Catching Objects in Flight
Open accessThe DOI matches its Crossref record; 48 of the 52 references it cites were found in a registry or an index; 18 of the 25 sources its claims cite were checked for support.
Abstract
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 catching configuration in a probabilistic manner. We use the dynamical systems approach to encode motion from several demonstrations. This enables a rapid and reactive adaptation of the arm motion in the presence of sensor uncertainty. We validate the approach in simulation with the iCub humanoid robot and in real-world experiments with the KUKA LWR 4+ (7-degree-of-freedom arm robot) to catch a hammer, a tennis racket, an empty bottle, a partially filled bottle, and a cardboard box.
Overview
CoChat Summary
## TL;DR
This paper presents a real-time robot-catching framework that learns object flight dynamics and feasible grasping/reachability from demonstrations, then combines them to predict where and when to catch in-flight objects. It is validated in iCub simulation and on a KUKA LWR 4+ with an Allegro hand, achieving 100% success in simulation and 73.2% in real-world trials.
## Key findings
- The paper reports a 100% success rate for catching two objects in iCub simulation, based on 50 throws; 3 of 50 throws were excluded because they did not enter the robot’s reachable space.
- In real-robot experiments, the system caught 52 out of 71 total trials, yielding a 73.2% success rate; 9 of 80 throws were excluded because they never entered reachable space.
- The system predicts the best catching configuration in about 0.2 ms on a 2.7-GHz quad-core PC, enabling real-time replanning.
- For the real robot, the paper reports mean flying time across all trials of 4.97 ± 0.46 s, and the model predicts trajectories better than a rigid-body model, especially for the partially filled bottle.
## Methods
- The framework has two iterative threads: one continuously predicts object trajectory and updates the best catching configuration and timing; the other adapts arm and finger motion to the updated target.
- Object dynamics are learned from demonstrations using support vector regression with an RBF kernel and coupled with an EKF for noisy sensing; the paper states the model uses about 20 throwing examples per object.
- Graspable space and reachable space are each modeled as Gaussian mixture models, with the optimal catching posture found by maximizing the joint probability of the combined models; arm/hand motion is generated using coupled dynamical systems (CDS) and a timing controller.
- Validation uses iCub simulation with a hammer and tennis racket, and a KUKA LWR 4+ with Allegro hand in real-world experiments on an empty bottle, partially filled bottle, tennis racket, and cardboard box.
## Limitations
- The paper states that the trajectory model is local: if an object is thrown very differently from the demonstrations, prediction can become inaccurate, especially for highly nonlinear motions such as a partially filled bottle.
- The authors say they do not explicitly compute collisions between the object and the hand/arm before catching; they use heuristics instead, and this leads to some failures.
- They state they model only task dynamics, not robot dynamics, so some generated trajectories produce velocities the robot cannot follow.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
14 Valid · 9 Not valid · 2 Not checked · 81 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“Note that this does not require any prior information on the physical properties of the object, such as its mass, position of COM, and moment of inertia.”
What the sources say
- Supportedcites [22] [22] S. Kim and A. Billard, 'Estimating the non-linear dynamics of free-flying objects,' Robot. Auton. Syst. , vol. 60, no. 9, pp. 1108-1122, 2012. - source
Section 2.4 says the DS encoding learns from observed motion without prior information about physical properties such as mass, and that the approach makes no assumption about the center-of-mass position. The passage labeled Table 11 contrasts it with conventional techniques that require properties such as moment of inertia. (LLM, conf=0.94)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In our previous work [22], we learned from demonstrations the dynamics of more complex objects whose shapes are arbitrary, nonrigid, or their points of interest are not at the COM.”
What the sources say
- Partly supportedcites [22] [22] S. Kim and A. Billard, 'Estimating the non-linear dynamics of free-flying objects,' Robot. Auton. Syst. , vol. 60, no. 9, pp. 1108-1122, 2012. - sourceExperimental — accuracy not yet measured
The Introduction describes learning motion dynamics from human throwing demonstrations, and Section 2.4 says the method handles arbitrarily shaped objects and points away from the center of mass. Section 4.1.1 also studies a half-filled bottle whose moment of inertia changes in flight, but our copy does not establish that the method was applied to nonrigid objects themselves. (LLM, conf=0.84)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In [38], we show that modeling arm and hand motion through coupled dynamical systems (CDS) is advantageous over the classic approaches reviewed previously.”
