Catching Objects in Flight

@article{Kim2014CatchingOI,
  title={Catching Objects in Flight},
  author={Seungsu Kim and Ashwini Shukla and Aude Billard},
  journal={IEEE Transactions on Robotics},
  year={2014},
  volume={30},
  pages={1049-1065}
}
We address the difficult problem of catching in-flight objects with uneven shapes. This requires the solution of three complex problems: accurate prediction of the trajectory of fastmoving objects, predicting the feasible catching configuration, and planning the arm motion, and all within milliseconds. We follow a programming-by-demonstration approach in order to learn, from throwing examples, models of the object dynamics and arm movement. We propose a new methodology to find a feasible… Expand
Neural Motion Prediction for In-flight Uneven Object Catching
TLDR
Experimental results show that motion prediction with NAE and NAE-DF is superior to other methods and has a good generalization performance on unseen objects. Expand
A Dynamical System Approach for Softly Catching a Flying Object: Theory and Experiment
TLDR
This work presents a strategy to overcome for sensorimotor imprecision by introducing softness in the catching approach, and proposes a method to approximate the parameters of LPV systems using Gaussian mixture models, based on a set of kinematically feasible demonstrations generated by an offline optimal control framework. Expand
Batting an in-flight object to the target
TLDR
This paper investigates the problem of a two-degree-of-freedom robotic arm intercepting an object in free flight and redirecting it to some target with a single strike, assuming all the movements take place in one vertical plane. Expand
Revisiting Ball Catching with a Mobile Manipulator : A Discrete Trajectory Planning Approach
Catching a ball with a mobile manipulator is a classic robotics benchmark that requires continuously interleaving prediction and re-planning in order to make a successful grasp mid-air. ExistingExpand
Robotic batting and motion estimation of objects in free flight
TLDR
This thesis addresses the problem of a robotic arm striking an object in free flight to a target, and a closely related problem of estimating its pose and motion during the flight based on vision, and presents a stereo vision system consisting of two high-speed cameras. Expand
Hitting flying objects with learning from demonstration
  • J. Chen, Shen Shen, H. Lau
  • Engineering, Computer Science
  • 2017 18th International Conference on Advanced Robotics (ICAR)
  • 2017
TLDR
A six degrees-of-freedom UR5 robot is implemented to hit a freely flying ball, the dynamics of the ball is derived, and the analytical inverse kinematics model of the robot is given. Expand
Catching and Throwing Control of a Physically Simulated Hand
We design a nominal controller for animating an articulated physicsbased human arm model, including the hands and fingers, to catch and throw objects. The controller is based on a finite stateExpand
Fast kNN-based prediction for the trajectory of a thrown body
  • K. Mironov, M. Pongratz
  • Computer Science
  • 2016 24th Mediterranean Conference on Control and Automation (MED)
  • 2016
TLDR
The parallelized version of the algorithm, based on nearest neighbor regression, is implemented on the robotic catching system and provide successful catch for up to 86 % of thrown objects. Expand
Robust Ballistic Catching: A Hybrid System Stabilization Problem
TLDR
A novel parameterization is derived to reduce the three-dimensional catching problem to 1-D on the ballistic flight path and constrained dynamic optimization maximizes convergence speed while satisfying all kinematic and dynamic limits. Expand
No-frills Dynamic Planning using Static Planners
TLDR
This paper addresses the task of interacting with dynamic environments where the changes in the environment are independent of the agent through the context of trapping a moving ball with a UR5 robotic arm and proposes an approach to utilize a static planner for dynamic tasks using a Dynamic Planning add-on. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 47 REFERENCES
Trajectory planning for optimal robot catching in real-time
TLDR
Evaluations indicate that the presented method is highly efficient in complex tasks such as ball-catching, which can be formulated as a non-linear optimization problem where the desired trajectory is encoded by an adequate parametric representation. Expand
Learning motion dynamics to catch a moving object
TLDR
An extension of the system that allows to control the timing of the motion while still benefitting from all the robustness properties deriving from the time-independent encoding of the DS is proposed. Expand
Kinematically optimal catching a flying ball with a hand-arm-system
TLDR
A mechatronically complex dexterous hand is used for grasping the ball and the decision of where, when and how to catch the ball, while obeying joint, speed and work cell limits, is formulated as an unified nonlinear optimization problem with nonlinear constraints. Expand
Estimating the non-linear dynamics of free-flying objects
TLDR
A model-free method to estimate the dynamics of free-flying objects and is coupled with an Extended Kalman Filter for robustness against noisy sensing to enable real-time tracking. Expand
Coupled dynamical system based arm-hand grasping model for learning fast adaptation strategies
TLDR
A coupled dynamical system based controller is developed, whereby two dynamical systems driving the hand and finger motions are coupled, which offers a compact encoding for reach-to-grasp motions that ensures fast adaptation with zero latency for re-planning. Expand
Sensor-based online trajectory generation for smoothly grasping moving objects
  • M. Zhang, M. Buehler
  • Computer Science
  • Proceedings of 1994 9th IEEE International Symposium on Intelligent Control
  • 1994
TLDR
The authors develop a geometric controller which specifies the full 6DOF position and orientation of the robot's end effector, and provides a framework for general sensor based control of robotic tasks. Expand
Movement templates for learning of hitting and batting
TLDR
The Ijspeert framework is reformulate to incorporate the possibility of specifying a desired hitting point and a desired hit velocity while maintaining all advantages of the original formulation and is shown to work well in two scenarios. Expand
Planning and Control of Robotic Juggling and Catching Tasks
TLDR
A new class of control algorithms—the "mirror algorithms"— gives rise to experimentally observed juggling and catching behavior in a planar robotic mechanism and the physical setup and underlying mathematical theory are reviewed. Expand
Learning Non-linear Multivariate Dynamics of Motion in Robotic Manipulators
TLDR
An algorithm to estimate multivariate robot motions through a mixture of Gaussians, which allows a generalization of motion to unseen context and provides fast on-line replanning of the motion in case of of spatio-temporal perturbations. Expand
Learning the Nonlinear Multivariate Dynamics of Motion of Robotic Manipulators
Motion imitation requires reproduction of a dynamical signature of a movement, i.e. a robot should be able to encode and reproduce a particular path together with a specific velocity and/or anExpand
...
1
2
3
4
5
...