Kohei Kumazaki

Results 106 issues of Kohei Kumazaki

Differentiable Boustrophedon Paths That Enable Optimization Via Gradient Descent https://ift.tt/52J7gvt arXiv:2309.09882v2 Announce Type: replace Abstract: This paper introduces a differentiable representation for the optimization of boustrophedon path plans in convex...

GNSS/Multi-Sensor Fusion Using Continuous-Time Factor Graph Optimization for Robust Localization https://ift.tt/2JPF40s arXiv:2309.11134v2 Announce Type: replace Abstract: Accurate and robust vehicle localization in highly urbanized areas is challenging. Sensors are often...

Vision-Language Interpreter for Robot Task Planning https://ift.tt/oaTs2Gx arXiv:2311.00967v2 Announce Type: replace Abstract: Large language models (LLMs) are accelerating the development of language-guided robot planners. Meanwhile, symbolic planners offer the advantage...

DisMech: A Discrete Differential Geometry-based Physical Simulator for Soft Robots and Structures https://ift.tt/3M7ZWtK arXiv:2311.18126v3 Announce Type: replace Abstract: Fast, accurate, and generalizable simulations are a key enabler of modern advances...

A Simulation-based Approach to Kinematics Analysis of a Quadruped Robot and Prototype Leg Testing https://ift.tt/zp4IVlt arXiv:2312.06365v3 Announce Type: replace Abstract: A multi-joint enabled robot requires extensive mathematical calculations to be...

Kinesthetic-based In-Hand Object Recognition with an Underactuated Robotic Hand https://ift.tt/dhF0524 Tendon-based underactuated hands are intended to be simple, compliant and affordable. Often, they are 3D printed and do not include...

3D-Printed Hydraulic Fluidic Logic Circuitry for Soft Robots https://ift.tt/DxcHaAs Fluidic logic circuitry analogous to its electric counterpart could potentially provide soft robots with machine intelligence due to its supreme adaptability,...

Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control https://ift.tt/eSqrVOx This paper presents a comprehensive study on using deep reinforcement learning (RL) to create dynamic locomotion controllers for bipedal...

Memory-centered and Affordance-based Framework for Mobile Manipulation https://ift.tt/ehgHCcd Performing versatile mobile manipulation actions in human-centered environments requires highly sophisticated software frameworks that are flexible enough to handle special use cases,...

An ARGoS plug-in for the Crazyflie drone https://ift.tt/HzdKtTM We present a new plug-in for the ARGoS swarm robotic simulator to implement the Crazyflie drone, including its controllers, sensors, and some...