader–follower multiagent systems (MASs) under limited resources, external disturbances, measurement noise, and random deception attacks, where a Bernoulli process is used to model random deception attacks occurring in the communication channels. A distributed sliding-mode observer (SMO) is proposed to estimate the inaccurate states of MASs, while handling the external perturbations. Then, a distributed dynamic triggering scheme is proposed based on the SMO states such that the interevent interval can be adjusted dynamically, and thus reduce the unnecessary resource consumption. By means of the SMO states and the event-triggered scheme, a distributed secure control protocol is proposed to realize the formation for MASs in the presence of one-to-all random deception attacks. Furthermore, it is extended to one-to-one random deception attack scenario. By employing the Lyapunov function and the linear matrix inequalities method, some sufficient conditions are provided to guarantee the bounded formation for MASs under a directed graph and both one-to-one and one-to-all attack scenarios. Experiments using multiple quadrotors are conducted to verify the developed formation control scheme.

World models have become increasingly popular in acting as learned traffic simulators. Recent work has explored replacing traditional traffic simulators with world models for policy training. In this work, we explore the robustness of existing metrics to evaluate world models as traffic simulators to see if the same metrics are suitable for evaluating a world model as a pseudo-environment for policy training. Specifically, we analyze the metametric employed by the Waymo Open Sim-Agents Challenge (WOSAC) and compare world model predictions on standard scenarios where the agents are fully or partially controlled by the world model (partial replay). Furthermore, since we are interested in evaluating the ego actionconditioned world model, we extend the standard WOSAC evaluation domain to include agents that are causal to the ego vehicle. Our evaluations reveal a significant number of scenarios where top-ranking models perform well under no perturbation but fail when the ego agent is forced to replay the original trajectory. To address these cases, we propose new metrics to highlight the sensitivity of world models to uncontrollable objects and evaluate the performance of world models as pseudo-environments for policy training and analyze some state-of-the-art world models under these new metrics.

This paper proposes an adaptive neural fault-tolerant approximated inverse control for a class of fractional-order (FO) nonlinear hysteretic systems. First, by co-designing the approximated inverse method and adaptive neural laws, the controller compensates hysteresis in the FO nonlinear hysteretic systems and maintains precise tracking under actuator and sensor faults. Then, combine the FO Nussbaum-type function with a coordinate transformation, the unknown fault gains are ingeniously handled. Additionally, the FO dynamic surface control (FODSC) scheme has applied which solve the "computational complexity" issue for FO backstepping (FOBS) method. Finally, the effectiveness of the proposed control strategy is validated through a simulation example.

This article studies a data-driven event-triggered sliding-mode control approach for wind turbines with prescribed performance and quantified information to maximize power generation efficiency. Initially, a partial form of the dynamic linearization model is established for the controlled wind turbine system. A logarithmic quantizer is considered to quantize data before it is transmitted. Then, a data-driven event-triggered sliding-mode control scheme is established, where a smooth function is employed to limit the control error to a prescribed range, and an event-triggered scheme is designed to reduce the communication frequencies of the controlled plant. Finally, the convergence of the formulated approach is rigorously demonstrated, and the simulation results further verify the effectiveness of the developed method.

This paper proposes approximate inference particle filtering for mobile robot simultaneous localization and mapping (SLAM) with landmarks. Range-bearing measurements are obtained by detecting landmarks using an onboard laser range finder and the maximum likelihood approach is used to handle unknown data associations. The system model is created depending on the robot motion and range-bearing measurements. The new particle filter is developed to estimate the robot pose and landmark locations separately based on approximate inferences, where the intractable distributions of the robot pose and landmark locations are approximated by optimal Gaussian distributions minimizing Kullback-Leibler divergences. Simulations and experiments are provided to show the performance of the proposed particle filter. Note to Practitioners—The SLAM technique is crucial to an autonomous mobile robot. The laser range finder perceives surroundings and is used for mobile robot SLAM in global positioning system denied environments. This paper proposes a mobile robot SLAM method based on the robot motion model and the onboard laser range finder. Range-bearing measurements are extracted from raw data of the laser range finder as the inputs of the method. The simulations and experiments indicate the proposed method has better accuracy and more robust to unknown data associations. The proposed method can be applied to many practical applications such as transport operations and mowing with a mobile robot. In the future, we will address the SLAM technique for multiple mobile robots.

