Long-term autonomy requires robust navigation in environments subject to dynamic and static changes, as well as adverse weather conditions. Teach-and-Repeat (T&R) navigation offers a reliable and cost-effective solution by avoiding the need for consistent global mapping; however, existing T&R systems lack a systematic solution to tackle various environmental variations such as weather degradation, ephemeral dynamics, and structural changes. This work proposes LTR$^{2}$, the first cross-modal, cross-platform LiDAR-Teach-and-Radar-Repeat system that systematically addresses these challenges. LTR$^{2}$leverages LiDAR during the teaching phase to capture precise structural information under normal conditions and utilizes 4D millimeter-wave radar during the repeating phase for robust operation under environmental degradations. To align sparse and noisy forward-looking 4D radar with dense and accurate omnidirectional 3D LiDAR data, we introduce a Cross-Modal Registration (CMR) network that jointly exploits Doppler-based motion priors and the physical laws governing LiDAR intensity and radar power density. Furthermore, we propose an adaptive fine-tuning strategy that incrementally updates the CMR network based on localization errors, enabling long-term adaptability to static environmental changes without ground-truth labels. We demonstrate that the proposed CMR network achieves state-of-the-art cross-modal registration performance on the open-access dataset. Then we validate LTR$^{2}$across three robot platforms over a large-scale, long-term deployment (40+ km over 6 months), including challenging conditions such as nighttime smoke. Experimental results and ablation studies demonstrate centimeter-level accuracy and strong robustness against diverse environmental disturbances, significantly outperforming existing approaches.

Control Barrier Functions (CBFs) have emerged as a prominent approach to designing safe navigation systems of robots. Despite their popularity, current CBF-based methods exhibit some limitations: optimization-based safe control techniques tend to be either myopic or computationally intensive, and they rely on simplified system models; conversely, the learning-based methods suffer from the lack of quantitative indication in terms of navigation performance and safety. In this paper, we present a new model-free reinforcement learning algorithm called Certificated Actor-Critic (CAC), which introduces a hierarchical reinforcement learning framework and well-defined reward functions derived from CBFs. We carry out theoretical analysis and proof of our algorithm, and propose several improvements in algorithm implementation. Our analysis is validated by two simulation experiments, showing the effectiveness of our proposed CAC algorithm.

A comprehensive understanding of 3D scenes is essential for autonomous vehicles (AVs), and among various perception tasks, occupancy estimation plays a central role by providing a general representation of drivable and occupied space. However, most existing occupancy estimation methods rely on LiDAR or cameras, which perform poorly in degraded environments such as smoke, rain, snow, and fog. In this paper, we propose 4D-ROLLS, the first weakly supervised occupancy estimation method for 4D radar using the LiDAR point cloud as the supervisory signal. Specifically, we introduce a method for generating pseudo-LiDAR labels, including occupancy queries and LiDAR height maps, as multi-stage supervision to train the 4D radar occupancy estimation model. Then the model is aligned with the occupancy map produced by LiDAR, fine-tuning its accuracy in occupancy estimation. Extensive comparative experiments validate the exceptional performance of 4D-ROLLS. Its robustness in degraded environments and effectiveness in cross-dataset training are qualitatively demonstrated. The model is also seamlessly transferred to downstream tasks BEV segmentation and point cloud occupancy prediction, highlighting its potential for broader applications. The lightweight network enables 4D-ROLLS model to achieve fast inference speeds at about 30 Hz on a 4060 GPU. The code of 4D-ROLLS will be made available at https://github.com/CLASS-Lab/4D-ROLLS.

Control Barrier Function (CBF) based quadratic programs (QPs) have become an effective method for enforcing safety in safety-critical systems and robotics. However, these methods often suffer from infeasibility or overly conservative relaxations when handling multiple constraints, potentially compromising safety. In this paper, we propose a hierarchical framework called “Safety-first" for control design, which simultaneously incorporates performance objectives formulated using Control Lyapunov Functions (CLFs), and safety guarantees via CBFs with input constraints. Unlike existing approaches, the proposed method guarantees solution feasibility while achieving improved performance, and it is scalable to an arbitrary number of CBF constraints. This scalability enables more precise and flexible representation of complex safety requirements using multiple simple CBFs. For application to mobile robot navigation, we employ Constrained Delaunay Triangulation (CDT) to construct multiple CBFs that approximate irregularly-shaped obstacles. Real-world experiments in cluttered and dynamic environments demonstrate that the Safety-first algorithm achieves safe navigation, validating both the theoretical guarantee and practical advantages over existing methods.