What the sources say
- Partly supportedcites [38] [38] A. Shukla and A. Billard, 'Coupled dynamical system based armhand grasping model for learning fast adaptation strategies,' Robot. Auton. Syst. , vol. 60, no. 3, pp. 424-440, 2012. - sourceExperimental — accuracy not yet measured
The Conclusion and discussion says that explicit coupling of hand and finger motion was advantageous over implicit coupling learned with other density-based methods. Section 4.3.1 illustrates that advantage against a single-GMM approach. The paper does not establish an advantage over classic approaches generally, as the citing sentence suggests. (LLM, conf=0.78)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Such a spatial coupling between hand and fingers ensures timely closure of the fingers while following the learned dynamics as closely as possible, even in the presence of arbitrary perturbations.”
What the sources say
- Partly supportedcites [38] [38] A. Shukla and A. Billard, 'Coupled dynamical system based armhand grasping model for learning fast adaptation strategies,' Robot. Auton. Syst. , vol. 60, no. 3, pp. 424-440, 2012. - sourceExperimental — accuracy not yet measured
Section 4.3.1 reports that explicit coupling delays finger closure after a target switch and produces a successful grasp; Section 4.2.2 says finger trajectories resume the unperturbed motion model after perturbation. The claim overextends these results to arbitrary perturbations: Section 5.1 notes that perturbations far from demonstrated motions may yield infeasible robot motions, and the experiments stayed within the center of the robot’s workspace. Page numbers are not available in our copy. (LLM, conf=0.86)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“This offers a robust and fast control of the complete hand-arm system without resorting to extensive parameter tuning.”
What the sources say
- Supportedcites [38] [38] A. Shukla and A. Billard, 'Coupled dynamical system based armhand grasping model for learning fast adaptation strategies,' Robot. Auton. Syst. , vol. 60, no. 3, pp. 424-440, 2012. - source
Section 4.3 reports robust reach-and-grasp control and rapid adaptation to perturbations; Section 4.1 says the implementation controls the arm and finger joints together. Sections 4.2.3 and 5.1 describe just two free parameters that can be inferred from human data and call the parameterization simple and explicit, supporting the claim that extensive tuning is unnecessary—not that no tuning occurs. Page numbers are unavailable in our copy. (LLM, conf=0.86)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
50 more claims · 5 with their cited sources checked
Create a free account to see all 106 claims and every source verdict.
- It may state two separate claims as one. 31
- Probably not a substantial claim. 22
- The quote only partly states this claim. 4
Citations
Cites
Maximum Likelihood from Incomplete Data Via the EM Algorithm
Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1977.tb01600.x · Cited by 50,444
Estimating the Dimension of a Model
Schwarz, G. (1978) · The Annals of Statistics · doi:10.1214/aos/1176344136 · Cited by 47,033
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918
On Learning, Representing, and Generalizing a Task in a Humanoid Robot
Calinon, S., Guenter, F., & Billard, A. (2007) · IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) · doi:10.1109/tsmcb.2006.886952 · Cited by 1,090 · cited 1×
“13 come from the sin- gularity of using Euler angles to represent the orientation (note that the real orientation trajectory of the both models are continuous).”
MethodSelf-citationLearning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models
Khansari-Zadeh, S. M., & Billard, A. (2011) · IEEE Transactions on Robotics · doi:10.1109/tro.2011.2159412 · Cited by 771
Self-citationCapturing robot workspace structure: representing robot capabilities
Zacharias, F., Borst, C., & Hirzinger, G. (2007) · 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2007.4399105 · Cited by 269
A dynamical system approach to realtime obstacle avoidance
Khansari-Zadeh, S. M., & Billard, A. (2012) · Autonomous Robots · doi:10.1007/s10514-012-9287-y · Cited by 264 · cited 1×
“In Section III, we validate the method in simulation by using the iCub simulator, and in a real robot by using the LWR 4+. Section IV concludes with a summary of remaining issues that will be addressed in future work.”
MethodSelf-citationWorkspaces of planar parallel manipulators
Merlet, J.-P., Gosselin, C. M., & Mouly, N. (1998) · Mechanism and Machine Theory · doi:10.1016/s0094-114x(97)00025-6 · Cited by 240
Planning and Control of Robotic Juggling and Catching Tasks
Buehler, M., Koditschek, D. E., & Kindlmann, P. J. (1994) · The International Journal of Robotics Research · doi:10.1177/027836499401300201 · Cited by 227
Kyriakopoulos, K. J., & Saridis, G. N. (2003) · Proceedings. 1988 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.1988.12075 · Cited by 212
Research works printed but not linked: 1
- [34] S. Schaal and D. Sternad, 'Programmable pattern generators,' in Proc. Int. Conf. Comput. Intell. Neurosci. , 1998, pp. 48-51. -
Cited by
Items 101–200 of 220
Estimating the trajectory of a thrown object from video signal with use of genetic programming
Gayanov, R., Mironov, K., Mironov, K., & Kurennov, D. (2017) · IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) · doi:10.1109/isspit.2017.8388630 · Cited by 10
“73% in [9], 80% in [1,7], 84% in [22]).”
