Low-Altitude UAV Tracking via Sensing-Assisted Predictive Beamforming

Sensing-assisted predictive beamforming, as one of the enabling technologies for emerging integrated sensing and communication (ISAC) paradigm, shows significant promise for enhancing various future unmanned aerial vehicle (UAV) applications. However, current works predominately emphasized on spectral efficiency enhancement, while the impact of such beamforming techniques on the communication reliability was largely unexplored and challenging to characterize. To fill this research gap and tackle this issue, this paper investigates outage capacity maximization for UAV tracking under the sensing-assisted predictive beamforming scheme. Specifically, a cellular-connected UAV tracking scheme is proposed leveraging extended Kalman filtering (EKF), where the predicted UAV trajectory, sensing duration ratio, and target constant received signal-to-noise ratio (SNR) are jointly optimized to maximize the outage capacity at each time slot. To address the implicit nature of the objective function, closed-form approximations of the outage probabilities (OPs) at both prediction and measurement stages of each time slot are proposed based on second-order Taylor expansions, providing an efficient and full characterization of outage capacity. Subsequently, an efficient algorithm is proposed based on a combination of bisection search and successive convex approximation (SCA) to address the non-convex optimization problem with guaranteed convergence. To further reduce computational complexity, a second efficient algorithm is developed based on alternating optimization (AO). Simulation results validate the accuracy of the derived OP approximations, the effectiveness of the proposed algorithms, and the significant outage capacity enhancement over various benchmarks, while also indicating a trade-off between decreasing path loss and enjoying wide beam coverage for outage capacity maximization.

ActiveVLN: Towards Active Exploration via Multi-Turn RL in Vision-and-Language Navigation

The Vision-and-Language Navigation (VLN) task requires an agent to follow natural language instructions and navigate through complex environments. Existing MLLM-based VLN methods primarily rely on imitation learning (IL) and often use DAgger for post-training to mitigate covariate shift. While effective, these approaches incur substantial data collection and training costs. Reinforcement learning (RL) offers a promising alternative. However, prior VLN RL methods lack dynamic interaction with the environment and depend on expert trajectories for reward shaping, rather than engaging in open-ended active exploration. This restricts the agent's ability to discover diverse and plausible navigation routes. To address these limitations, we propose ActiveVLN, a VLN framework that explicitly enables active exploration through multi-turn RL. In the first stage, a small fraction of expert trajectories is used for IL to bootstrap the agent. In the second stage, the agent iteratively predicts and executes actions, automatically collects diverse trajectories, and optimizes multiple rollouts via the GRPO objective. To further improve RL efficiency, we introduce a dynamic early-stopping strategy to prune long-tail or likely failed trajectories, along with additional engineering optimizations. Experiments show that ActiveVLN achieves the largest performance gains over IL baselines compared to both DAgger-based and prior RL-based post-training methods, while reaching competitive performance with state-of-the-art approaches despite using a smaller model. Code and data will be released soon.

Empowering Multi-Robot Cooperation via Sequential World Models

Model-based reinforcement learning (MBRL) has shown significant potential in robotics due to its high sample efficiency and planning capability. However, extending MBRL to multi-robot cooperation remains challenging due to the complexity of joint dynamics. To address this, we propose the Sequential World Model (SeqWM), a novel framework that integrates the sequential paradigm into model-based multi-agent reinforcement learning. SeqWM employs independent, sequentially structured agent-wise world models to decompose complex joint dynamics. Latent rollouts and decision-making are performed through sequential communication, where each agent generates its future trajectory and plans its actions based on the predictions of its predecessors. This design enables explicit intention sharing, enhancing cooperative performance, and reduces communication overhead to linear complexity. Results in challenging simulated environments (Bi-DexHands and Multi-Quad) show that SeqWM outperforms existing state-of-the-art model-free and model-based baselines in both overall performance and sample efficiency, while exhibiting advanced cooperative behaviors such as predictive adaptation and role division. Furthermore, SeqWM has been success fully deployed on physical quadruped robots, demonstrating its effectiveness in real-world multi-robot systems. Demos and code are available at: https://github.com/zhaozijie2022/seqwm-marl

