Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Filters








1,210 Hits in 7.1 sec

Mini Cheetah, the Falling Cat: A Case Study in Machine Learning and Trajectory Optimization for Robot Acrobatics [article]

Vince Kurtz, He Li, Patrick M. Wensing, Hai Lin
2022 arXiv   pre-print
Seemingly in defiance of basic physics, cats consistently land on their feet after falling. In this paper, we design a controller that lands the Mini Cheetah quadruped robot on its feet as well.  ...  We validate our proposed controller in both simulation and hardware experiments, and are able to land the robot on its feet from falls with initial pitch angles between -90 and 90 degrees.  ...  The Mini Cheetah is sponsored by the MIT Biomimetic Robotics Lab and NAVER LABS.  ... 
arXiv:2109.04424v2 fatcat:wp2lmeklqfaxbnks3utp45s4le

On the dynamics and control of a squirrel locking its head/eyes toward a fixed spot for safe landing while its body is tumbling in air

Tianqi Ma, Tao Zhang, Ou Ma
2022 Frontiers in Robotics and AI  
Understanding the underline dynamics and how the squirrel does this behavior can inspire robotics researchers to develop bio-inspired control strategies for challenging robotic operations such as hopping  ...  One of the control methods is a conventional proportional-derivative (PD) controller, and the other is a reinforcement learning (RL)-based controller.  ...  τ; γ ∈ [0, 1) denotes the discount factor; and E [R(τ)] (approximated by a neural network) is the expectation of trajectory reward R(τ).The control method is based on the PPO2 algorithm, as shown in Figure  ... 
doi:10.3389/frobt.2022.1030601 pmid:36504492 pmcid:PMC9729943 fatcat:3ecjmpgk5bealbmiq42r5ijkgy

A Bio-Inspired Hopping Kangaroo Robot with an Active Tail

Guan-Horng Liu, Hou-Yi Lin, Huai-Yu Lin, Shao-Tuan Chen, Pei-Chun Lin
2014 Journal of Bionic Engineering  
Inspired by kangaroo's locomotion, we report on developing a kangaroo-style hopping robot.  ...  In this work, we generate the Center of Mass (CoM) locomotion of the robot based on the reduced-order Rolling Spring Loaded Inverted Pendulum (R-SLIP) model, for matching the dynamic behavior of the empirical  ...  This work is supported by National Science Council (NSC), Taiwan, under contract NSC 100-2628-E-002-021-MY3.  ... 
doi:10.1016/s1672-6529(14)60066-4 fatcat:vqmaisfilfhr3ieadyuszcxxoq

A neurobiological perspective on humanoid robot design

S.F. Giszter, K.A. Moxon, I. Rybak, J.K. Chapin
2000 IEEE Intelligent Systems and their Applications  
We are inspired by computational design because of its unrivaled flexibility, fault tolerance, and power to manage vast arrays of sensory information and novel tasks.  ...  During the last two decades, biologically inspired robotics developed into a burgeoning field exploring the ideas of artificial life and adaptive behaviors (see the sidebar, "An expanding field").  ...  Acknowledgments This work was partially funded by National Institutes of Health contract NS34640 to Simon Giszter and NIH contract NS62352 and Office of Naval Research grant N00014-98-1-0679 to John Chapin  ... 
doi:10.1109/5254.867914 fatcat:fc26b7ev2regvc2zqsonpa24ri

Sampling-Based Motion Planning for Free-Floating Space Robot without Inverse Kinematics

Hongwen Zhang, Zhanxia Zhu
2020 Applied Sciences  
Motion planning is one of the most important technologies for free-floating space robots (FFSRs) to increase operation safety and autonomy in orbit.  ...  Thus, faced with these questions, this paper investigates a novel motion planning algorithm based on rapidly-exploring random trees (RRTs) for an FFSR from an initial configuration to a goal end-effector  ...  Introduction Free-floating space robots (FFSRs) are composed of a manipulator and a base spacecraft.  ... 
doi:10.3390/app10249137 fatcat:plxmh7vvund23hbe5ih2ejvog4

Active learning in robotics: A review of control principles

Annalisa T. Taylor, Thomas A. Berrueta, Todd D. Murphey
2021 Mechatronics (Oxford)  
This is a review of active learning in robotics, focusing on methods amenable to the demands of embodied learning systems.  ...  We discuss classes of learning tasks that robots typically encounter, measures with which they gauge the information content of observations, and algorithms for generating action plans.  ...  Acknowledgments We would like to thank Muchen Sun, Ana Pervan, Kyra Rudy, Frank Park, and the anonymous reviewers of the first draft for their many helpful comments on this manuscript.  ... 
doi:10.1016/j.mechatronics.2021.102576 fatcat:qt47bncznzdtdc7ntpmis5dqw4

Legless Locomotion: A Novel Locomotion Technique for Legged Robots

Ravi Balasubramanian, Alfred A. Rizzi, Matthew T. Mason
2008 The international journal of robotics research  
We present a novel locomotion strategy called legless locomotion that allows a round-bodied legged robot to locomote approximately when it is high-centered.  ...  Typically, a high-centered robot is stuck since the robot's legs do not touch the ground.  ...  Acknowledgments The authors thank their colleagues from the Robotics Institute at Carnegie Mellon University for providing feedback in this research.  ... 
doi:10.1177/0278364908091023 fatcat:vsxqa7eljvcvra4q7rhnfbamti

Efficient Object Manipulation to an Arbitrary Goal Pose: Learning-based Anytime Prioritized Planning [article]

