RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation

Robots need to explore their surroundings to adapt to and tackle tasks in unknown environments. Prior work has proposed building scene graphs of the environment but typically assumes that the environment is static, omitting regions that require active interactions. This severely limits their ability to handle more complex tasks in household and office environments: before setting up a table, robots must explore drawers and cabinets to locate all utensils and condiments. In this work, we introduce the novel task of interactive scene exploration, wherein robots autonomously explore environments and produce an action-conditioned scene graph (ACSG) that captures the structure of the underlying environment. The ACSG accounts for both low-level information, such as geometry and semantics, and high-level information, such as the action-conditioned relationships between different entities in the scene. To this end, we present the Robotic Exploration (RoboEXP) system, which incorporates the Large Multimodal Model (LMM) and an explicit memory design to enhance our system's capabilities. The robot reasons about what and how to explore an object, accumulating new information through the interaction process and incrementally constructing the ACSG. We apply our system across various real-world settings in a zero-shot manner, demonstrating its effectiveness in exploring and modeling environments it has never seen before. Leveraging the constructed ACSG, we illustrate the effectiveness and efficiency of our RoboEXP system in facilitating a wide range of real-world manipulation tasks involving rigid, articulated objects, nested objects like Matryoshka dolls, and deformable objects like cloth.

D$^3$Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Robotic Manipulation

Scene representation has been a crucial design choice in robotic manipulation systems. An ideal representation should be 3D, dynamic, and semantic to meet the demands of diverse manipulation tasks. However, previous works often lack all three properties simultaneously. In this work, we introduce D$^3$Fields - dynamic 3D descriptor fields. These fields capture the dynamics of the underlying 3D environment and encode both semantic features and instance masks. Specifically, we project arbitrary 3D points in the workspace onto multi-view 2D visual observations and interpolate features derived from foundational models. The resulting fused descriptor fields allow for flexible goal specifications using 2D images with varied contexts, styles, and instances. To evaluate the effectiveness of these descriptor fields, we apply our representation to a wide range of robotic manipulation tasks in a zero-shot manner. Through extensive evaluation in both real-world scenarios and simulations, we demonstrate that D$^3$Fields are both generalizable and effective for zero-shot robotic manipulation tasks. In quantitative comparisons with state-of-the-art dense descriptors, such as Dense Object Nets and DINO, D$^3$Fields exhibit significantly better generalization abilities and manipulation accuracy.

Sensing User's Activity, Channel, and Location with Near-Field Extra-Large-Scale MIMO

This paper proposes a grant-free massive access scheme based on the millimeter wave (mmWave) extra-large-scale multiple-input multiple-output (XL-MIMO) to support massive Internet-of-Things (IoT) devices with low latency, high data rate, and high localization accuracy in the upcoming sixth-generation (6G) networks. The XL-MIMO consists of multiple antenna subarrays that are widely spaced over the service area to ensure line-of-sight (LoS) transmissions. First, we establish the XL-MIMO-based massive access model considering the near-field spatial non-stationary (SNS) property. Then, by exploiting the block sparsity of subarrays and the SNS property, we propose a structured block orthogonal matching pursuit algorithm for efficient active user detection (AUD) and channel estimation (CE). Furthermore, different sensing matrices are applied in different pilot subcarriers for exploiting the diversity gains. Additionally, a multi-subarray collaborative localization algorithm is designed for localization. In particular, the angle of arrival (AoA) and time difference of arrival (TDoA) of the LoS links between active users and related subarrays are extracted from the estimated XL-MIMO channels, and then the coordinates of active users are acquired by jointly utilizing the AoAs and TDoAs. Simulation results show that the proposed algorithms outperform existing algorithms in terms of AUD and CE performance and can achieve centimeter-level localization accuracy.

Beyond Conservatism: Diffusion Policies in Offline Multi-agent Reinforcement Learning

We present a novel Diffusion Offline Multi-agent Model (DOM2) for offline Multi-Agent Reinforcement Learning (MARL). Different from existing algorithms that rely mainly on conservatism in policy design, DOM2 enhances policy expressiveness and diversity based on diffusion. Specifically, we incorporate a diffusion model into the policy network and propose a trajectory-based data-augmentation scheme in training. These key ingredients make our algorithm more robust to environment changes and achieve significant improvements in performance, generalization and data-efficiency. Our extensive experimental results demonstrate that DOM2 outperforms existing state-of-the-art methods in multi-agent particle and multi-agent MuJoCo environments, and generalizes significantly better in shifted environments thanks to its high expressiveness and diversity. Furthermore, DOM2 shows superior data efficiency and can achieve state-of-the-art performance with $20+$ times less data compared to existing algorithms.

Sensing User's Channel and Location with Terahertz Extra-Large Reconfigurable Intelligent Surface under Hybrid-Field Beam Squint Effect

This paper investigates the sensing of user's uplink channel and location in terahertz extra-large reconfigurable intelligent surface (XL-RIS) systems, where the unique hybrid far-near field effect and the beam squint effect caused by the XL array aperture as well as the XL bandwidth are overcome. Specifically, we first propose a joint channel and location sensing scheme, which consists of a location-assisted generalized multiple measurement vector orthogonal matching pursuit (LA-GMMV-OMP) algorithm for channel estimation (CE) and a complete dictionary based localization (CDL) scheme, where a frequency selective polar-domain redundant dictionary is proposed to overcome the hybrid field beam squint effect. The CE module outputs coarse on-grid angle estimation (respectively observed from the BS and RIS) to the localization module, which returns the fine off-grid angle estimation to improve CE. Particularly, with RIS, CDL can obtain user's location via line intersection, and a polar-domain gradient descent (PGD) algorithm at the base station is proposed to achieve the off-grid angle estimation with super-resolution accuracy. Additionally, to further reduce the sensing overhead, we propose a partial dictionary-based localization scheme, which is decoupled from CE, where RIS is served as an anchor to lock the user on the hyperbola according to time difference of arrival and the user's off-grid location can be obtained by using the proposed PGD algorithm. Simulation results demonstrate the superiority of the two proposed localization schemes and the proposed CE scheme over state-of-the-art baseline approaches.

Network Topology Optimization via Deep Reinforcement Learning

Topology impacts important network performance metrics, including link utilization, throughput and latency, and is of central importance to network operators. However, due to the combinatorial nature of network topology, it is extremely difficult to obtain an optimal solution, especially since topology planning in networks also often comes with management-specific constraints. As a result, local optimization with hand-tuned heuristic methods from human experts are often adopted in practice. Yet, heuristic methods cannot cover the global topology design space while taking into account constraints, and cannot guarantee to find good solutions. In this paper, we propose a novel deep reinforcement learning (DRL) algorithm, called Advantage Actor Critic-Graph Searching (A2C-GS), for network topology optimization. A2C-GS consists of three novel components, including a verifier to validate the correctness of a generated network topology, a graph neural network (GNN) to efficiently approximate topology rating, and a DRL actor layer to conduct a topology search. A2C-GS can efficiently search over large topology space and output topology with satisfying performance. We conduct a case study based on a real network scenario, and our experimental results demonstrate the superior performance of A2C-GS in terms of both efficiency and performance.