📝 Learning Task Skills and Goals Simultaneously From Physical Interaction 🦾

"Develops a framework that enables a robot to learn functional modules and long-term task objectives simultaneously from human demonstrations using a novel functional module identification algorithm and an objective alignment algorithm." [gal30b+] 🤖 #RO

🔗 https://arxiv.org/abs/2309.04596v1 #arxiv

📝 Multi-Contact Stochastic Predictive Control for Legged Robots with Contact Locations Uncertainty 🦾

"Addresses the problem of robust kino-dynamic trajectory optimization using stochastic nonlinear model predictive control (SNMPC) by considering additive uncertainties on the model dynamics subject to contact location chance-constraints as a function of robot's full kinematics." [gal30b+] 🤖 #RO #SY

🔗 https://arxiv.org/abs/2309.04469v1 #arxiv

📝 Comparative Study of Visual SLAM-Based Mobile Robot Localization Using Fiducial Markers 🦾🔭

"The three approaches have similar algorithmic pipeline with a few variations, starting with the fiducial marker detection and camera pose estimation using the Perspective-n-Point (PnP) algorithm [ Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography, Fischler]." [gal30b+] 🤖 #RO #CV

🔗 https://arxiv.org/abs/2309.04441v1 #arxiv

📝 Data-Driven Batch Localization and SLAM Using Koopman Linearization 🦾

"Uses lifting functions to map a control and measurement-affine system into a high-dimensional space where both the process model and measurement model are rendered bilinear by applying the Koopman operator, also known as the composition operator, to each function." [gal30b+] 🤖 #RO

🔗 https://arxiv.org/abs/2309.04375v1 #arxiv

📝 Incremental Learning of Humanoid Robot Behavior From Natural Interaction and Large Language Models 🦾👾

"A large language model generates Python statements to invoke robot perception and action, which are used in the interaction loop to improve the language model based on the human feedback, environment observations, and execution results." [gal30b+] 🤖 #RO #AI

🔗 https://arxiv.org/abs/2309.04316v1 #arxiv

📝 Predictive and Robust Robot Assistance for Sequential Manipulation 🦾

"In order to predict a physically impaired human's behavior, it is essential to have knowledge of the user's intended goals as well as the user's physical limitations." [gal30b+] 🤖 #RO

⚙️ https://github.com/HRI-EU/Rcs
🔗 https://arxiv.org/abs/2309.04185v1 #arxiv

📝 A Novel Method for Layer Jamming-Based Continuum Robots 🦾

"Uses a layer jamming mechanism to adjust the stiffness of LJ-based continuum robots, and propose an energy-based dynamical model that integrates with the LuGre frictional model." [gal30b+] 🤖 #RO #SY

🔗 https://arxiv.org/abs/2309.04154v1 #arxiv

📝 Proprioceptive External Torque Learning for Floating Base Robot and Its Applications to Humanoid Locomotion 🦾👾

"A recurrent neural network and learns how to estimate external joint torque using random walking data of a humanoid robot solely using proprioceptive sensors (encoders and IMUs)." [gal30b+] 🤖 #RO #AI

🔗 https://arxiv.org/abs/2309.04138v1 #arxiv

📝 Sample-Efficient Co-Design of Robotic Agents Using Multi-Fidelity Training on Universal Policy Network 🦾🧠

"Proposes to use Hyperband as a multi-fidelity optimization strategy to improve efficiency of the Co-design optimization by warm starting the control optimization using a universal policy learner that ties the controllers learnt across the design spaces." [gal30b+] 🤖 #RO #LG

🔗 https://arxiv.org/abs/2309.04085v1 #arxiv

📝 SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments 🦾👾

"Presents SayNav, a new approach that leverages human knowledge from Large Language Models (LLMs) for efficient generalization to complex navigation tasks in unknown large-scale environments." [gal30b+] 🤖 #RO #AI

⚙️ https://github.com/allenai/object-nav-eval
🔗 https://arxiv.org/abs/2309.04077v1 #arxiv

皆で新しくキャラクターを新規作成・資産共有しての企画プレイを配信しております。良かったらご視聴ください～。目指すは夢幻！ＰＴ募集中！
https://youtu.be/LtXEmYhDZSc
#RO #ラグナロクオンライン

ROニューゲーム（無課金でET／夢幻） NO032】

https://youtube.com/live/LtXEmYhDZSc

～本日のお品書き～
◆行先
　AB育成の続きと
　4人揃ったら150目指してロックリッジウィークリーとビオモル
◆PTM募集中です！詳しくはDMください。
#RO #ラグナロクオンライン

📝 REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation 🧠👾🦾

"Uses reinforcement learning and an imitation-based pickup policy to learn manipulation skills with a dexterous four-fingered robotic hand in the real world." [gal30b+] 🤖 #LG #AI #RO

🔗 https://arxiv.org/abs/2309.03322v1 #arxiv

📝 ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation 🦾🔭🧠

"Uses reinforcement learning with a curriculum of increasing difficulty that starts with single-hand manipulation of stationary objects and continues with multi-agent training including both hands and non-stationary objects." [gal30b+] 🤖 #RO #CV #LG

🔗 https://arxiv.org/abs/2309.03891v1 #arxiv

📝 Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning 🦾👋🧠

"Proposes a reinforcement learning algorithm to train an agent that learns a denoiser for raw human command signals and provides shared autonomy assistance by inferring the user's intent." [gal30b+] 🤖 #RO #HC #LG

🔗 https://arxiv.org/abs/2309.03839v1 #arxiv

📝 Learning From Demonstration via Probabilistic Diagrammatic Teaching 🦾🧠

"A demonstration trajectory is first sketched by the user on a 2D image of the scene using a pen and paper, the trajectory is then represented as a time-varying probability density." [gal30b+] 🤖 #RO #LG

🔗 https://arxiv.org/abs/2309.03835v1 #arxiv

📝 An Anthropomorphic Continuum Robotic Neck Actuated by SMA Spring-Based Multipennate Muscle Architecture 🦾

"SMA spring actuator is embedded within a continuum joint with specific geometric configuration to deliver smooth, high-energy-efficient motion for continuum robots as demonstrated in this work for humanoid neck." [gal30b+] 🤖 #RO #SY

🔗 https://arxiv.org/abs/2309.03683v1 #arxiv

📝 Estimating the Coverage Measure and the Area Explored by a Line-Sweep Sensor on the Plane 🦾

"Leverages the concept of coverage measure of the environment and its relation to the topological degree in the plane, to estimate the extent of the explored region using the sensor footprint and the coverage measure." [gal30b+] 🤖 #RO #SY

⚙️ https://github.com/marialuizacvianna/extended
🔗 https://arxiv.org/abs/2309.03604v1 #arxiv

ROニューゲーム（無課金でET／夢幻） NO031】

https://youtube.com/live/y_00FNVC-6E

～本日のお品書き～
◆行先
　90レベルからのAB育成！
◆PTM募集中です！詳しくはDMください。
#RO #ラグナロクオンライン

📝 Occlusion-Free Image Based Visual Servoing Using Probabilistic Control Barrier Certificates 🦾

"We propose a CBF-based controller that enables occlusion-free IBVS tasks by automatically adjusting the robot's configuration to keep the feature points in the field of view and away from obstacles." [gal30b+] 🤖 #RO

🔗 https://arxiv.org/abs/2309.03476v1 #arxiv