This article develops an event-based adaptive robust control scheme for multiple networked Euler–Lagrange systems with a dynamic leader, addressing some key challenges such as parameter uncertainties, unknown perturbations, inherent nonlinearities, and limited resources, for the practical applications of networked robotics and autonomous systems. To reduce the communication network burden and the computational resources consumption, an adaptive dynamic triggering strategy is developed. In addition, to estimate the inaccurate states, a nested adaptive sliding-mode estimator is proposed. Then, a fully distributed adaptive dynamic event-based time-varying sliding-mode control strategy is developed based on the designed triggering scheme and estimator, without requiring any global information. This strategy reduces the effect of large initial errors on the varying gain during adaptation, and compensates for the influences of inherent nonlinearities, unknown external perturbations, and parameter uncertainties, making it feasible for practical implementation. Moreover, Lyapunov stability theory is used to guarantee the asymptotic convergence of the closed-loop networked systems. Finally, hardware experiments are conducted using multiple quadrotors to validate the effectiveness of the proposed control scheme in multiagent coordination tasks.

For an autonomous vehicle to plan a path in its environment, it must be able to accurately forecast the trajectory of all dynamic objects in its proximity. While many traditional methods encode observations in the scene to solve this problem, there are few approaches that consider the effect of the ego vehicle’s behavior on the future state of the world. In this paper, we introduce VRD, a vectorized world model-inspired approach to the multi-agent motion forecasting problem. Our method combines a traditional open-loop training regime with a novel dreamed closed-loop training pipeline that leverages a kinematic reconstruction task to imagine the trajectory of all agents, conditioned on the action of the ego vehicle. Quantitative and qualitative experiments are conducted on the Argoverse 2 multi-world forecasting evaluation dataset and the intersection drone (inD) dataset to demonstrate the performance of our proposed model. Our model achieves state-of-the-art performance on the single prediction miss rate metric on the Argoverse 2 dataset and performs on par with the leading models for the single prediction displacement metrics.

This paper presents a novel trajectory planning approach for two typical aerial transportation systems: UAV-slung-load and flying inverted pendulum. By integrating Rapidly-exploring Random Trees*(RRT*) into Nonlinear Model Predictive Control (NMPC), the proposed method en-hances motion planning, enabling effective navigation in complex environments while ensuring stability and safety. Simulation results demonstrate the approach's capability to overcome local minima and generate feasible trajectories, highlighting its potential to advance trajectory planning in UAV transportation systems.

This paper investigates a data-driven dynamic event-triggered sliding mode heading control problem for un-manned surface vehicles with uncertain dynamics models. First, a virtual sensor is introduced to establish a compact dynamic linearization model for the unmanned surface vehicle. Then, a dynamic event-triggered scheme is developed to alleviate the communication burden. Moreover, a sliding mode surface is designed, and a data-driven dynamic event-triggered sliding mode heading control approach is formulated. Finally, rigorous mathematical proofs are given, and several simulations demon-strate the effectiveness and superiority of the proposed method compared to existing approaches.