BackgroundData-driven learning and control of nonlinear system dynamics
Becerra, Y., & Acosta, J. Á. (2024) · Nonlinear Dynamics · doi:10.1007/s11071-024-10149-1 · Cited by 7
The role of early anticipations for human-robot ball catching
Carneiro, D., da Silva, F. M. T. P., & Georgieva, P. (2018) · IEEE International Conference on Autonomous Robot Systems and Competitions · doi:10.1109/icarsc.2018.8374153 · Cited by 7
“[2] presented a learning framework to teach a robot to catch fast objects with uneven shapes through the observation of demonstrations encoded by dynamical systems (DS).”
BackgroundYamamoto, K., Ito, H., Ichiwara, H., Hiroki, M. O. R. I., & Ogata, T. (2024) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii58957.2024.10417201 · Cited by 13
“) by programming-by-demonstration [12].”
RETRO: Reactive Trajectory Optimization for Real-Time Robot Motion Planning in Dynamic Environments
Dastider, A., Fang, H., & Lin, M. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610542 · Cited by 7
Catch It! Learning to Catch in Flight with Mobile Dexterous Hands
Zhang, Y., Liang, T., Chen, Z., Ze, Y., & Xu, H. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127596 · Cited by 39
“Some studies omit mobile platforms [4], [7], [18], [24], restricting the workspace to catch distant objects, while others lack dexterous hands [1], [8], limiting interaction with diverse objects.”
Motor-Primed Visual Attention for Humanoid Robots
Lukic, L., Billard, A., & Santos-Victor, J. (2015) · IEEE Transactions on Autonomous Mental Development · doi:10.1109/tamd.2015.2417353 · Cited by 7
Self-citationA Gaussian Mixture Models based Multi-RRTs method for high-dimensional path planning
Zhao, X., Zhao, H., Wan, S., et al. (2018) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2018.8665048 · Cited by 6
“GMM is widely used in learning for demonstration [14] or learning reachable space [15] [16].”
BackgroundWu, M., Yang, J., Zhang, X., et al. (2023) · ZAMM ‐ Journal of Applied Mathematics and Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik · doi:10.1002/zamm.202300383 · Cited by 6
“In recent years, with the rapid development of intelligent control technology, the application field of the robot has been more extensive, such as military tasks, manufacturing and daily life [1–3].”
BackgroundChoi, H. J., & Figueroa, N. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611601 · Cited by 13
“It has various applications, such as guiding mobile manipulators to adjust their legs or wheels [25], [26] and optimizing grasp poses for fixed manipulators [13], [14].”
BackgroundMethodHumanoid robot performing jump-and-hit motions using structure-integrated pneumatic cable cylinders
Tanaka, K., Nishikawa, S., Niiyama, R., et al. (2017) · doi:10.1109/humanoids.2017.8246948 · Cited by 6
Observing and Forecasting the Trajectory of the Thrown Body with use of Genetic Programming
Mironov, K., Gayanov, R., & Kurennov, D. (2019) · Advances in Science Technology and Engineering Systems Journal · doi:10.25046/aj040124 · Cited by 6
“These include the ones described in [1-4,7-11] as well as the system discussed in this section.”
BackgroundMethodPhase portraits as movement primitives for fast humanoid robot control
Maeda, G. J., Koç, O., & Morimoto, J. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.04.007 · Cited by 6
“[1, 2, 3, 4]), no conscious effort seems to be spent on either the ball prediction or the trajectory planning of the hands.”
BackgroundMethodVision-based Reinforcement learning: Moving object grasping with a Single Active-view Camera
Jang, S., Jeong, H., & Yang, H. (2022) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas55662.2022.10003899 · Cited by 5
“For the case of offline planning methods [22], by setting the dynamic model of system, grasping posture was predicted online from the trajectory of moving objects which was used to calculate the gripper’s trajectory for grasping [23, 24].”
MethodImpact-Friendly Object Catching at Non-Zero Velocity Based on Combined Optimization and Learning
Zhao, J., Lahr, G. J. G., Tassi, F., Santopaolo, A., Momi, E. D., & Ajoudani, A. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341600 · Cited by 9
“Activities such as throwing [1], hitting [2], juggling [3], and catching [4], [5] play an important role in various applications, including logistics and aerospace.”
