Mastering Multi-Drone Volleyball through Hierarchical Co-Self-Play Reinforcement Learning

In this paper, we tackle the problem of learning to play 3v3 multi-drone volleyball, a new embodied competitive task that requires both high-level strategic coordination and low-level agile control. The task is turn-based, multi-agent, and physically grounded, posing significant challenges due to its long-horizon dependencies, tight inter-agent coupling, and the underactuated dynamics of quadrotors. To address this, we propose Hierarchical Co-Self-Play (HCSP), a hierarchical reinforcement learning framework that separates centralized high-level strategic decision-making from decentralized low-level motion control. We design a three-stage population-based training pipeline to enable both strategy and skill to emerge from scratch without expert demonstrations: (I) training diverse low-level skills, (II) learning high-level strategy via self-play with fixed low-level controllers, and (III) joint fine-tuning through co-self-play. Experiments show that HCSP achieves superior performance, outperforming non-hierarchical self-play and rule-based hierarchical baselines with an average 82.9\% win rate and a 71.5\% win rate against the two-stage variant. Moreover, co-self-play leads to emergent team behaviors such as role switching and coordinated formations, demonstrating the effectiveness of our hierarchical design and training scheme.

VTire: A Bimodal Visuotactile Tire with High-Resolution Sensing Capability

Developing smart tires with high sensing capability is significant for improving the moving stability and environmental adaptability of wheeled robots and vehicles. However, due to the classical manufacturing design, it is always challenging for tires to infer external information precisely. To this end, this paper introduces a bimodal sensing tire, which can simultaneously capture tactile and visual data. By leveraging the emerging visuotactile techniques, the proposed smart tire can realize various functions, including terrain recognition, ground crack detection, load sensing, and tire damage detection. Besides, we optimize the material and structure of the tire to ensure its outstanding elasticity, toughness, hardness, and transparency. In terms of algorithms, a transformer-based multimodal classification algorithm, a load detection method based on finite element analysis, and a contact segmentation algorithm have been developed. Furthermore, we construct an intelligent mobile platform to validate the system's effectiveness and develop visual and tactile datasets in complex terrains. The experimental results show that our multimodal terrain sensing algorithm can achieve a classification accuracy of 99.2\%, a tire damage detection accuracy of 97\%, a 98\% success rate in object search, and the ability to withstand tire loading weights exceeding 35 kg. In addition, we open-source our algorithms, hardware, and datasets at https://sites.google.com/view/vtire.

AllTact Fin Ray: A Compliant Robot Gripper with Omni-Directional Tactile Sensing

Tactile sensing plays a crucial role in robot grasping and manipulation by providing essential contact information between the robot and the environment. In this paper, we present AllTact Fin Ray, a novel compliant gripper design with omni-directional and local tactile sensing capabilities. The finger body is unibody-casted using transparent elastic silicone, and a camera positioned at the base of the finger captures the deformation of the whole body and the contact face. Due to the global deformation of the adaptive structure, existing vision-based tactile sensing approaches that assume constant illumination are no longer applicable. To address this, we propose a novel sensing method where the global deformation is first reconstructed from the image using edge features and spatial constraints. Then, detailed contact geometry is computed from the brightness difference against a dynamically retrieved reference image. Extensive experiments validate the effectiveness of our proposed gripper design and sensing method in contact detection, force estimation, object grasping, and precise manipulation.

VET: A Visual-Electronic Tactile System for Immersive Human-Machine Interaction

In the pursuit of deeper immersion in human-machine interaction, achieving higher-dimensional tactile input and output on a single interface has become a key research focus. This study introduces the Visual-Electronic Tactile (VET) System, which builds upon vision-based tactile sensors (VBTS) and integrates electrical stimulation feedback to enable bidirectional tactile communication. We propose and implement a system framework that seamlessly integrates an electrical stimulation film with VBTS using a screen-printing preparation process, eliminating interference from traditional methods. While VBTS captures multi-dimensional input through visuotactile signals, electrical stimulation feedback directly stimulates neural pathways, preventing interference with visuotactile information. The potential of the VET system is demonstrated through experiments on finger electrical stimulation sensitivity zones, as well as applications in interactive gaming and robotic arm teleoperation. This system paves the way for new advancements in bidirectional tactile interaction and its broader applications.

AVR: Active Vision-Driven Robotic Precision Manipulation with Viewpoint and Focal Length Optimization

Robotic manipulation within dynamic environments presents challenges to precise control and adaptability. Traditional fixed-view camera systems face challenges adapting to change viewpoints and scale variations, limiting perception and manipulation precision. To tackle these issues, we propose the Active Vision-driven Robotic (AVR) framework, a teleoperation hardware solution that supports dynamic viewpoint and dynamic focal length adjustments to continuously center targets and maintain optimal scale, accompanied by a corresponding algorithm that effectively enhances the success rates of various operational tasks. Using the RoboTwin platform with a real-time image processing plugin, AVR framework improves task success rates by 5%-16% on five manipulation tasks. Physical deployment on a dual-arm system demonstrates in collaborative tasks and 36% precision in screwdriver insertion, outperforming baselines by over 25%. Experimental results confirm that AVR framework enhances environmental perception, manipulation repeatability (40% $\le $1 cm error), and robustness in complex scenarios, paving the way for future robotic precision manipulation methods in the pursuit of human-level robot dexterity and precision.

