Safe offline RL is a promising way to bypass risky online interactions towards safe policy learning. Most existing methods only enforce soft constraints, i.e., constraining safety violations in expectation below thresholds predetermined. This can lead to potentially unsafe outcomes, thus unacceptable in safety-critical scenarios. An alternative is to enforce the hard constraint of zero violation. However, this can be challenging in offline setting, as it needs to strike the right balance among three highly intricate and correlated aspects: safety constraint satisfaction, reward maximization, and behavior regularization imposed by offline datasets. Interestingly, we discover that via reachability analysis of safe-control theory, the hard safety constraint can be equivalently translated to identifying the largest feasible region given the offline dataset. This seamlessly converts the original trilogy problem to a feasibility-dependent objective, i.e., maximizing reward value within the feasible region while minimizing safety risks in the infeasible region. Inspired by these, we propose FISOR (FeasIbility-guided Safe Offline RL), which allows safety constraint adherence, reward maximization, and offline policy learning to be realized via three decoupled processes, while offering strong safety performance and stability. In FISOR, the optimal policy for the translated optimization problem can be derived in a special form of weighted behavior cloning. Thus, we propose a novel energy-guided diffusion model that does not require training a complicated time-dependent classifier to extract the policy, greatly simplifying the training. We compare FISOR against baselines on DSRL benchmark for safe offline RL. Evaluation results show that FISOR is the only method that can guarantee safety satisfaction in all tasks, while achieving top returns in most tasks.
Medical image segmentation, particularly in the context of ultrasound data, is a crucial aspect of computer vision and medical imaging. This paper delves into the complexities of uncertainty in the segmentation process, focusing on fetal head and femur ultrasound images. The proposed methodology involves extracting target contours and exploring techniques for precise parameter measurement. Uncertainty modeling methods are employed to enhance the training and testing processes of the segmentation network. The study reveals that the average absolute error in fetal head circumference measurement is 8.0833mm, with a relative error of 4.7347%. Similarly, the average absolute error in fetal femur measurement is 2.6163mm, with a relative error of 6.3336%. Uncertainty modeling experiments employing Test-Time Augmentation (TTA) demonstrate effective interpretability of data uncertainty on both datasets. This suggests that incorporating data uncertainty based on the TTA method can support clinical practitioners in making informed decisions and obtaining more reliable measurement results in practical clinical applications. The paper contributes to the advancement of ultrasound image segmentation, addressing critical challenges and improving the reliability of biometric measurements.
Discrepancies between the true Martian atmospheric density and the onboard density model can significantly impair the performance of spacecraft entry navigation filters. This work introduces a new approach to online filtering for Martian entry by using a neural network to estimate atmospheric density and employing a consider analysis to account for the uncertainty in the estimate. The network is trained on an exponential atmospheric density model, and its parameters are dynamically adapted in real time to account for any mismatches between the true and estimated densities. The adaptation of the network is formulated as a maximum likelihood problem, leveraging the measurement innovations of the filter to identify optimal network parameters. The incorporation of a neural network enables the use of stochastic optimizers known for their efficiency in the machine learning domain within the context of the maximum likelihood approach. Performance comparisons against previous approaches are conducted in various realistic Mars entry navigation scenarios, resulting in superior estimation accuracy and precise alignment of the estimated density with a broad selection of realistic Martian atmospheres sampled from perturbed Mars-GRAM data.
Self-navigation in non-coordinating crowded environments is formidably challenging within multi-agent systems consisting of non-holonomic robots operating through local sensing. Our primary objective is the development of a novel, rapid, sensor-driven, self-navigation controller that directly computes control commands to enable safe maneuvering while coexisting with other agents. We propose an input-constrained feedback controller meticulously crafted for non-holonomic mobile robots and the characterization of associated invariant sets. The invariant sets are the key to maintaining stability and safety amidst the non-cooperating agents. We then propose a planning strategy that strategically guides the generation of invariant sets toward the agent's intended target. This enables the agents to directly compute theoretically safe control inputs without explicitly requiring pre-planned paths/trajectories to reliably navigate through crowded multi-agent environments. The practicality of our technique is demonstrated through hardware experiments, and the ability to parallelize computations to shorten computational durations for synthesizing safe control commands. The proposed approach finds potential applications in crowded multi-agent scenarios that require rapid control computations based on perceived safety bounds during run-time.
Two-timescale stochastic approximation (TTSA) is among the most general frameworks for iterative stochastic algorithms. This includes well-known stochastic optimization methods such as SGD variants and those designed for bilevel or minimax problems, as well as reinforcement learning like the family of gradient-based temporal difference (GTD) algorithms. In this paper, we conduct an in-depth asymptotic analysis of TTSA under controlled Markovian noise via central limit theorem (CLT), uncovering the coupled dynamics of TTSA influenced by the underlying Markov chain, which has not been addressed by previous CLT results of TTSA only with Martingale difference noise. Building upon our CLT, we expand its application horizon of efficient sampling strategies from vanilla SGD to a wider TTSA context in distributed learning, thus broadening the scope of Hu et al. (2022). In addition, we leverage our CLT result to deduce the statistical properties of GTD algorithms with nonlinear function approximation using Markovian samples and show their identical asymptotic performance, a perspective not evident from current finite-time bounds.
