Channel Estimation for Beyond Diagonal Reconfigurable Intelligent Surfaces with Group-Connected Architectures

We study channel estimation for a beyond diagonal reconfigurable intelligent surface (BD-RIS) aided multiple input single output system. We first describe the channel estimation strategy based on the least square (LS) method, derive the mean square error (MSE) of the LS estimator, and formulate the BD-RIS design problem that minimizes the estimation MSE with unique constraints induced by group-connected architectures of BD-RIS. Then, we propose an efficient BD-RIS design which theoretically guarantees to achieve the MSE lower bound. Finally, we provide simulation results to verify the effectiveness of the proposed channel estimation scheme.

Beyond Diagonal Reconfigurable Intelligent Surfaces Utilizing Graph Theory: Modeling, Architecture Design, and Optimization

Recently, beyond diagonal reconfigurable intelligent surface (BD-RIS) has been proposed to generalize conventional RIS. BD-RIS has a scattering matrix that is not restricted to being diagonal and thus brings a performance improvement over conventional RIS. While different BD-RIS architectures have been proposed, it still remains an open problem to develop a systematic approach to design BD-RIS architectures achieving the optimal trade-off between performance and circuit complexity. In this work, we propose novel modeling, architecture design, and optimization for BD-RIS based on graph theory. This graph theoretical modeling allows us to develop two new efficient BD-RIS architectures, denoted as tree-connected and forest-connected RIS. Tree-connected RIS, whose corresponding graph is a tree, is proven to be the least complex BD-RIS architecture able to achieve the performance upper bound in multiple-input single-output (MISO) systems. Besides, forest-connected RIS allows us to strike a balance between performance and complexity, further decreasing the complexity over tree-connected RIS. To optimize tree-connected RIS, we derive a closed-form global optimal solution, while forest-connected RIS is optimized through a low-complexity iterative algorithm. Numerical results confirm that tree-connected (resp. forest-connected) RIS achieves the same performance as fully-connected (resp. group-connected) RIS, while reducing the complexity by up to 16.4 times.

Synergizing Beyond Diagonal Reconfigurable Intelligent Surface and Rate-Splitting Multiple Access

This work focuses on the synergy of rate-splitting multiple access (RSMA) and beyond diagonal reconfigurable intelligent surface (BD-RIS) to enlarge the coverage, improve the performance, and save on antennas. Specifically, we employ a multi-sector BD-RIS modeled as a prism, which can achieve highly directional full-space coverage, in a multiuser multiple input single output communication system. With the multi-sector BD-RIS aided RSMA model, we jointly design the transmit precoder and BD-RIS matrix under the imperfect channel state information (CSI) conditions. The robust design is performed by solving a stochastic average sum-rate maximization problem. With sample average approximation and weighted minimum mean square error-rate relationship, the stochastic problem is transformed into a deterministic one with multiple blocks, each of which is iteratively designed. Simulation results show that multi-sector BD-RIS aided RSMA outperforms space division multiple access schemes. More importantly, synergizing multi-sector BD-RIS with RSMA is an efficient strategy to reduce the number of active antennas at the transmitter and the number of passive antennas in BD-RIS.

Reconfigurable Intelligent Surfaces 2.0: Beyond Diagonal Phase Shift Matrices

Reconfigurable intelligent surface (RIS) has been envisioned as a promising technique to enable and enhance future wireless communications due to its potential to engineer the wireless channels in a cost-effective manner. Extensive research attention has been drawn to the use of conventional RIS 1.0 with diagonal phase shift matrices, where each RIS element is connected to its own load to ground but not connected to other elements. However, the simple architecture of RIS 1.0 limits its flexibility of manipulating passive beamforming. To fully exploit the benefits of RIS, in this paper, we introduce RIS 2.0 beyond diagonal phase shift matrices, namely beyond diagonal RIS (BD-RIS). We first explain the modeling of BD-RIS based on the scattering parameter network analysis and classify BD-RIS by the mathematical characteristics of the scattering matrix, supported modes, and architectures. Then, we provide simulations to evaluate the sum-rate performance with different modes/architectures of BD-RIS. We summarize the benefits of BD-RIS in providing high flexibility in wave manipulation, enlarging coverage, facilitating the deployment, and requiring low complexity in resolution bit and element numbers. Inspired by the benefits of BD-RIS, we also discuss potential applications of BD-RIS in various wireless systems. Finally, we list key challenges in modeling, designing, and implementing BD-RIS in practice and point to possible future research directions for BD-RIS.

A Dual-Function Radar-Communication System Empowered by Beyond Diagonal Reconfigurable Intelligent Surface

This work focuses on the use of reconfigurable intelligent surface (RIS) in dual-function radar-communication (DFRC) systems to improve communication capacity and sensing precision, and enhance coverage for both functions. In contrast to most of the existing RIS aided DFRC works where the RIS is modeled as a diagonal phase shift matrix and can only reflect signals to half space, we propose a novel beyond diagonal RIS (BD-RIS) aided DFRC system. Specifically, the proposed BD-RIS supports the hybrid reflecting and transmitting mode, and is compatible with flexible single/group/fully-connected architectures, enabling the system to realize full-space coverage. To achieve the expected benefits, we jointly optimize the transmit waveform, the BD-RIS coefficients, and sensing receive filters, by maximizing the minimum signal-to-clutter-plus-noise ratio for fair target detection, subject to the constraints of the communication quality of service, different BD-RIS architectures and power budget. To solve the non-convex and non-smooth max-min problem, a general solution based on the alternating direction method of multipliers is provided for all considered BD-RIS architectures. Numerical simulations validate the efficacy of the proposed algorithm and show the superiority of the BD-RIS aided DFRC system in terms of both communication and sensing compared to conventional RIS aided DFRC.