BackgroundConfidence-Aware Object Capture for a Manipulator Subject to Floating-Base Disturbances
Xu, R., Jiang, Z., Liu, B., Wang, Y., & Qian, H. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3463476 · Cited by 10
Task-Oriented Dexterous Hand Pose Synthesis Using Differentiable Grasp Wrench Boundary Estimator
Chen, J., Chen, Y., Zhang, J., & Wang, H. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802652 · Cited by 32
“Non-prehensile manipulation encompasses various tasks, including pushing [32], catching [33], pivoting [34], and in-hand manipulation [35].”
BackgroundImplementation of Feeding Task via Learning from Demonstration
Ettehadi, N., & Behal, A. (2018) · IEEE International Conference on Robotic Computing (IRC) · doi:10.1109/irc.2018.00058 · Cited by 9
“While most PBD approaches focus mostly on learning merely the position trajectories, here, by adopting a novel approach from [12], the orientations are learned too as they are very important for the task of feeding, i.”
BackgroundInfluentialBuilding Skill Learning Systems for Robotics
Lutter, M., Clever, D., Kirsten, R., Listmann, K. D., & Peters, J. (2021) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case49439.2021.9551562 · Cited by 6
“For example ai might be options [10], [8], trajectories [16] or torques [2] while si might be images [9], [7], object locations [17], time [4], [6] or joint configuration [17].”
BackgroundRobot Anticipation Learning System for Ball Catching
Carneiro, D., da Silva, F. M. T. P., & Georgieva, P. (2021) · Robotics · doi:10.3390/robotics10040113 · Cited by 7
Sparse Gaussian processes for multi-step motion prediction of space tumbling objects
Yu, M., Luo, J., Wang, M., et al. (2022) · Advances in Space Research · doi:10.1016/j.asr.2022.09.015 · Cited by 5
ProSIP: Probabilistic Surface Interaction Primitives for Learning of Robotic Cleaning of Edges
Unger, C., Hartl-Nesic, C., Vu, M. N., & Kugi, A. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802255 · Cited by 13
“LfD has been applied to a variety of tasks ranging from assembly [2], [6] to dynamically catching a water bottle [7], [8].”
Continuous task-priority rearrangement during motion execution with a mixture of torque controllers
Dehio, N., Reinhart, F., & Steil, J. J. (2016) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2016.7803287 · Cited by 5
“Robots have recently become proficient in abilities such as efficient walking [1] or catching objects in flight [2].”
BackgroundKinematic Trajectory Planning for Dynamically Unconstrained Nonprehensile Joints
Schill, M. M., & BUSS, M. J. (2017) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2017.2788197 · Cited by 6
“Unlike grasping approaches [2], a generic nonprehensile end-effector provides a large potential contact area.”
BackgroundZhang, S., Dai, S., & Zhao, Y. (2021) · Engineering Optimization · doi:10.1080/0305215x.2021.1958210 · Cited by 5
“The continuous trajectory planning problem for robots, which is to replan the trajectory for robots in a high frequency according to the changes of obstacles and the objective in dynamic environments, is widely used in practice, such as playing ball games [1] and catching flying objects [2, 3].”
BackgroundMethodInfluentialCatching and Throwing Control of a Physically Simulated Hand
Luo, Y., Xie, K., Andrews, S., & Kry, P. G. (2021) · Motion in Games · doi:10.1145/3487983.3488300 · Cited by 5
“Related work by Kim et al. [2014] uses a Gaussian mixture model to plan grasping poses for catching.”
Aerial Interception of Non-Cooperative Intruder using Model Predictive Control
Srivastava, R., Lima, R., & Das, K. (2022) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc53348.2022.9867190 · Cited by 6
“[12], [13] presented approaches for catching fast flying objects using robotic arms by predicting their trajectories.”
BackgroundVFAS-Grasp: Closed Loop Grasping with Visual Feedback and Adaptive Sampling
Piacenza, P., Yuan, J., Huh, J., & Isler, V. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611183 · Cited by 6
“Other approaches such as [23], [24] and [25] requires prior knowledge of the object shape thus are more restricted for real-world applications.”
BackgroundIntention Inference for Human-Robot Collaboration in Assistive Robotics
Ravichandar, H. C., & Dani, A. (2017) · Human Modelling for Bio-Inspired Robotics · doi:10.1016/b978-0-12-803137-7.00007-0 · Cited by 5
Target dynamic grasping during mobile robot movement based on learning methods
Li, E., Feng, H., Zhai, Y., Zhou, H., Li, X., & Fu, Y. (2020) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir-01-2020-0005 · Cited by 5
Vision-guided Dynamic Object Grasping of Robotic Manipulators
Huang, J., Zhang, F., Dong, X., Yang, R., Xie, J., & Shang, W. (2020) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma49215.2020.9233783 · Cited by 6
“[12] [13] addressed the difficult problem of catching in-flight objects by learning dynamics of the robotic manipulator motion.”