In the ever-evolving field of software engineering, the advent of large language models and conversational interfaces, exemplified by ChatGPT, represents a significant revolution. While their potential is evident in various domains, this paper expands upon our previous research, where we experimented with GPT –4, on its ability to create safety cases. A safety case is a structured argument supported by a body of evidence to demonstrate that a given system is safe to operate in a given environment. In this paper, we first determine GPT –4’s comprehension of the Goal Structuring Notation (GSN), a well-established notation for visually representing safety cases. Additionally, we conduct four distinct experiments using GPT –4 to evaluate its ability to generate safety cases within a specified system and application domain. To assess GPT –4’s performance in this context, we compare the results it produces with the ground-truth safety cases developed for an X-ray system, a machine learning-enabled component for tire noise recognition in a vehicle, and a lane management system from the automotive domain. This comparison enables us to gain valuable insights into the model’s generative capabilities. Our findings indicate that GPT –4 is able to generate moderately accurate and reasonable safety cases.

This article investigates the online learning and energy-efficient control issues for nonlinear discrete-time multiagent systems (MASs) with unknown dynamics models and antagonistic interactions. First, a distributed combined measurement error function is formulated using the signed graph theory to transfer the bipartite formation issue into a consensus issue. Then, an enhanced linearization controller model for the controlled MASs is developed by employing dynamic linearization technology. After that, an online learning adaptive event-triggered (ET) actor-critic neural network (AC-NN) framework for the MASs to implement bipartite formation control tasks is proposed by employing the optimized NNs and designed adaptive ET mechanism. Moreover, the convergence of the designed formation control framework is strictly proved by the constructed Lyapunov functions. Finally, simulation and experimental studies further demonstrate the effectiveness of the proposed algorithm.

This article investigates the information congestion problems for nonlinear discrete-time multi-input–multi-output multiagent systems (MASs) with fading channels when executing formation tasks. We first establish a virtual linear data model with a time-varying pseudo-Jacobian matrix variable for the MASs, which is independent of the dynamics model. Then, we formulate an event-triggered control scheme and a predictive compensation method to alleviate the communication burden and information congestion effects, respectively. Moreover, we propose two formation schemes for the MASs, considering limited communication resources, fading channels, and random delays to perform formation control and bipartite formation control tasks. The convergences of these two control protocols are strictly proved. Finally, simulations and hardware tests are conducted to verify the effectiveness of the proposed strategies.

Reconstructing 3D vehicles from noisy and sparse partial point clouds is of great significance to autonomous driving. Most existing 3D reconstruction methods cannot be directly applied to this problem because they are elaborately designed to deal with dense inputs with trivial noise. In this work, we propose a novel framework, dubbed MV-DeepSDF, which estimates the optimal Signed Distance Function (SDF) shape representation from multi-sweep point clouds to reconstruct vehicles in the wild. Although there have been some SDF-based implicit modeling methods, they only focus on single-view-based reconstruction, resulting in low fidelity. In contrast, we first analyze multi-sweep consistency and complementarity in the latent feature space and propose to transform the implicit space shape estimation problem into an element-to-set feature extraction problem. Then, we devise a new architecture to extract individual element-level representations and aggregate them to generate a set-level predicted latent code. This set-level latent code is an expression of the optimal 3D shape in the implicit space, and can be subsequently decoded to a continuous SDF of the vehicle. In this way, our approach learns consistent and complementary information among multi-sweeps for 3D vehicle reconstruction. We conduct thorough experiments on two real-world autonomous driving datasets (Waymo and KITTI) to demonstrate the superiority of our approach over state-of-the-art alternative methods both qualitatively and quantitatively.

The most challenging task for autonomous vehicles (AVs) is to share the road with human-driven vehicles (HDVs), since the driving behaviors of HDVs are unknown to the AVs. And AVs are supposed to make optimal decisions in real time based on onboard sensors only. To achieve this goal, we model the problem as a Partially Observable Markov Decision Process (POMDP) and propose an end-to-end decision-making framework for AVs based on a deep reinforcement learning (DRL) algorithm in combination with classical control methods to allow vehicles to achieve an adaptive cruise control. To reduce the gap in the Sim2real problem, a high-fidelity simulator is developed using ROS-Gazebo, which allows for a realistic multi-vehicle simulation with various sensors. The raw data obtained from these sensors is the input of a LSTM neural network, which could be mapped directly to the low-level commands. Then, an adaptive driving policy will be learned automatically from the virtual environment through self-play training mode. Finally, the trained model is tested in both virtual platform and corresponding real-world scenario, which validates the effectiveness and feasibility of the proposed decision-making framework.

