864 papers
This paper proposes TPK, a trustworthy trajectory prediction framework that integrates class-specific interaction and kinematic priors to ensure physically feasible and interpretable predictions for mixed traffic agents, demonstrating improved reliability over state-of-the-art baselines on the Argoverse 2 dataset despite a minor trade-off in raw accuracy.
This paper proposes "Feature Mixing," an extremely simple and fast modality-agnostic method for multimodal outlier synthesis that achieves state-of-the-art performance in out-of-distribution detection and segmentation while offering significant speedups, alongside the introduction of a new multimodal dataset called CARLA-OOD.
This paper introduces pyCub, an open-source, Python-based simulation framework for the iCub humanoid robot that eliminates the need for C++ and YARP middleware while providing scalable exercises to teach robotics fundamentals to students with varying programming skills.
This paper proposes Q-SVMPC, a novel framework that integrates Q-guided Stein variational inference with an RL-informed policy prior to enable diverse, robust, and sample-efficient trajectory optimization in Model Predictive Control, overcoming the mode collapse limitations of existing learning-based MPC methods.
VITA is a novel, noise-free, and conditioning-free flow matching framework that accelerates inference by directly mapping visual representations to structured latent actions via a jointly trained autoencoder and flow latent decoding, achieving state-of-the-art performance on diverse robotic tasks.
Point2Act is an efficient framework that leverages Multimodal Large Language Models to distill 2D semantic understanding into precise 3D action points, enabling zero-shot, context-aware robotic grasping in unseen environments within under 20 seconds.
This paper presents a vision-free robotic grasping method that utilizes whole-body sensitive skin for rapid coarse exploration followed by precise end-effector localization, achieving an 85.7% success rate and operating six times faster than end-effector-only baselines in challenging visual environments.
This paper presents a novel, efficient, and robust geometric method based on projective geometric algebra that reformulates rigid body dynamics into a "tetrahedral-point" model to analytically derive and automatically identify the complete set of base inertial parameters for diverse robotic systems, including complex parallel kinematics mechanisms.
To address the challenges of inconsistent dependencies and data formats hindering fair comparisons in the rapidly growing field of event-based localization, the authors present Event-LAB, a unified framework built on the Pixi package manager that streamlines the implementation, evaluation, and analysis of multiple localization methods across diverse datasets.
This paper addresses the unexplored challenge of label noise in action-based video object segmentation by introducing the ActiSeg-NL benchmark, analyzing the impact of textual and mask annotation noise, and proposing a Parallel Mask Head Mechanism to enhance robustness for embodied intelligence applications.
This paper introduces PRoP, a model-agnostic framework that enables robots to personalize their policies for individual users while preserving privacy by using unique cryptographic keys to mathematically transform network weights, ensuring that only authorized users can access their specific behavioral adaptations.
This paper presents a fast local solver for category-level object shape and pose estimation that leverages learned semantic keypoints and active shape models to achieve global optimality certification in under a millisecond via an efficient self-consistent field iteration.
RehearseVLA is an RL-based post-training framework that leverages a physically-consistent world simulator and a VLM-guided reflector to enable safe, data-efficient fine-tuning of Vision-Language-Action models in data-scarce and high-risk environments, achieving significant performance gains with minimal expert demonstrations.
The paper proposes ELMUR, a transformer architecture equipped with structured external memory that enables robotic agents to effectively handle long-horizon, partially observable tasks by significantly extending effective horizons and outperforming existing baselines on synthetic and real-world manipulation benchmarks.
TIGeR is a novel framework that enhances Vision-Language Models for robotics by integrating external computational tools to perform precise geometric calculations, supported by a new dataset and a two-stage training pipeline, thereby achieving centimeter-level accuracy in real-world manipulation tasks.
LaViRA is a zero-shot framework for Vision-and-Language Navigation in Continuous Environments that decomposes navigation into a coarse-to-fine hierarchy of language, vision, and robot actions, leveraging Multimodal Large Language Models to achieve superior generalization and performance without prior training.
SoraNav is a novel framework that enables zero-shot Vision-Language Model reasoning for UAV task-centric navigation by integrating Multi-modal Visual Annotation to encode 3D geometric priors and an Adaptive Decision Making strategy to validate commands, thereby significantly outperforming existing methods in both 2.5D and complex 3D environments.
This paper introduces Dynamic-ICP, a real-time, Doppler-aware registration framework for FMCW LiDAR that robustly estimates ego-motion and aligns scans in highly dynamic environments by integrating point-to-plane geometry with rotation-only Doppler residuals, eliminating the need for external sensors or calibration.
This paper presents a metric, inertially aligned monocular state estimation framework for flexible robotic systems that integrates MLP-learned deformation-force models with continuous-time B-spline kinematics to leverage kinetodynamic priors for robust pose estimation and the recovery of inertial sensing properties like metric scale and gravity.
This paper introduces CERNet, a unified hierarchical predictive-coding recurrent neural network that integrates real-time robot motion generation, online intent recognition, and intrinsic confidence estimation into a single compact framework, demonstrating superior trajectory reproduction and recognition accuracy on a humanoid robot.