BackgroundLiu, J., Jin, H., Yin, H., et al. (2024) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2024.3366218 · Cited by 4
Zhang, Y., Wang, R., & Chen, X. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3557746 · Cited by 13
Catching Objects with a Robot Arm using Model Predictive Control
Gold, T., Römer, R., Völz, A., & Graichen, K. (2022) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc53348.2022.9867380 · Cited by 10
“There also exist machine learning-based approaches for estimating the (possibly highly nonlinear) dynamics of complex objects like hammers or half-filled bottles [6], but since those methods are sensitive to the choice of the hyperparameters, a new setup often requires time-consuming tuning.”
BackgroundModular Neural Network Policies for Learning In-Flight Object Catching with a Robot Hand-Arm System
Hu, W., Acero, F., Triantafyllidis, E., Liu, Z., & Li, Z. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341463 · Cited by 10
“Encoding the arm and hand as Dynamical Systems (DS) [7] is one approach to catching tasks [5], [6], where kinematically feasible trajectories of the robot arm and hand are collected as demonstrations.”
BackgroundMethodInfluentialServo-based High-speed Alignment Software using EGM Interface
Qian, Y., & Dong, D. (2023) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio58561.2023.10354721 · Cited by 4
Chen, L., Lu, W., Zhang, K., Zhang, Y., Zhao, L., & Zheng, Y. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3416009 · Cited by 8
High-speed 3-D measurement of a moving object with visual servo
Shimada, K., Namiki, A., & Ishii, I. (2016) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2016.7844006 · Cited by 4
“In Kim’s research[2] and Salehian’s research[3], a robot arm caught flying objects of various forms, such as a plastic bottle, a tennis racket, and a brick, by estimating the trajectories via machine learning.”
BackgroundSaad, M., Shirazi, R. A., & Liaquat, M. (2018) · International Conference on Control, Mechatronics and Automation (ICCMA) · doi:10.1145/3284516.3284547 · Cited by 4
“[5] B. Xiao, S. Yin and O. Kaynak, "Tracking Control of Robotic Manipulators With Uncertain Kinematics and Dynamics", IEEE Transactions on Industrial Electronics, vol. 63, no. 10, pp. 6439-6449, 2016.”
BackgroundInfluentialOptimal Nonprehensile Interception Strategy for Objects in Flight
Zhou, C. Y., Long, Y., Cao, Y. S., Zhao, L., Huang, B., & Zheng, Y. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981714 · Cited by 4
“A new methodology was proposed to obtain the feasible catching configuration by a probability manner in [8].”
MethodAn fast reconstruction approach for actuator fault in robot manipulators
Xiao, B., & Yin, S. (2016) · International Workshop on Variable Structure Systems · doi:10.1109/vss.2016.7506955 · Cited by 4
“Many tasks such as object grasping [1], are autonomously accomplished by using one robot manipulator.”
BackgroundA Novel Robot Teaching System Based on Mixed Reality
Xu, Y., Yang, C., Liu, X., & Li, Z. (2018) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm.2018.8610861 · Cited by 4
“Using Monte Carlo algorithm to sample the joint angle, we can calculate the robot’s end position and posture by the kinematics [19].”
MethodRobust Nonlinear Model Predictive Control for Robot Manipulators with Disturbances
Yu, Y., Dai, L., Sun, Z., et al. (2018) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2018.8483122 · Cited by 3
“Robot manipulators have found applications in a great variety of fields, such as industrial autonomous manufacturing [1, 2], orbital missions [3] and surgery [4, 5].”
BackgroundTracking and Catching of an In-Flight Ring using a High-Speed Vision System and a Robot Arm
Liang, X., Zhu, H., Chen, Y., & Yamakawa, Y. (2021) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon48115.2021.9589565 · Cited by 4
“It requires the solution of three complex problems [1]: Firstly, make an accurate prediction of the trajectory of fast moving objects using the measured points.”
BackgroundRun and Catch: Dynamic Object-Catching of Quadrupedal Robots
You, Y., Liu, T., Liang, X., Xu, Z., Zhou, M., Li, Z., & Zhang, S. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341977 · Cited by 6
“Although there has been a long history of study on this task [1], [2], [3], [4], [5], only a handful of works have focused on legged robots.”
BackgroundDastider, A., Fang, H., & Lin, M. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802535 · Cited by 5
Srinivasan, A. R., & Chakraborty, S. (2016) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2016.7743527 · Cited by 3
“Also a recent work by Billard's group trained a manipulator both in simulation and in real-time to catch a flying object [10], [11].”
BackgroundHitting flying objects with learning from demonstration
Chen, J., Shen, S., & Lau, H. Y. K. (2017) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2017.8023496 · Cited by 4
“Secondly, the optimal catching pose for the robot needs to be derived [3].”