A Dynamic Grouping Strategy for Beyond Diagonal Reconfigurable Intelligent Surfaces with Hybrid Transmitting and Reflecting Mode

Beyond diagonal reconfigurable intelligent surface (BD-RIS) is a novel branch of RIS which breaks through the limitation of traditional RIS with diagonal scattering matrices. However, the existing research focuses on BD-RIS with fixed architectures regardless of channel state information (CSI), which limit the achievable performance of BD-RIS. To solve this issue, in this paper, we propose a novel dynamically group-connected BD-RIS based on a dynamic grouping strategy. Specifically, RIS antennas are dynamically divided into several subsets adapting to the CSI, yielding a permuted block-diagonal scattering matrix. To verify the effectiveness of the proposed dynamically group-connected BD-RIS, we propose an efficient algorithm to optimize the BD-RIS with dynamic grouping for a BD-RIS-assisted multi-user multiple-input single-output system. Simulation results show that the proposed dynamically group-connected architecture outperforms fixed group-connected architectures.

StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networks

Obstacle detection is a safety-critical problem in robot navigation, where stereo matching is a popular vision-based approach. While deep neural networks have shown impressive results in computer vision, most of the previous obstacle detection works only leverage traditional stereo matching techniques to meet the computational constraints for real-time feedback. This paper proposes a computationally efficient method that leverages a deep neural network to detect occupancy from stereo images directly. Instead of learning the point cloud correspondence from the stereo data, our approach extracts the compact obstacle distribution based on volumetric representations. In addition, we prune the computation of safety irrelevant spaces in a coarse-to-fine manner based on octrees generated by the decoder. As a result, we achieve real-time performance on the onboard computer (NVIDIA Jetson TX2). Our approach detects obstacles accurately in the range of 32 meters and achieves better IoU (Intersection over Union) and CD (Chamfer Distance) scores with only 2% of the computation cost of the state-of-the-art stereo model. Furthermore, we validate our method's robustness and real-world feasibility through autonomous navigation experiments with a real robot. Hence, our work contributes toward closing the gap between the stereo-based system in robot perception and state-of-the-art stereo models in computer vision. To counter the scarcity of high-quality real-world indoor stereo datasets, we collect a 1.36 hours stereo dataset with a Jackal robot which is used to fine-tune our model. The dataset, the code, and more visualizations are available at https://lhy.xyz/stereovoxelnet/

Dynamic Hybrid Beamforming Design for Dual-Function Radar-Communication Systems

This paper investigates dynamic hybrid beamforming (HBF) for a dual-function radar-communication (DFRC) system, where the DFRC base station (BS) simultaneously serves multiple single-antenna users and senses a target in the presence of multiple clutters. Particularly, we apply a HBF architecture with dynamic subarrays and double phase shifters in the DFRC BS. Aiming at maximizing the radar mutual information, we consider jointly designing the dynamic HBF of the DFRC system, subject to the constraints of communication quality of service (QoS), transmit power, and analog beamformer. To solve the complicated non-convex optimization, an efficient alternating optimization algorithm based on the majorization-minimization methods is developed. Simulation results verify the advancement of the considered HBF architecture and the effectiveness of the proposed design method.

Deep Reinforcement Learning based Robot Navigation in Dynamic Environments using Occupancy Values of Motion Primitives

This paper presents a Deep Reinforcement Learning based navigation approach in which we define the occupancy observations as heuristic evaluations of motion primitives, rather than using raw sensor data. Our method enables fast mapping of the occupancy data, generated by multi-sensor fusion, into trajectory values in 3D workspace. The computationally efficient trajectory evaluation allows dense sampling of the action space. We utilize our occupancy observations in different data structures to analyze their effects on both training process and navigation performance. We train and test our methodology on two different robots within challenging physics-based simulation environments including static and dynamic obstacles. We benchmark our occupancy representations with other conventional data structures from state-of-the-art methods. The trained navigation policies are also validated successfully with physical robots in dynamic environments. The results show that our method not only decreases the required training time but also improves the navigation performance as compared to other occupancy representations. The open-source implementation of our work and all related info are available at \url{https://github.com/RIVeR-Lab/tentabot}.

Learning to Learn to Predict Performance Regressions in Production at Meta

Catching and attributing code change-induced performance regressions in production is hard; predicting them beforehand, even harder. A primer on automatically learning to predict performance regressions in software, this article gives an account of the experiences we gained when researching and deploying an ML-based regression prediction pipeline at Meta. In this paper, we report on a comparative study with four ML models of increasing complexity, from (1) code-opaque, over (2) Bag of Words, (3) off-the-shelve Transformer-based, to (4) a bespoke Transformer-based model, coined SuperPerforator. Our investigation shows the inherent difficulty of the performance prediction problem, which is characterized by a large imbalance of benign onto regressing changes. Our results also call into question the general applicability of Transformer-based architectures for performance prediction: an off-the-shelve CodeBERT-based approach had surprisingly poor performance; our highly customized SuperPerforator architecture initially achieved prediction performance that was just on par with simpler Bag of Words models, and only outperformed them for down-stream use cases. This ability of SuperPerforator to transfer to an application with few learning examples afforded an opportunity to deploy it in practice at Meta: it can act as a pre-filter to sort out changes that are unlikely to introduce a regression, truncating the space of changes to search a regression in by up to 43%, a 45x improvement over a random baseline. To gain further insight into SuperPerforator, we explored it via a series of experiments computing counterfactual explanations. These highlight which parts of a code change the model deems important, thereby validating the learned black-box model.