Accelerating Protein Molecular Dynamics Simulation with DeepJump

Unraveling the dynamical motions of biomolecules is essential for bridging their structure and function, yet it remains a major computational challenge. Molecular dynamics (MD) simulation provides a detailed depiction of biomolecular motion, but its high-resolution temporal evolution comes at significant computational cost, limiting its applicability to timescales of biological relevance. Deep learning approaches have emerged as promising solutions to overcome these computational limitations by learning to predict long-timescale dynamics. However, generalizable kinetics models for proteins remain largely unexplored, and the fundamental limits of achievable acceleration while preserving dynamical accuracy are poorly understood. In this work, we fill this gap with DeepJump, an Euclidean-Equivariant Flow Matching-based model for predicting protein conformational dynamics across multiple temporal scales. We train DeepJump on trajectories of the diverse proteins of mdCATH, systematically studying our model's performance in generalizing to long-term dynamics of fast-folding proteins and characterizing the trade-off between computational acceleration and prediction accuracy. We demonstrate the application of DeepJump to ab initio folding, showcasing prediction of folding pathways and native states. Our results demonstrate that DeepJump achieves significant $\approx$1000$\times$ computational acceleration while effectively recovering long-timescale dynamics, providing a stepping stone for enabling routine simulation of proteins.

Model Predictive Control with Reference Learning for Soft Robotic Intracranial Pressure Waveform Modulation

This paper introduces a learning-based control framework for a soft robotic actuator system designed to modulate intracranial pressure (ICP) waveforms, which is essential for studying cerebrospinal fluid dynamics and pathological processes underlying neurological disorders. A two-layer framework is proposed to safely achieve a desired ICP waveform modulation. First, a model predictive controller (MPC) with a disturbance observer is used for offset-free tracking of the system's motor position reference trajectory under safety constraints. Second, to address the unknown nonlinear dependence of ICP on the motor position, we employ a Bayesian optimization (BO) algorithm used for online learning of a motor position reference trajectory that yields the desired ICP modulation. The framework is experimentally validated using a test bench with a brain phantom that replicates realistic ICP dynamics in vitro. Compared to a previously employed proportional-integral-derivative controller, the MPC reduces mean and maximum motor position reference tracking errors by 83 % and 73 %, respectively. In less than 20 iterations, the BO algorithm learns a motor position reference trajectory that yields an ICP waveform with the desired mean and amplitude.

Safety Critical Model Predictive Control Using Discrete-Time Control Density Functions

This paper presents MPC-CDF, a new approach integrating control density functions (CDFs) within a model predictive control (MPC) framework to ensure safety-critical control in nonlinear dynamical systems. By using the dual formulation of the navigation problem, we incorporate CDFs into the MPC framework, ensuring both convergence and safety in a discrete-time setting. These density functions are endowed with a physical interpretation, where the associated measure signifies the occupancy of system trajectories. Leveraging this occupancy-based perspective, we synthesize safety-critical controllers using the proposed MPC-CDF framework. We illustrate the safety properties of this framework using a unicycle model and compare it with a control barrier function-based method. The efficacy of this approach is demonstrated in the autonomous safe navigation of an underwater vehicle, which avoids complex and arbitrary obstacles while achieving the desired level of safety.