BackgroundLearning Motor Skills of Reactive Reaching and Grasping of Objects
Hu, W., Yang, C., Yuan, K., & Li, Z. (2021) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio54168.2021.9739420 · Cited by 3
“catching flying objects [10]; however, human demonstrations are required to learn such coupled motion-models and the graspable space of the objects.”
BackgroundEnd-Effector Trajectory Tracking Control of Space Robot with L2 Gain Performance
Zhang, H., Wang, D., Wei, C., & Xiao, B. (2015) · Mathematical Problems in Engineering · doi:10.1155/2015/175342 · Cited by 3
Observer-based control for robotic manipulations with uncertain kinematics and dynamics
Xiao, B., Yin, S., Kaynak, O., & Gao, H. (2016) · IEEE International Workshop on Advanced Motion Control (AMC) · doi:10.1109/amc.2016.7496364 · Cited by 5
“For instance, the problems of object grasping [1], fault detection and diagnosis [2, 3], and robotic manipulation in space for on-orbit servicing [4], have been extensively investigated.”
BackgroundCotugno, G., Konstantinova, J., Althoefer, K. A., & Nanayakkara, T. (2018) · PLoS ONE · doi:10.1371/journal.pone.0208228 · Cited by 3
“limit [14], is still considered a research topic.”
Augmenting Action Model Learning by Non-Geometric Features
Nematollahi, I., Kuhner, D., Welschehold, T., & Burgard, W. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794153 · Cited by 3
“In [10] Kim et al.”
Estimation and Control for Autonomous UAV System to Neutralize unknown Aerial Maneuvering Target
Srivastava, R., Lima, R., Shinde, C., Pushp, D., & Das, K. (2021) · Indian Control Conference · doi:10.1109/icc54714.2021.9703182 · Cited by 3
Controlling the Cascade: Kinematic Planning for N-ball Toss Juggling
Ploeger, K., & Peters, J. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981678 · Cited by 9
“To solve the more complex task of catching non-spherical objects, distributions over grasp positions and catching behaviors were learned from demonstrations [26].”
BackgroundXu, Y., & Feng, S. (2024) · International Journal on Interactive Design and Manufacturing (IJIDeM) · doi:10.1007/s12008-024-02080-x · Cited by 2
Bridging the latency gap with a continuous stream evaluation framework in event-driven perception
Chu, J., Zhang, R., Yang, C., Yu, Z., Bu, Z., Liu, H., Röhrbein, F., Knoll, A., Chen, G., & Jiang, C. (2026) · Nature Communications · doi:10.1038/s41467-026-70240-6 · Cited by 4
Mass Estimation of a Moving Object Through Minimal Manipulation Interaction
Aguilera, S., Murtaza, M. A., Zhao, Y., et al. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9560975 · Cited by 2
“edu irregular shaped objects [3], taking advantage of the shape of the object to come up with novel catching techniques [10], [17], or using highly dexterous grasping hands [16].”
BackgroundReal-time motion force-feedback system with predictive-vision for improving motor accuracy
Matsui, R., Aoyama, T., Kato, K. H., & Hasegawa, Y. (2024) · Scientific Reports · doi:10.1038/s41598-024-52811-z · Cited by 2
“Kim et al. developed a system that can even catch objects with a changing mass distribution by applying ”predictive-vision” to the objects and constantly updating the predicted flight trajectory 12 .”
BackgroundLearning to Catch Reactive Objects with a Behavior Predictor
Lü, K., Zhong, J.-X., Yang, B., Wang, B., & Markham, A. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611106 · Cited by 5
“In the tasks of catching a flying ball [7], [12], [13], [23], [24] or tool [11], high-speed external cameras [23], [24] or optical tracking systems [7] are often used to capture the object and fit it into a ballistic trajectory.”
MethodChen, L., Qiu, J., Li, L., Luo, X., Chi, G., & Zheng, Y. (2024) · The International Journal of Robotics Research · doi:10.1177/02783649241275674 · Cited by 2
DexDribbler: Learning Dexterous Soccer Manipulation via Dynamic Supervision
Hu, Y., Wen, K., & Yu, F. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802022 · Cited by 8
“Successful demonstrations are showcased on a variety of robotics platforms ranging from robotic arms [12], legged robots [13] to drones [11].”
Ball Trajectory Estimation and Robot Control to Reach the Ball Using Single Camera
Nobahar, B., Shoaran, M., & Karimian, G. (2020) · Journal of Control · doi:10.29252/joc.14.3.75 · Cited by 2
A Surprisingly Efficient Representation for Multi-Finger Grasping
Yan, H., Fang, H.-S., & Lu, C. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611424 · Cited by 4
“In dynamic scenes, previous works predominantly use a fixed trajectory or select the nearest pose at two adjacent moments as the tracking pose [34, 35, 36, 37, 38].”
