Monocular outdoor navigation requires robust camera motion estimation and a dense, navigable map, where 3D Gaussian Splatting SLAM serves this task through an explicit differentiable parameterization and closed-form projection. However, typically, the geometry is recovered by associating 2D pixels with 3D points, so a...
Ziang Guo, Didar Seyidov, Yi-Xiao Zhou et al.· 0 citations
Robots sharing walkways need to know where people will be, yet semantic occupancy maps show only where they are. We present ReForesight, an open-source ROS 2 toolkit that adds instance-level future occupancy and re-identification after occlusion to a particle-based semantic mapping pipeline. A 36.6k-parameter MLP predi...
Didar Seyidov, F. Ogunwoye, Hajira Amjad et al.· 0 citations
We present HorizonNav, a video diffusion-based framework for anticipatory robot navigation that transforms a single RGB image and a text prompt into a geometrically aligned representation of plausible surrounding 3D space. Given the initial observation and a textual description of the reconstruction objective, a vision...
Hajira Amjad, Valerii Serpiva, Viacheslav Liubimov et al.· 0 citations
Autonomous multi-drone navigation requires fleets to service distributed objectives in cluttered environments under tight computational budgets. Efficient coordination depends on task bundling, where each drone visits multiple objectives along its route. Separate solvers for cost estimation, assignment, and execution i...
Iana Zhura, S. Akopyan, Roohan Ahmed Khan et al.· 0 citations
World-action models (WAMs) such as Cosmos 3 jointly generate future video and robot actions from an observation and instruction. Adapting one such model with a lightweight LoRA fine-tune to a previously unseen robot, a Unitree G1 humanoid with five-fingered BrainCo hands, exposes a video-action asymmetry: the video ren...
S. Kurchev, Ia M. Kolomiets, Miguel Altamirano Cabrera et al.· 0 citations
Results suggest that contact-guided execution-time adaptation can improve the object-level generalization of a fixed VLA to held-out objects by adapting physical realization without object-specific retraining.
E. Semenyakina, Ivan Snegirev, Mikhail Kiselev et al.· 0 citations
Multi UAV missions in complex environments require the system to understand both the surrounding scene and the intent of a human operator while maintaining feasible task allocation as mission conditions change. This paper presents AgenticSwarm, an agentic framework for semantic perception and adaptive task allocation i...
Muhammad Ahsan Mustafa, Yasheerah Yaqoot, Faryal Batool et al.· 0 citations
CognitiveReality turns a robot's RGB-D stream into a live, semantically indexed Gaussian-TSDF map shared by an operator in virtual reality and a tool-using language agent, and raises object quality by 2-5 dB on robot data.
Timofei Kozlov, Д. А. Малюков, A. Marchenko et al.· arXiv.org· 0 citations
Reliable robotic grasping benefits from estimating the evolving physical interaction and selecting a grasp-dependent compression target. Tactile sensors provide direct interaction measurements but require dedicated hardware at deployment. We introduce ZeroTouch, a tactile-supervised framework that predicts dense contac...
D. Kosenkov, Daniia Zinniatullina, Miguel Altamirano Cabrera et al.· 0 citations
HapticWAM is introduced, a world-action model that combines heterogeneous tactile encoding, structured contact prediction and teacher-student distillation that jointly generates actions and a contact package describing future events and mechanics.
M. Sannikov, I. Mikhalchuk, Konstantin Gubernatorov et al.· 0 citations
AgenticDiffusion is proposed, an agentic multi-view UAV navigation framework that semantically coordinates first-person-view and top-view observations for mission-level navigation that is robust to lexical variation in target descriptions.
Faryal Batool, Muhammad Ahsan Mustafa, Fawad Mehboob et al.· 0 citations
AgenticRL, a multimodal closed loop framework in which role-specialized agents generate executable rewards, diagnose failures of the resulting policies, formulate targeted refinement instructions, and regenerate improved rewards is introduced.
Roohan Ahmed Khan, Yasheerah Yaqoot, A. Habel et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.