Accurate and robust geo-localization in all-weather conditions is essential for enabling autonomous vehicles and delivery robots to offer uninterrupted mobility services in the real world. In this paper, we propose the first camera and radar fusion based geo-localisation method that is robust to all-weather conditions. The core of the proposed method is to leverage the rich semantics information in images and sensing consistency in radars across all-weather. Our proposed method surpasses the state of the art camera-based and LiDAR-camera based methods in inclement weather conditions, shown by extensive comparative experiments. Notably, our approach requires only an open accessible map, eliminating the need for high-definition maps and offering a cost-effective solution for geo-localizing or globally localizing autonomous vehicles in any weather condition. Our code and trained model will be released publicly.

Multimodal sensor fusion has been successfully utilized in many odometry and localization methods as it increases both estimate accuracy and robustness in application scenarios. To address the challenge of odometry under varying-weather conditions, we propose a novel visual 4D radar fusion based odometry in an unsupervised deep learning approach. In our method, we adopt transformer-based cascaded decoders to facilitate efficient feature extraction of images and radar point clouds. Considering that radars are weather-agnostic and information-rich cameras are susceptible to adverse weathers, we deliberately introduce an adaptive attention-based feature fusion mechanism, in which the attention shifts dynamically to adapt to changing weather conditions based on the amount of information content in image features. Through extensive comparative experiments, our method surpasses different state-of-the-art single-modal odometry estimation methods. Our code and trained model will be released publicly.

An increasing number of Autonomous Mobile Robots (AMRs) are used in warehouses and factories in recent years. The risk of some of the AMRs being out of control is surging. Although Reinforcement Learning (RL)-based approaches have achieved dramatic success in the motion planning of a large number of AMRs, the available RL-based motion planning approaches cannot provide a safety guarantee for the remaining functional AMRs if some of the AMRs are out of control. To this end, this paper develops a scalable Multi-agent RL (MARL) with Control Barrier Function (CBF)-based shields algorithm. The MARL with CBF-based shields algorithm can address complex high-level tasks by MARL and deal with the safety issue of every single functional AMR by a low-level CBF-based shield. A CBF-based shield is designed for every single functional AMR to ensure that the action of the functional AMR is safe, even if an uncontrollable AMR is pursuing the functional AMR. Experiments are conducted based on simulated warehouse environments to evaluate the effectiveness and scalability of a safe RL-based motion planning approach (The safe RL-based motion planning approach developed in this study is demonstrated in a video: https://youtu.be/I7ja5nFVpY4). developed according to the MARL with CBF-based shields algorithm.

We aim to address the Nash equilibrium (NE) seeking problem for multiple players over Markovian switching communication networks in this article, where a new type of distributed synchronous discrete-time algorithm is proposed and utilized. Specifically, each player in the present game model is assumed to employ a gradient-like projection algorithm to choose its action based upon the estimated ones for all the others. Under the mild condition that the union network of all communication network candidates is connected, we show that the players' actions could converge to an arbitrarily small neighborhood of the NE in the mean-square sense by adjusting the algorithm parameters. It is further found that the unique NE is mean-square stable when it is not restricted by any constraint set. In addition, we show that the proposed distributed discrete-time NE seeking algorithm can be utilized to deal with the energy trading problem in microgrids where each microgrid is modeled as a rational player using a purchase price as its action to buy energy from other microgrids with surplus supplies. The energy market allocates the excess energy according to the principle of proportional distribution. Some numerical simulations are finally presented to verify the validity of the present discrete-time NE seeking algorithm in solving the energy trading problem.

Active disturbance rejection control (ADRC) is an efficient control technique to accommodate both internal uncertainties and external disturbances. In the typical ADRC framework, however, the design philosophy is to "force" the system dynamics into a double-integral form by an extended state observer (ESO) and then the controller is designed. Especially, the systems' physical structure has been neglected in such a design paradigm. In this article, a new ADRC framework is proposed by incorporating at a fundamental level the physical structure of the Euler-Lagrange (EL) systems. In particular, the differential feedback gain can be selected considerably small or even 0, due to the effective exploitation of the system's internal damping. The design principle stems from an analysis of the energy balance of EL systems, yielding a physically interpretable design. Moreover, the exploitation of the system's internal damping is thoroughly discussed, which is of practical significance for applications of the proposed design. Besides, a sliding-mode ESO is designed to improve the estimation performance over traditional linear ESO. Finally, the proposed control framework is illustrated through tracking control of an omnidirectional mobile robot. Extensive experimental tests are conducted to verify the proposed design as well as the discussions.

