Learning Whole-Body Loco-Manipulation for Omni-Directional Task Space Pose Tracking with a Wheeled-Quadrupedal-Manipulator

In this paper, we study the whole-body loco-manipulation problem using reinforcement learning (RL). Specifically, we focus on the problem of how to coordinate the floating base and the robotic arm of a wheeled-quadrupedal manipulator robot to achieve direct six-dimensional (6D) end-effector (EE) pose tracking in task space. Different from conventional whole-body loco-manipulation problems that track both floating-base and end-effector commands, the direct EE pose tracking problem requires inherent balance among redundant degrees of freedom in the whole-body motion. We leverage RL to solve this challenging problem. To address the associated difficulties, we develop a novel reward fusion module (RFM) that systematically integrates reward terms corresponding to different tasks in a nonlinear manner. In such a way, the inherent multi-stage and hierarchical feature of the loco-manipulation problem can be carefully accommodated. By combining the proposed RFM with the a teacher-student RL training paradigm, we present a complete RL scheme to achieve 6D EE pose tracking for the wheeled-quadruped manipulator robot. Extensive simulation and hardware experiments demonstrate the significance of the RFM. In particular, we enable smooth and precise tracking performance, achieving state-of-the-art tracking position error of less than 5 cm, and rotation error of less than 0.1 rad. Please refer to https://clearlab-sustech.github.io/RFM_loco_mani/ for more experimental videos.

CktGen: Specification-Conditioned Analog Circuit Generation

Automatic synthesis of analog circuits presents significant challenges. Existing methods usually treat the task as optimization problems, which limits their transferability and reusability for new requirements. To address this limitation, we introduce a task that directly generates analog circuits based on specified specifications, termed specification-conditioned analog circuit generation. Specifically, we propose CktGen, a simple yet effective variational autoencoder (VAE) model, that maps specifications and circuits into a joint latent space, and reconstructs the circuit from the latent. Moreover, given that a single specification can correspond to multiple distinct circuits, simply minimizing the distance between the mapped latent representations of the circuit and specification does not capture these one-to-many relationships. To address this, we integrate contrastive learning and classifier guidance to prevent model collapse. We conduct comprehensive experiments on the Open Circuit Benchmark (OCB) and introduce new evaluation metrics for cross-model consistency in the specification-to-circuit generation task. Experimental results demonstrate substantial improvements over existing state-of-the-art methods.

Valuing an Engagement Surface using a Large Scale Dynamic Causal Model

With recent rapid growth in online shopping, AI-powered Engagement Surfaces (ES) have become ubiquitous across retail services. These engagement surfaces perform an increasing range of functions, including recommending new products for purchase, reminding customers of their orders and providing delivery notifications. Understanding the causal effect of engagement surfaces on value driven for customers and businesses remains an open scientific question. In this paper, we develop a dynamic causal model at scale to disentangle value attributable to an ES, and to assess its effectiveness. We demonstrate the application of this model to inform business decision-making by understanding returns on investment in the ES, and identifying product lines and features where the ES adds the most value.

Extremely Large-Scale Dynamic Metasurface Antennas (XL-DMAs): Near-Field Modeling and Channel Estimation

Dynamic metasurface antennas (DMAs) represent a novel transceiver array architecture for extremely large-scale (XL) communications, offering the advantages of reduced power consumption and lower hardware costs compared to conventional arrays. This paper focuses on near-field channel estimation for XL-DMAs. We begin by analyzing the near-field characteristics of uniform planar arrays (UPAs) and introducing the Oblong Approx. model. This model decouples elevation-azimuth (EL-AZ) parameters for XL-DMAs, providing an effective means to characterize the near-field effect. It offers simpler mathematical expressions than the second-order Taylor expansion model, all while maintaining negligible model errors for oblong-shaped arrays. Building on the Oblong Approx. model, we propose an EL-AZ-decoupled estimation framework that involves near- and far-field parameter estimation for AZ/EL and EL/AZ directions, respectively. The former is formulated as a distributed compressive sensing problem, addressed using the proposed off-grid distributed orthogonal least squares algorithm, while the latter involves a straightforward parallelizable search. Crucially, we illustrate the viability of decoupled EL-AZ estimation for near-field UPAs, exhibiting commendable performance and linear complexity correlated with the number of metasurface elements. Moreover, we design an measurement matrix optimization method with the Lorentzian constraint on DMAs and highlight the estimation performance degradation resulting from this constraint.

Combining Teacher-Student with Representation Learning: A Concurrent Teacher-Student Reinforcement Learning Paradigm for Legged Locomotion

Thanks to the explosive developments of data-driven learning methodologies recently, reinforcement learning (RL) emerges as a promising solution to address the legged locomotion problem in robotics. In this manuscript, we propose a novel concurrent teacher-student reinforcement learning architecture for legged locomotion over challenging terrains, based only on proprioceptive measurements in real-world deployment. Different from convectional teacher-student architecture that trains the teacher policy via RL and transfers the knowledge to the student policy through supervised learning, our proposed architecture trains teacher and student policy networks concurrently under the reinforcement learning paradigm. To achieve this, we develop a new training scheme based on conventional proximal policy gradient (PPO) method to accommodate the interaction between teacher policy network and student policy network. The effectiveness of the proposed architecture as well as the new training scheme is demonstrated through extensive indoor and outdoor experiments on quadrupedal robots and point-foot bipedal robot, showcasing robust locomotion over challenging terrains and improved performance compared to two-stage training methods.

GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement

Object pose refinement is essential for robust object pose estimation. Previous work has made significant progress towards instance-level object pose refinement. Yet, category-level pose refinement is a more challenging problem due to large shape variations within a category and the discrepancies between the target object and the shape prior. To address these challenges, we introduce a novel architecture for category-level object pose refinement. Our approach integrates an HS-layer and learnable affine transformations, which aims to enhance the extraction and alignment of geometric information. Additionally, we introduce a cross-cloud transformation mechanism that efficiently merges diverse data sources. Finally, we push the limits of our model by incorporating the shape prior information for translation and size error prediction. We conducted extensive experiments to demonstrate the effectiveness of the proposed framework. Through extensive quantitative experiments, we demonstrate significant improvement over the baseline method by a large margin across all metrics.

POMDP-Guided Active Force-Based Search for Robotic Insertion

In robotic insertion tasks where the uncertainty exceeds the allowable tolerance, a good search strategy is essential for successful insertion and significantly influences efficiency. The commonly used blind search method is time-consuming and does not exploit the rich contact information. In this paper, we propose a novel search strategy that actively utilizes the information contained in the contact configuration and shows high efficiency. In particular, we formulate this problem as a Partially Observable Markov Decision Process (POMDP) with carefully designed primitives based on an in-depth analysis of the contact configuration's static stability. From the formulated POMDP, we can derive a novel search strategy. Thanks to its simplicity, this search strategy can be incorporated into a Finite-State-Machine (FSM) controller. The behaviors of the FSM controller are realized through a low-level Cartesian Impedance Controller. Our method is based purely on the robot's proprioceptive sensing and does not need visual or tactile sensors. To evaluate the effectiveness of our proposed strategy and control framework, we conduct extensive comparison experiments in simulation, where we compare our method with the baseline approach. The results demonstrate that our proposed method achieves a higher success rate with a shorter search time and search trajectory length compared to the baseline method. Additionally, we show that our method is robust to various initial displacement errors.

Task-Space Riccati Feedback based Whole Body Control for Underactuated Legged Locomotion

This manuscript primarily aims to enhance the performance of whole-body controllers(WBC) for underactuated legged locomotion. We introduce a systematic parameter design mechanism for the floating-base feedback control within the WBC. The proposed approach involves utilizing the linearized model of unactuated dynamics to formulate a Linear Quadratic Regulator(LQR) and solving a Riccati gain while accounting for potential physical constraints through a second-order approximation of the log-barrier function. And then the user-tuned feedback gain for the floating base task is replaced by a new one constructed from the solved Riccati gain. Extensive simulations conducted in MuJoCo with a point bipedal robot, as well as real-world experiments performed on a quadruped robot, demonstrate the effectiveness of the proposed method. In the different bipedal locomotion tasks, compared with the user-tuned method, the proposed approach is at least 12% better and up to 50% better at linear velocity tracking, and at least 7% better and up to 47% better at angular velocity tracking. In the quadruped experiment, linear velocity tracking is improved by at least 3% and angular velocity tracking is improved by at least 23% using the proposed method.

RSTAR: Rotational Streak Artifact Reduction in 4D CBCT using Separable and Circular Convolutions

Four-dimensional cone-beam computed tomography (4D CBCT) provides respiration-resolved images and can be used for image-guided radiation therapy. However, the ability to reveal respiratory motion comes at the cost of image artifacts. As raw projection data are sorted into multiple respiratory phases, there is a limited number of cone-beam projections available for image reconstruction. Consequently, the 4D CBCT images are covered by severe streak artifacts. Although several deep learning-based methods have been proposed to address this issue, most algorithms employ ordinary network models, neglecting the intrinsic structural prior within 4D CBCT images. In this paper, we first explore the origin and appearance of streak artifacts in 4D CBCT images.Specifically, we find that streak artifacts exhibit a periodic rotational motion along with the patient's respiration. This unique motion pattern inspires us to distinguish the artifacts from the desired anatomical structures in the spatiotemporal domain. Thereafter, we propose a spatiotemporal neural network named RSTAR-Net with separable and circular convolutions for Rotational Streak Artifact Reduction. The specially designed model effectively encodes dynamic image features, facilitating the recovery of 4D CBCT images. Moreover, RSTAR-Net is also lightweight and computationally efficient. Extensive experiments substantiate the effectiveness of our proposed method, and RSTAR-Net shows superior performance to comparison methods.

RIS-Enabled Joint Near-Field 3D Localization and Synchronization in SISO Multipath Environments

Reconfigurable Intelligent Surfaces (RIS) show great promise in the realm of 6th generation (6G) wireless systems, particularly in the areas of localization and communication. Their cost-effectiveness and energy efficiency enable the integration of numerous passive and reflective elements, enabling near-field propagation. In this paper, we tackle the challenges of RIS-aided 3D localization and synchronization in multipath environments, focusing on the near-field of mmWave systems. Specifically, our approach involves formulating a maximum likelihood (ML) estimation problem for the channel parameters. To initiate this process, we leverage a combination of canonical polyadic decomposition (CPD) and orthogonal matching pursuit (OMP) to obtain coarse estimates of the time of arrival (ToA) and angle of departure (AoD) under the far-field approximation. Subsequently, distances are estimated using $l_{1}$-regularization based on a near-field model. Additionally, we introduce a refinement phase employing the spatial alternating generalized expectation maximization (SAGE) algorithm. Finally, a weighted least squares approach is applied to convert channel parameters into position and clock offset estimates. To extend the estimation algorithm to ultra-large (UL) RIS-assisted localization scenarios, it is further enhanced to reduce errors associated with far-field approximations, especially in the presence of significant near-field effects, achieved by narrowing the RIS aperture. Moreover, the Cram\'er-Rao Bound (CRB) is derived and the RIS phase shifts are optimized to improve the positioning accuracy. Numerical results affirm the efficacy of the proposed estimation algorithm.