14,432 Hits in 4.6 sec

STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation [article]

Mohak Bhardwaj, Balakumar Sundaralingam, Arsalan Mousavian, Nathan Ratliff, Dieter Fox, Fabio Ramos, Byron Boots
2021 arXiv   pre-print
In this paper, we develop a system for fast, joint space sampling-based MPC for manipulators that is efficiently parallelized using GPUs.  ...  Sampling-based model-predictive control (MPC) is a promising tool for feedback control of robots with complex, non-smooth dynamics, and cost functions.  ...  However, manipulation tasks often involve Our sampling-based model-predictive control framework operates in the joint space to enable a robot to achieve manipulation objectives such as tracking a moving  ... 
arXiv:2104.13542v2 fatcat:3tfrs3eh3nex7fwicravdvr62a

SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control [article]

Arunkumar Byravan, Felix Leeb, Franziska Meier, Dieter Fox
2017 arXiv   pre-print
We further show that our model can be used for closed-loop control directly in the learned low-dimensional pose space, where the actions are computed by minimizing error in the pose space using gradient-based  ...  Our deep dynamics model, a variant of SE3-Nets, learns a low-dimensional pose embedding for visuomotor control via an encoder-decoder structure.  ...  We would also like to thank NVIDIA for generously providing a DGX used for this research via the UW NVIDIA AI Lab (NVAIL).  ... 
arXiv:1710.00489v1 fatcat:gvacvwuexzdbvlwuxw2ywsec6e

Hierarchical planning architectures for mobile manipulation tasks in indoor environments

Ross A Knepper, Siddhartha S Srinivasa, Matthew T Mason
2010 2010 IEEE International Conference on Robotics and Automation  
This paper describes a hierarchical planner deployed on a mobile manipulation system.  ...  We place a premium on fast response, so the global planner achieves speed by using a very rough approximation of the robot kinematics, and the local planner begins execution of the next action even without  ...  Local Planner The arm controller relies on a combination of model predictive and PID control.  ... 
doi:10.1109/robot.2010.5509669 dblp:conf/icra/KnepperSM10 fatcat:j7cxkhpbjnfvxn2ahu4vot6y4i

Compensation of Nonlinear Torsion in Flexible Joint Robots: Comparison of Two Approaches

Michael Ruderman
2016 IEEE transactions on industrial electronics (1982. Print)  
The second approach relies on the modeling of motor drives and inverse hysteresis and uses the generalized momenta when predicting the joint torsion.  ...  In this paper, two approaches for compensating the nonlinear joint torsion with hysteresis are described and compared with each other.  ...  The observed reactive joint torque allows for computing the relative joint torsion. Thus, the motor drive feedback control operates in the 'virtual' joint link space by accounting for torsion.  ... 
doi:10.1109/tie.2016.2574299 fatcat:mdokjsrt3zatnlx3kzu55pqhby

Real-time Perception meets Reactive Motion Generation [article]

Daniel Kappler, Jim Mainprice , Vincent Berenz and Jeannette Bohg Autonomous Motion Department at the MPI for Intelligent Systems, Tübingen, Germany, CLMC lab at the University of Southern California, Los Angeles, CA, USA, Lula Robotics Inc., Seattle, WA, USA, Dept. of Computer Science & Engineering, Univ. of Washington (+1 others)
2017 arXiv   pre-print
This uncertainty is due to noisy sensing, inaccurate models and hard-to-predict environment dynamics.  ...  only reacts to local environment dynamics and (iii) a reactive planner that integrates feedback control and motion optimization.  ...  On real robotic platforms, kinematic models and measured joint angles are commonly inaccurate and therefore lead to erroneous predictions of end-effector pose relative to the camera.  ... 
arXiv:1703.03512v3 fatcat:y3y25efvw5fsjeqw6j3xh7glve

Flexible-Joint Manipulator Trajectory Tracking with Learned Two-Stage Model employing One-Step Future Prediction [article]

Dmytro Pavlichenko, Sven Behnke
2021 arXiv   pre-print
Flexible-joint manipulators are frequently used for increased safety during human-robot collaboration and shared workspace tasks.  ...  We compare joint position, joint velocity and end-effector position tracking accuracy against the classical baseline controller and several simpler models.  ...  INTRODUCTION Robot manipulators have been used for decades, and trajectory tracking control has been extensively researched to achieve fast and accurate motion.  ... 
arXiv:2112.02979v1 fatcat:ity4vwokzrb2vipd45wilz3h6a

Efficient and Reactive Planning for High Speed Robot Air Hockey [article]

Puze Liu, Davide Tateo, Haitham Bou-Ammar, Jan Peters
2021 arXiv   pre-print
Using two Kuka Iiwa 14, we show how to design a policy for general-purpose robotic manipulators for the air hockey game.  ...  For these reasons, this environment is perfect for pushing to the limit the performance of currently available general-purpose robotic manipulators.  ...  After each prediction step, we apply the collision model from [1] . Every time a collision happens, we don't update the covariance matrix, as it is hard to model the bounce uncertainty.  ... 
arXiv:2107.06140v2 fatcat:dj2k2ybwabchzlrgana6c4e6ne

Motion Control of a Robot Manipulator in Free Space Based on Model Predictive Control [chapter]