This paper presents a deep reinforcement learning (DRL) algorithm for orientation estimation using inertial sensors combined with a magnetometer. Lyapunov’s method in control theory is employed to prove the convergence of orientation estimation errors. The estimator gains and a Lyapunov function are parametrised by deep neural networks and learned from samples based on the theoretical results. The DRL estimator is compared with three well-known orientation estimation methods on both numerical simulations and real dataset collected from commercially available sensors. The results show that the proposed algorithm is superior for arbitrary estimation initialisation and can adapt to a drastic angular velocity profile for which other algorithms can be hardly applicable. To the best of our knowledge, this is the first DRL-based orientation estimation method with an estimation error boundedness guarantee.

Inertial measurement units are widely used in different fields to estimate the attitude. Many algorithms have been proposed to improve estimation performance. However, most of them still suffer from 1) inaccurate initial estimation, 2) inaccurate initial filter gain, and 3) non-Gaussian process and/or measurement noise. This paper will leverage reinforcement learning to compensate for the classical extended Kalman filter estimation, i.e., to learn the filter gain from the sensor measurements. We also analyse the convergence of the estimate error. The effectiveness of the proposed algorithm is validated on both simulated data and real data.

This paper presents a multiobjective optimization approach for path planning of autonomous surface vehicles (ASVs). A unique feature of the technique is the unification of the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) with good seamanship's practice along with hierarchical (rather than simultaneous) inclusion of objectives. The requirements of collision avoidance are formulated as mathematical inequalities and constraints in the optimization framework and thus collision-free manoeuvres and COLREGs-compliant behaviours are provided in a seafarer-like way. Specific expert knowledge is also taken into account when designing the multiobjective optimization algorithm. For example, good seamanship reveals that if allowed, an evasive manoeuvre with course changes is always preferred over one with speed changes in practical maritime navigation. As a result, a hierarchical sorting rule is designed to prioritize the objective of course/speed change preference over other objectives such as path length and path smoothness, and then incorporated into a specific evolutionary algorithm called hierarchical multiobjective particle swarm optimization (H-MOPSO) algorithm. The H-MOPSO algorithm solves the real-time path planning problem through finding solutions of the formulated optimization problem. The effectiveness of the proposed H-MOPSO algorithm is demonstrated through both desktop and high-fidelity networked bridge simulations.

Wide dissemination of unverified claims has negative influence on social lives. Rumors are easy to emerge and spread in the crowds especially in Online Social Network (OSN), due to its openness and extensive amount of users. Therefore, rumor detection in OSN is a very challenging and urgent issue. In this paper, we propose an Attention-Residual network combined with CNN (ARC), which is based on the content features for rumor detection. First, we build a data encoding model based on word-level data for contextual feature representation. Second, we propose a residual framework based on fine-tuned attention mechanism to capture long-range dependency. Third, we apply convolution neural network with varying window size to select important components and local features. Experiments on two twitter datasets demonstrate that the proposed model has better performance than other content-based methods both in rumor detection and early rumor verification. To the best of our knowledge, we are the first work that utilize attention model in conjunction with residual network on rumor detection.

In this paper, a recursive filter algorithm is developed to deal with the state estimation problem for power systems with quantized nonlinear measurements. The measurements from both the remote terminal units and the phasor measurement unit are subject to quantizations described by a logarithmic quantizer. Attention is focused on the design of a recursive filter such that, in the simultaneous presence of nonlinear measurements and quantization effects, an upper bound for the estimation error covariance is guaranteed and subsequently minimized. Instead of using the traditional approximation methods in nonlinear estimation that simply ignore the linearization errors, we treat both the linearization and quantization errors as norm-bounded uncertainties in the algorithm development so as to improve the performance of the estimator. For the power system with such kind of introduced uncertainties, a filter is designed in the framework of robust recursive estimation, and the developed filter algorithm is tested on the IEEE benchmark power system to demonstrate its effectiveness.