MethodLearning Optimized Human Motion via Phase Space Analysis
Gesel, P., Mikulis-Borsoi, F. A. S., LaRoche, D. P., Arthanat, S., & Begum, M. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340773 · Cited by 2
“edu Dynamic system based approaches benefit from quick reaction time by mapping the robot’s state to actions [18].”
BackgroundHybrid modeling: Applications in real-time diagnosisPreprint
Matei, I., de Kleer, J., Feldman, A., Rai, R., & Chowdhury, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.02671 · Cited by 6
“A set of recent results [1], [10], [27], [28], [42] have the same high level objective as in our case: to build hybrid models that are more accurate and generalizable.”
BackgroundResultHybrid Multi-camera Visual Servoing to Moving Target
Cuevas-Velasquez, H., Li, N., Tyleček, R., Saval-Calvo, M., & Fisher, R. B. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593652 · Cited by 25
“However, in [8] statistically and dynamically unbalanced objects (half full bottles or a racket) are used, hence they readjust the near future predicted target position iteratively.”
BackgroundDual-Arm Dynamic Planning with Considering Arm Reachability Constraint in Task Space
Shu, X., Fan, X., Min, K., Ji, Z., Ni, F., & Liu, H. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-6489-5_21 · Cited by 1
Dynamic Object Catching with Quadruped Robot Front Legs
Schakkal, A., Bellegarda, G., & Ijspeert, A. J. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801922 · Cited by 7
“Alternatively, Gaussian Mixture Models (GMMs) offer a probabilistic approach, allowing the selection of the catching point based on the highest likelihood within the constraints of the optimization problem [26].”
InfluentialTassi, F., Zhao, J., Lahr, G. J. G., Gava, L., Monforte, M., Glover, A., Bartolozzi, C., & Ajoudani, A. (2025) · The International Journal of Robotics Research · doi:10.1177/02783649251345851 · Cited by 6
“Activities such as throwing (Zeng et al. 2020), hitting (Hattori et al. 2020), jug-gling (Tanaka et al. 2021), and catching (Kim et al. 2014; Salehian et al. 2016) are only some of the applications that characterize multiple fields, ranging from logistics to aerospace.”
Robotic gripper for dynamic capture using passive variable stiffness and damping regulator (P-VSDR)
Yang, S., Song, Z., Branson, D. T., Sun, T., Dai, J. S., & Kang, R. (2025) · Robotica · doi:10.1017/s0263574725102105 · Cited by 1
Yan, L., Zhou, B., Zheng, Z., et al. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3632077 · Cited by 1
Yan, L., Zheng, Z., Zhou, B., et al. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3632606 · Cited by 1
Fan, J., Xu, H., Ma, H., et al. (2026) · Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science · doi:10.1177/09544062251406970 · Cited by 1
“26,27 Reward: The ball catching reward is where O pad is the dot product between the normalized z-axis coordinate of the pad and the z-axis unit vector, helping the pad stay horizontal, p pad is the current position of the pad, p tar is the target hitting position derived from the ball’s initial…”
An exploration of 3D spatial training in teams with a remotely controlled robotic system
Reychav, I., Wu, D., Shvalb, N., et al. (2014) · International Journal of Learning Technology · doi:10.1504/ijlt.2014.067736 · Cited by 1
“For example, while controlling a robotic arm, there are several task-related parameters that need to be considered simultaneously (Kim et al., 2014).”
BackgroundChen, J., & Lau, H. Y. K. (2016) · IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO) · doi:10.1109/arso.2016.7736287 · Cited by 1
“With this method, the behavior is modeled with a set of differential equations and global stability at the target is ensured through a linear dynamical system.”
MethodAutomate robot reaching task with learning from demonstration
Chen, J., Ren, H., & Lau, H. Y. K. (2017) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2017.8023663 · Cited by 1
Real-time kinematical optimal trajectory planning for haptic feedback manipulators
Zhang, S., & Dai, S. (2019) · SIMULATION · doi:10.1177/0037549718815755 · Cited by 1
Dynamic Problem Solving in Space
Freksa, C., Vasardani, M., & Kroll, F. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-57983-8_2 · Cited by 1
Visual Servoing of manipulator with moving base
Ma, X., Lyu, S., Qiao, J., et al. (2022) · International Symposium on Autonomous Systems (ISAS) · doi:10.1109/isas55863.2022.9757313 · Cited by 1
“Support Vector Regression (SVR) method is adopted to predict the horizontal movements of the base due to its advantages of good fitting and simple operations [8] [9] [10].”