Despite the promise of superior performance under challenging conditions, event-based motion estimation remains a hard problem owing to the difficulty of extracting and tracking stable features from event streams. In order to robustify the estimation, it is generally believed that fusion with other sensors is a requirement. In this work, we demonstrate reliable, purely event-based visual odometry on planar ground vehicles by employing the constrained non-holonomic motion model of Ackermann steering platforms. We extend single feature n-linearities for regular frame-based cameras to the case of quasi time-continuous event-tracks, and achieve a polynomial form via variable degree Taylor expansions. Robust averaging over multiple event tracks is simply achieved via histogram voting. As demonstrated on both simulated and real data, our algorithm achieves accurate and robust estimates of the vehicle's instantaneous rotational velocity, and thus results that are comparable to the delta rotations obtained by frame-based sensors under normal conditions. We furthermore significantly outperform the more traditional alternatives in challenging illumination scenarios. The code is available at \url{https://github.com/gowanting/NHEVO}.
This paper investigates a cooperative motion planning problem for large-scale connected autonomous vehicles (CAVs) under limited communications, which addresses the challenges of high communication and computing resource requirements. Our proposed methodology incorporates a parallel optimization algorithm with improved consensus ADMM considering a more realistic locally connected topology network, and time complexity of O(N) is achieved by exploiting the sparsity in the dual update process. To further enhance the computational efficiency, we employ a lightweight evolution strategy for the dynamic connectivity graph of CAVs, and each sub-problem split from the consensus ADMM only requires managing a small group of CAVs. The proposed method implemented with the receding horizon scheme is validated thoroughly, and comparisons with existing numerical solvers and approaches demonstrate the efficiency of our proposed algorithm. Also, simulations on large-scale cooperative driving tasks involving 80 vehicles are performed in the high-fidelity CARLA simulator, which highlights the remarkable computational efficiency, scalability, and effectiveness of our proposed development. Demonstration videos are available at https://henryhcliu.github.io/icadmm_cmp_carla.
Illegitimate intelligent reflective surfaces (IRSs) can pose significant physical layer security risks on multi-user multiple-input single-output (MU-MISO) systems. Recently, a DISCO approach has been proposed an illegitimate IRS with random and time-varying reflection coefficients, referred to as a "disco" IRS (DIRS). Such DIRS can attack MU-MISO systems without relying on either jamming power or channel state information (CSI), and classical anti-jamming techniques are ineffective for the DIRS-based fully-passive jammers (DIRS-based FPJs). In this paper, we propose an IRS-enhanced anti-jamming precoder against DIRS-based FPJs that requires only statistical rather than instantaneous CSI of the DIRS-jammed channels. Specifically, a legitimate IRS is introduced to reduce the strength of the DIRS-based jamming relative to the transmit signals at a legitimate user (LU). In addition, the active beamforming at the legitimate access point (AP) is designed to maximize the signal-to-jamming-plus-noise ratios (SJNRs). Numerical results are presented to evaluate the effectiveness of the proposed IRS-enhanced anti-jamming precoder against DIRS-based FPJs.
In wireless communications, electromagnetic theory and information theory constitute a pair of fundamental theories, bridged by antenna theory and wireless propagation channel modeling theory. Up to the fifth generation (5G) wireless communication networks, these four theories have been developing relatively independently. However, in sixth generation (6G) space-air-ground-sea wireless communication networks, seamless coverage is expected in the three-dimensional (3D) space, potentially necessitating the acquisition of channel state information (CSI) and channel capacity calculation at anywhere and any time. Additionally, the key 6G technologies such as ultra-massive multiple-input multiple-output (MIMO) and holographic MIMO achieves intricate interaction of the antennas and wireless propagation environments, which necessitates the joint modeling of antennas and wireless propagation channels. To address the challenges in 6G, the integration of the above four theories becomes inevitable, leading to the concept of the so-called electromagnetic information theory (EIT). In this article, a suite of 6G key technologies is highlighted. Then, the concepts and relationships of the four theories are unveiled. Finally, the necessity and benefits of integrating them into the EIT are revealed.
The usage of federated learning (FL) in Vehicular Ad hoc Networks (VANET) has garnered significant interest in research due to the advantages of reducing transmission overhead and protecting user privacy by communicating local dataset gradients instead of raw data. However, implementing FL in VANETs faces challenges, including limited communication resources, high vehicle mobility, and the statistical diversity of data distributions. In order to tackle these issues, this paper introduces a novel framework for hierarchical federated learning (HFL) over multi-hop clustering-based VANET. The proposed method utilizes a weighted combination of the average relative speed and cosine similarity of FL model parameters as a clustering metric to consider both data diversity and high vehicle mobility. This metric ensures convergence with minimum changes in cluster heads while tackling the complexities associated with non-independent and identically distributed (non-IID) data scenarios. Additionally, the framework includes a novel mechanism to manage seamless transitions of cluster heads (CHs), followed by transferring the most recent FL model parameter to the designated CH. Furthermore, the proposed approach considers the option of merging CHs, aiming to reduce their count and, consequently, mitigate associated overhead. Through extensive simulations, the proposed hierarchical federated learning over clustered VANET has been demonstrated to improve accuracy and convergence time significantly while maintaining an acceptable level of packet overhead compared to previously proposed clustering algorithms and non-clustered VANET.