Kechun Xu, Hongxiang Yu, Renlang Huang, Dashun Guo, Yue Wang, Rong Xiong
2022 arXiv   pre-print
We focus on the task of object manipulation to an arbitrary goal pose, in which a robot is supposed to pick an assigned object to place at the goal position with a specific orientation.  ...  However, limited by the execution space of the manipulator with gripper, one-step picking, moving and releasing might be failed, where a reorientation object pose is required as a transition.  ...  RELATED WORK A. Robotic 6-DoF Grasping Robotic 6-DoF grasping has been a topic of interest for researchers for decades.  ... 
arXiv:2109.10583v2 fatcat:vpsk5nb2hjfrpo47xak7yukiq4

A Wearable Body Controlling Device for Application of Functional Electrical Stimulation

Nazita Taghavi, Greg Luecke, Nicholas Jeffery
2018 Sensors  
In this research, we describe a new balancing device used to stabilize the rear quarters of a patient dog with spinal cord injuries.  ...  During this phase of development, we designed and built a mechanical test-bed to develop the control and stimulation algorithms before we use the device on our animal subjects.  ...  Acknowledgments: Authors would like to appreciate financial support of the McGee-Wagner Interdisciplinary Research Fund and the Virtual Reality Application Center at Iowa State University.  ... 
doi:10.3390/s18041251 pmid:29670039 pmcid:PMC5948602 fatcat:n5zio4u6hva7pkgtcffgnqm4ai

Hierarchical control of visually-guided movements in a 3D-printed robot arm [article]

Adam Matic, Pavle Valerjev, Alex Gomez-Marin
2021 bioRxiv   pre-print
We built a robot arm system with four degrees of freedom, including a visual system for locating the planar position of the hand, joint angle proprioception, and pressure sensing in one point of contact  ...  These behavioral properties emerge without trajectory planning or explicit optimization algorithms.  ...  We are grateful to Regina Zaghi-Lara for photos of the robot arm.  ... 
doi:10.1101/2021.08.10.455600 fatcat:xgasqxhq7zhijible5kka2vmve

Hierarchical Control of Visually-Guided Movements in a 3D-Printed Robot Arm

Adam Matić, Pavle Valerjev, Alex Gomez-Marin
2021 Frontiers in Neurorobotics  
We built a robot arm system with four degrees of freedom, including a visual system for locating the planar position of the hand, joint angle proprioception, and pressure sensing in one point of contact  ...  These behavioral properties emerge without trajectory planning or explicit optimization algorithms.  ...  We are grateful to Regina Zaghi-Lara for photos of the robot arm.  ... 
doi:10.3389/fnbot.2021.755723 pmid:34776921 pmcid:PMC8589028 fatcat:jj4gvctztngrzf27oafzr2l22u

Final Program

2021 2021 18th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE)  
Kalman introduced them at the end of 1950's. They have been constantly developed and improved from that time on, with a growing number of successfull applications.  ...  invention of Scanning Tunneling Microscope by Nobel Price winners G.  ...  and Path Planning of a Spherical Robot using Stochastic Signals SiOxCy Photoluminescence properties of SiOxCy-films deposited under argon atmosphere and Si-based organometallic precursor by O-Cat-CVD  ... 
doi:10.1109/cce53527.2021.9632879 fatcat:tklvuqrhajagxf4cfcmufbcveu

The Yoyo-Man [chapter]

Jean-Paul Laumond, Mehdi Benallegue, Justin Carpentier, Alain Berthoz
2017 Springer Proceedings in Advanced Robotics  
The motivation of the research starts from the simple observation that humans may stumble when following a simple reflex-based locomotion on uneven terrains.  ...  The rationale combines two well established results in robotics and neuroscience respectively: • Passive robot walkers, which are very efficient in terms of energy consumption, can be modelled by a simple  ...  Ackowledgements This paper benefits from the valuable comments by reviewers of a short version presented at the 17th International Symposium on Robotics Research (ISRR) in Sestri Levante in 2015.  ... 
doi:10.1007/978-3-319-60916-4_13 dblp:conf/isrr/LaumondBCB15 fatcat:vbezxpawfzhljhclcjrwed4c4u

Adaptive zero reaction motion control for free-floating space manipulators

Shuanfeng Xu, Hanlei Wang, Duzhou Zhang, Baohua Yang
2016 IEEE Transactions on Aerospace and Electronic Systems  
The performance of the proposed adaptive controller is shown by numerical simulations with a planar 3-DOF (degree-of-freedom) space manipulator.  ...  The main contribution of this paper is that we skillfully obtain such a linear expression, based on which, an adaptive version of the RNS-based controller (referred to as the adaptive zero reaction motion  ...  Xindong Li for their suggestions on improving the quality of this paper.  ... 
doi:10.1109/taes.2016.130715. fatcat:ne6ux7s66rb7jk5halvghrj5ze

UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy [article]

Yinzhen Xu, Weikang Wan, Jialiang Zhang, Haoran Liu, Zikang Shan, Hao Shen, Ruicheng Wang, Haoran Geng, Yijia Weng, Jiayi Chen, Tengyu Liu, Li Yi (+1 others)
2023 arXiv   pre-print
In this work, we tackle the problem of learning universal robotic dexterous grasping from a point cloud observation under a table-top setting.  ...  Inspired by successful pipelines used in parallel gripper grasping, we split the task into two stages: 1) grasp proposal (pose) generation and 2) goal-conditioned grasp execution.  ...  Once the process ends, we lift the robot's hand to see whether the object falls down. PPO PPO [52] is a popular model-free on-policy RL method.  ... 
arXiv:2303.00938v2 fatcat:d5oirltotzhuxnxv3agdsl5tgq
« Previous Showing results 1 — 15 out of 1,210 results