This article studies fully distributed data-driven problems for nonlinear discrete-time multiagent systems (MASs) with fixed and switching topologies preventing injection attacks. We first develop an enhanced compact form dynamic linearization model by applying the designed distributed bipartite combined measurement error function of the MASs. Then, a fully distributed event-triggered bipartite consensus (DETBC) framework is designed, where the dynamics information of MASs is no longer needed. Meanwhile, the restriction of the topology of the proposed DETBC method is further relieved. To prevent the MASs from injection attacks, neural network based detection and compensation schemes are developed. Rigorous convergence proof that the bipartite consensus error is ultimately bounded is presented. Finally, the effectiveness of the designed method is verified through simulations and experiments.

Feature extraction or localization based on the fiducial marker could fail due to motion blur in real-world robotic applications. To solve this problem, a lightweight generative adversarial network, named Ghost-DeblurGAN, for real-time motion deblurring is developed in this paper. Furthermore, on account that there is no existing deblurring benchmark for such task, a new large-scale dataset, York-Tag, is proposed that provides pairs of sharp/blurred images containing fiducial markers. With the proposed model trained and tested on YorkTag, it is demonstrated that when applied along with fiducial marker systems to motion-blurred images, Ghost-DeblurGAN improves the marker detection significantly. The datasets and codes used in this paper are available at: https://github.com/York-SDCNLab/Ghost-DeblurGAN.

In this letter, we propose a novel iterative method for computing generalized inverse, based on a novel KKT formulation. The proposed iterative algorithm requires making four matrix and vector multiplications at each iteration and thus has low computational complexity. The proposed method is proved to be globally convergent without any condition. Furthermore, for fast computing generalized inverse, we present an acceleration scheme based on the proposed iterative method. The global convergence of the proposed acceleration algorithm is also proved. Finally, the effectiveness of the proposed iterative algorithm is evaluated numerically.

This paper presents a development of component synthesis vibration suppression (CSVS) method for control of spacecrafts with large flexible appendages. The proposed method eliminates unwanted flexible modes of vibrations while achieving the desired rigid body motion. Unlike traditional input shaping in which a numerical optimization is utilized, design for CSVS commands is based on analytic methodology and is relatively easy to implement. The robustness to uncertainties of dynamic modeling parameters is analyzed. A case study is performed on a time-fuel optimal control strategy using constant amplitude reaction jet thrusters. Both simulation and experimental results validate the effectiveness of the CSVS approach.

In this paper, an enhanced hybrid control algorithm is proposed to control the rotation of a flexible beam while suppressing the beam's vibration. The control law combines an enhanced PD feedback with nonlinear differentiator to derive high-quality velocity signal to control gross motion of the beam, and a vibration control by PZT actuators bonded on the surface of the beam. The significance of the proposed method are threefold: i) The enhanced PD control is a non-model based control, and appears to be more robust against the noise; ii) The linear velocity in contrast the angular velocity is used in the PZT actuator control, a signal which is easily available; iii) A unique solution is provided for examination of actuator placement, based on the analysis of mode shape functions. Experimental results validate these theoretical analyses.

This paper presents a development of component synthesis vibration suppression (CSVS) method for control of flexible structures. The proposed method eliminates unwanted flexible modes of vibration while achieving the desired rigid body motion. The robustness to uncertainties of dynamic modeling parameters is analyzed. Unlike traditional input shaping, in which a numerical optimization is used, design for CSVS commands is based on analytic methodology and is relatively easy to implement. A case study is performed on a time-fuel optimal control strategy using constant amplitude reaction jet thrusters. Both simulation and experimental results validate the effectiveness of the proposed approach.