Out of Distribution Detection in Self-adaptive Robots with AI-powered Digital Twins

Self-adaptive robots (SARs) in complex, uncertain environments must proactively detect and address abnormal behaviors, including out-of-distribution (OOD) cases. To this end, digital twins offer a valuable solution for OOD detection. Thus, we present a digital twin-based approach for OOD detection (ODiSAR) in SARs. ODiSAR uses a Transformer-based digital twin to forecast SAR states and employs reconstruction error and Monte Carlo dropout for uncertainty quantification. By combining reconstruction error with predictive variance, the digital twin effectively detects OOD behaviors, even in previously unseen conditions. The digital twin also includes an explainability layer that links potential OOD to specific SAR states, offering insights for self-adaptation. We evaluated ODiSAR by creating digital twins of two industrial robots: one navigating an office environment, and another performing maritime ship navigation. In both cases, ODiSAR forecasts SAR behaviors (i.e., robot trajectories and vessel motion) and proactively detects OOD events. Our results showed that ODiSAR achieved high detection performance -- up to 98\% AUROC, 96\% TNR@TPR95, and 95\% F1-score -- while providing interpretable insights to support self-adaptation.

DYNAMO: Dependency-Aware Deep Learning Framework for Articulated Assembly Motion Prediction

Understanding the motion of articulated mechanical assemblies from static geometry remains a core challenge in 3D perception and design automation. Prior work on everyday articulated objects such as doors and laptops typically assumes simplified kinematic structures or relies on joint annotations. However, in mechanical assemblies like gears, motion arises from geometric coupling, through meshing teeth or aligned axes, making it difficult for existing methods to reason about relational motion from geometry alone. To address this gap, we introduce MechBench, a benchmark dataset of 693 diverse synthetic gear assemblies with part-wise ground-truth motion trajectories. MechBench provides a structured setting to study coupled motion, where part dynamics are induced by contact and transmission rather than predefined joints. Building on this, we propose DYNAMO, a dependency-aware neural model that predicts per-part SE(3) motion trajectories directly from segmented CAD point clouds. Experiments show that DYNAMO outperforms strong baselines, achieving accurate and temporally consistent predictions across varied gear configurations. Together, MechBench and DYNAMO establish a novel systematic framework for data-driven learning of coupled mechanical motion in CAD assemblies.

MGTraj: Multi-Granularity Goal-Guided Human Trajectory Prediction with Recursive Refinement Network

Accurate human trajectory prediction is crucial for robotics navigation and autonomous driving. Recent research has demonstrated that incorporating goal guidance significantly enhances prediction accuracy by reducing uncertainty and leveraging prior knowledge. Most goal-guided approaches decouple the prediction task into two stages: goal prediction and subsequent trajectory completion based on the predicted goal, which operate at extreme granularities: coarse-grained goal prediction forecasts the overall intention, while fine-grained trajectory completion needs to generate the positions for all future timesteps. The potential utility of intermediate temporal granularity remains largely unexplored, which motivates multi-granularity trajectory modeling. While prior work has shown that multi-granularity representations capture diverse scales of human dynamics and motion patterns, effectively integrating this concept into goal-guided frameworks remains challenging. In this paper, we propose MGTraj, a novel Multi-Granularity goal-guided model for human Trajectory prediction. MGTraj recursively encodes trajectory proposals from coarse to fine granularity levels. At each level, a transformer-based recursive refinement network (RRN) captures features and predicts progressive refinements. Features across different granularities are integrated using a weight-sharing strategy, and velocity prediction is employed as an auxiliary task to further enhance performance. Comprehensive experimental results in EHT/UCY and Stanford Drone Dataset indicate that MGTraj outperforms baseline methods and achieves state-of-the-art performance among goal-guided methods.

\emph{FoQuS}: A Forgetting-Quality Coreset Selection Framework for Automatic Modulation Recognition

Deep learning-based Automatic Modulation Recognition (AMR) model has made significant progress with the support of large-scale labeled data. However, when developing new models or performing hyperparameter tuning, the time and energy consumption associated with repeated training using massive amounts of data are often unbearable. To address the above challenges, we propose \emph{FoQuS}, which approximates the effect of full training by selecting a coreset from the original dataset, thereby significantly reducing training overhead. Specifically, \emph{FoQuS} records the prediction trajectory of each sample during full-dataset training and constructs three importance metrics based on training dynamics. Experiments show that \emph{FoQuS} can maintain high recognition accuracy and good cross-architecture generalization on multiple AMR datasets using only 1\%-30\% of the original data.