Vincent Duchaine, Samuel Bouchard, Clement Gosseli
2008 Robot Manipulators  
As shown in the previous section, the joint space velocity can be predicted using eq. (7).  ...  Application to manipulators This part aims at showing how Model Predictive Control can be efficiently applied to robot manipulators to suit their fast servo rate.  ...  Motion Control of a Robot Manipulator in Free Space Based on Model Predictive Control, Robot Manipulators, Marco Ceccarelli (Ed.), ISBN: 978-953-7619-06-0, InTech, Available from:  ... 
doi:10.5772/6202 fatcat:hdc2wlitnjg37lcy3fejasf6ea

A hierarchical approach to minimum-time control of industrial robots

Saed Al Homsi, Alexander Sherikov, Dimitar Dimitrov, Pierre-Brice Wieber
2016 2016 IEEE International Conference on Robotics and Automation (ICRA)  
Model predictive control is used in order to achieve reactive system behavior and to obtain accurate local approximations of the collision avoidance constraints (which are nonconvex).  ...  Our formulation is applied to the online generation of trajectories for industrial robots performing pick and place operations in the presence of obstacles.  ...  We achieve a reactive behavior by using model predictive control, and our approach has the capacity to suppress high frequency chattering in the control signal in the presence of noise: a common drawback  ... 
doi:10.1109/icra.2016.7487386 dblp:conf/icra/HomsiSDW16 fatcat:hkd2d5rrk5e7xfmfwq3kz3meti

Plan-Based Control of Joint Human-Robot Activities

Alexandra Kirsch, Thibault Kruse, E. Akin Sisbot, Rachid Alami, Martin Lawitzky, Dražen Brščić, Sandra Hirche, Patrizia Basili, Stefan Glasauer
2010 Künstliche Intelligenz  
We present a newly emerging application for autonomous robots: companion robots that are not merely machines performing tasks for humans, but assistants that achieve joint goals with humans.  ...  This collaborative aspect entails specific challenges for AI and robotics.  ...  Joint intention theory [4] provides a basis for modeling the commitment of the cooperation partners to a joint tasks.  ... 
doi:10.1007/s13218-010-0043-1 fatcat:xqiez7dgm5hfplr7ucksh5snye

A Proactive Strategy for Safe Human-Robot Collaboration based on a Simplified Risk Analysis

Audun Sanderud, Trygve Thomessen, Hisashi Osumi, Mihoko Niitsuma
2015 Modeling, Identification and Control  
Kinematic redundancy was exploited for simultaneous task performance within task constraints, and risk minimization. Sphere-based geometric models were used both for the human and robot.  ...  Based on this risk field, a control algorithm that constantly reduces the current risk within its task constraints was developed.  ...  Implementing this or similar strategies could also provide a predictive model, based on the likelihood analysis.  ... 
doi:10.4173/mic.2015.1.2 fatcat:hp7ldvtrkrcpphpnkg4ebpzj6y

Prediction-based reactive control strategy for human-robot interactions

Nima Najmaei, Mehrdad R Kermani
2010 2010 IEEE International Conference on Robotics and Automation  
In this paper a reactive control strategy intended for human-robot interactions (HRI) is presented. A conventional reactive control scheme is reviewed first.  ...  This is followed by the introduction of a new prediction-based reactive control strategy.  ...  Prediction-Based Reactive Control Strategy In this section, a new prediction-based reactive control strategy for human-safe robots is proposed.  ... 
doi:10.1109/robot.2010.5509179 dblp:conf/icra/NajmaeiK10 fatcat:gixmpchwkbhbtdr6gkaajvs76q

Collaborative Behavior Models for Optimized Human-Robot Teamwork [article]

Adam Fishman, Chris Paxton, Wei Yang, Dieter Fox, Byron Boots, Nathan Ratliff
2020 arXiv   pre-print
In this work, we describe a novel Model Predictive Control (MPC)-based framework for finding optimal trajectories in a collaborative, multi-agent setting, in which we simultaneously plan for the robot  ...  We use human-robot handovers to demonstrate that with a strong model of the collaborator, our framework produces fluid, reactive human-robot interactions in novel, cluttered environments.  ...  We derive predictive models for each external, i.e., uncontrolled, agent and an optimal control objective for the controlled agent, i.e.the robot.  ... 
arXiv:1910.04339v2 fatcat:gg4qlehnwfc2nd2btsbzr5dtzu

Comparing Alternate Modes of Teleoperation for Constrained Tasks [article]

Christopher E. Mower and Wolfgang Merkt and Aled Davies and Sethu Vijayakumar
2019 arXiv   pre-print
Our experiments show that higher performance is achieved when humans submit commands in low-dimensional task spaces as opposed to joint space manipulations.  ...  , task-informed control space while having the robot optimize for achieving desired job properties.  ...  typically model manipulation tasks in the task space.  ... 
arXiv:1905.04428v1 fatcat:simzxlpe35b4ja7wvuuhvxabfe

Multi 3D camera mapping for predictive and reflexive robot manipulator trajectory estimation

Justinas Miseikis, Kyrre Glette, Ole Jakob Elle, Jim Torresen
2016 2016 IEEE Symposium Series on Computational Intelligence (SSCI)  
However, robot control can be still a limiting factor for better adaptation of these technologies.  ...  We present a method combining 3D Camera based workspace mapping, and a predictive and reflexive robot manipulator trajectory estimation to allow more efficient and safer operation in dynamic workspaces  ...  ACKNOWLEDGMENT This work is partially supported by The Research Council of Norway as a part of the Engineering Predictability with Embodied Cognition (EPEC) project, under grant agreement 240862  ... 
doi:10.1109/ssci.2016.7850237 dblp:conf/ssci/MiseikisGET16 fatcat:ksoe7oth4jcjdhf6jrgb4z2xri
« Previous Showing results 1 — 15 out of 14,432 results