Kohei Kumazaki

Terrain-Attentive Learning for Efficient 6-DoF Kinodynamic Modeling on Vertically Challenging Terrain https://ift.tt/3HuG4KL arXiv:2403.16419v1 Announce Type: new Abstract: Wheeled robots have recently demonstrated superior mechanical capability to traverse vertically challenging terrain...

Augmented Reality based Simulated Data (ARSim) with multi-view consistency for AV perception networks https://ift.tt/rptmZ5G arXiv:2403.15370v1 Announce Type: cross Abstract: Detecting a diverse range of objects under various driving scenarios is...

Learning Hierarchical Control For Constrained Dynamic Task Assignment https://ift.tt/hiZGeyj arXiv:2403.14545v1 Announce Type: new Abstract: This paper introduces a novel data-driven hierarchical control scheme for managing a fleet of nonlinear, capacity-constrained...

Automatic Navigation Map Generation for Mobile Robots in Urban Environments https://ift.tt/Bx1DmPj arXiv:2403.13431v1 Announce Type: new Abstract: A fundamental prerequisite for safe and efficient navigation of mobile robots is the availability...

Shared Autonomy via Variable Impedance Control and Virtual Potential Fields for Encoding Human Demonstration https://ift.tt/SipcXwl arXiv:2403.12720v1 Announce Type: new Abstract: This article introduces a framework for complex human-robot collaboration tasks,...

Automatic Spatial Calibration of Near-Field MIMO Radar With Respect to Optical Sensors https://ift.tt/wj58Zxq arXiv:2403.10981v1 Announce Type: new Abstract: Despite an emerging interest in MIMO radar, the utilization of its complementary...

H-MaP: An Iterative and Hybrid Sequential Manipulation Planner https://ift.tt/1MdKylo arXiv:2403.10436v1 Announce Type: new Abstract: This study introduces the Hybrid Sequential Manipulation Planner (H-MaP), a novel approach that iteratively does motion...

3D-VLA: A 3D Vision-Language-Action Generative World Model https://ift.tt/ld7Y5oW arXiv:2403.09631v1 Announce Type: cross Abstract: Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D...

Analytical Forward Dynamics Modeling of Linearly Actuated Heavy-Duty Parallel-Serial Manipulators https://ift.tt/JXLCQTd arXiv:2403.08524v1 Announce Type: new Abstract: This paper presents a new geometric and recursive algorithm for analytically computing the forward...

Online Continual Learning For Interactive Instruction Following Agents https://ift.tt/s08ZgrH arXiv:2403.07548v1 Announce Type: cross Abstract: In learning an embodied agent executing daily tasks via language directives, the literature largely assumes that...