Exo-ViHa: A Cross-Platform Exoskeleton System with Visual and Haptic Feedback for Efficient Dexterous Skill Learning

Imitation learning has emerged as a powerful paradigm for robot skills learning. However, traditional data collection systems for dexterous manipulation face challenges, including a lack of balance between acquisition efficiency, consistency, and accuracy. To address these issues, we introduce Exo-ViHa, an innovative 3D-printed exoskeleton system that enables users to collect data from a first-person perspective while providing real-time haptic feedback. This system combines a 3D-printed modular structure with a slam camera, a motion capture glove, and a wrist-mounted camera. Various dexterous hands can be installed at the end, enabling it to simultaneously collect the posture of the end effector, hand movements, and visual data. By leveraging the first-person perspective and direct interaction, the exoskeleton enhances the task realism and haptic feedback, improving the consistency between demonstrations and actual robot deployments. In addition, it has cross-platform compatibility with various robotic arms and dexterous hands. Experiments show that the system can significantly improve the success rate and efficiency of data collection for dexterous manipulation tasks.

PUGS: Zero-shot Physical Understanding with Gaussian Splatting

Current robotic systems can understand the categories and poses of objects well. But understanding physical properties like mass, friction, and hardness, in the wild, remains challenging. We propose a new method that reconstructs 3D objects using the Gaussian splatting representation and predicts various physical properties in a zero-shot manner. We propose two techniques during the reconstruction phase: a geometry-aware regularization loss function to improve the shape quality and a region-aware feature contrastive loss function to promote region affinity. Two other new techniques are designed during inference: a feature-based property propagation module and a volume integration module tailored for the Gaussian representation. Our framework is named as zero-shot physical understanding with Gaussian splatting, or PUGS. PUGS achieves new state-of-the-art results on the standard benchmark of ABO-500 mass prediction. We provide extensive quantitative ablations and qualitative visualization to demonstrate the mechanism of our designs. We show the proposed methodology can help address challenging real-world grasping tasks. Our codes, data, and models are available at https://github.com/EverNorif/PUGS

MoDex: Planning High-Dimensional Dexterous Control via Learning Neural Hand Models

Controlling hands in the high-dimensional action space has been a longstanding challenge, yet humans naturally perform dexterous tasks with ease. In this paper, we draw inspiration from the human embodied cognition and reconsider dexterous hands as learnable systems. Specifically, we introduce MoDex, a framework which employs a neural hand model to capture the dynamical characteristics of hand movements. Based on the model, a bidirectional planning method is developed, which demonstrates efficiency in both training and inference. The method is further integrated with a large language model to generate various gestures such as ``Scissorshand" and ``Rock\&Roll." Moreover, we show that decomposing the system dynamics into a pretrained hand model and an external model improves data efficiency, as supported by both theoretical analysis and empirical experiments. Additional visualization results are available at https://tongwu19.github.io/MoDex.

pFedGPA: Diffusion-based Generative Parameter Aggregation for Personalized Federated Learning

Federated Learning (FL) offers a decentralized approach to model training, where data remains local and only model parameters are shared between the clients and the central server. Traditional methods, such as Federated Averaging (FedAvg), linearly aggregate these parameters which are usually trained on heterogeneous data distributions, potentially overlooking the complex, high-dimensional nature of the parameter space. This can result in degraded performance of the aggregated model. While personalized FL approaches can mitigate the heterogeneous data issue to some extent, the limitation of linear aggregation remains unresolved. To alleviate this issue, we investigate the generative approach of diffusion model and propose a novel generative parameter aggregation framework for personalized FL, \texttt{pFedGPA}. In this framework, we deploy a diffusion model on the server to integrate the diverse parameter distributions and propose a parameter inversion method to efficiently generate a set of personalized parameters for each client. This inversion method transforms the uploaded parameters into a latent code, which is then aggregated through denoising sampling to produce the final personalized parameters. By encoding the dependence of a client's model parameters on the specific data distribution using the high-capacity diffusion model, \texttt{pFedGPA} can effectively decouple the complexity of the overall distribution of all clients' model parameters from the complexity of each individual client's parameter distribution. Our experimental results consistently demonstrate the superior performance of the proposed method across multiple datasets, surpassing baseline approaches.

Depth Restoration of Hand-Held Transparent Objects for Human-to-Robot Handover

Transparent objects are common in daily life, while their unique optical properties pose challenges for RGB-D cameras, which struggle to capture accurate depth information. For assistant robots, accurately perceiving transparent objects held by humans is essential for effective human-robot interaction. This paper presents a Hand-Aware Depth Restoration (HADR) method for hand-held transparent objects based on creating an implicit neural representation function from a single RGB-D image. The proposed method introduces the hand posture as an important guidance to leverage semantic and geometric information. To train and evaluate the proposed method, we create a high-fidelity synthetic dataset called TransHand-14K with a real-to-sim data generation scheme. Experiments show that our method has a better performance and generalization ability compared with existing methods. We further develop a real-world human-to-robot handover system based on the proposed depth restoration method, demonstrating its application value in human-robot interaction.