MethodArif, T. M., McKay, S., & Conklin, B. (2022) · ASME Letters in Dynamic Systems and Control · doi:10.1115/1.4055837 · Cited by 1
Determining predictable strike points on tossed objects: A 2D physics simulation approach
Giladi, C., & Golan, Y. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107268 · Cited by 1
A Unified Trajectory Generation Algorithm for Dynamic Dexterous Manipulation
Zhou, C. Y., Gao, W., Lü, W., et al. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10342095 · Cited by 1
“The studies reviewed above show that dynamic dexterous manipulation tasks were studied separately so far [6], [9], [13], [14].”
BackgroundUltrafast capturing in-flight objects with reprogrammable working speed ranges
Jiang, Y., Tong, X., Sun, Z., Zhou, Y., Wang, Z., Jiang, S., Yin, Z., Ding, Y., He, B., & Li, Y. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610901 · Cited by 1
“Most of current works focus on the precise trajectory prediction of the fast-moving objects based on advanced algorithms or machine learning approaches, and then put the grippers or hands in the right place for fast grasping [9-15].”
BackgroundZhang, S., Sun, D. M., & Liao, Q. (2024) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2024.3477006 · Cited by 1
Trajectory Prediction Method of Flying Uneven Object Based on Improved Informer
Wang, Z., Huang, Y., & Zhang, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-0774-7_17 · Cited by 1
Humanoid Kinematics and Dynamics: Open Questions and Future Directions
Gienger, M., & Steil, J. J. (2017) · Springer eBooks · doi:10.1007/978-94-007-7194-9_8-1 · Cited by 1
A Generative Neural Network for Learning Coordinated Reach-Grasp Motions
Chong, E., Park, J., Kim, H., & Park, F. C. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2917381 · Cited by 2
“In [11] and [12], movements of the hand and arm are coupled via coupled dynamical systems, using Gaussian mixture models to encode human demonstrations.”
BackgroundMethodBlind Brains and Moral Machines: Neuroscience and Autonomous Weapon Systems
Evans, N. G. (2021) · Oxford University Press eBooks · doi:10.1093/oso/9780197546048.003.0014 · Cited by 1
Using Tactile Sensing to Improve Performance when Grasping Moving Objects
Lynch, P., & McGinn, C. (2021) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc52423.2021.9658609 · Cited by 1
“catching a flying object [8], [9], and the ability to grasp irregularly shaped moving objects [5].”
BackgroundResearch on Motion Control of Mobile Manipulator for Dynamic Target Grasping
Zhan, W., Li, L., & Wang, C. (2022) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma54519.2022.9855960 · Cited by 1
“This method can realize rapid identification of target objects, but the model requires a lot of offline training to achieve good results, which is time-consuming and labor-intensive; the team of Tan Yuanjie of Shanghai Jiaotong University [4] studied the items on the conveyor belt in the smart factory For the transfer…”
MethodDexterous robotic manipulation: Batting and cutting
Mu, X. (2021) · doi:10.31274/td-20240329-239 · Cited by 1
A Hybrid Robust Lyapunov Controller for Dynamic Catch, Grasp and Carry Maneuvers
Yunt, K. (2015) · Journal of Dynamic Systems Measurement and Control · doi:10.1115/1.4030285
Kaipa, K. N., Langsfeld, J. D., & Gupta, S. K. (2014) · Mechanical Engineering · doi:10.1115/9.2014-sep-2
Action Generation Adapted to Low-Level and High-Level Robot-Object Interaction States
Maestre, C., Mukhtar, G., Gonzales, C., & Doncieux, S. (2019) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2019.00056
“, 2007, 2010, 2011) do not generate stable actions, but it has been solved in posterior studies by a method called Stable Estimator of Dynamical Systems (SEDS) (Khansari-Zadeh and Billard, 2011, 2014; Kim et al., 2014), which ensures stability through a computation of Lyapunov candidates (Slotine and Li, 1991).”
InfluentialVisual Reaction: Learning to Play Catch with Your DronePreprint
Zeng, K.-H., Mottaghi, R., Weihs, L., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.02155
“[20] consider the problem of catching in-flight objects with uneven shapes.”
BackgroundPhase Portraits as Movement Primitives for Fast Humanoid Robot ControlPreprint
Maeda, G. J., Koç, O., & Morimoto, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.03535
“[1, 2, 3, 4]), no conscious effort seems to be spent on either the ball prediction or the trajectory planning of the hands.”
BackgroundMethodCatch the Ball: Accurate High-Speed Motions for Mobile Manipulators via Inverse Dynamics LearningPreprint
Dong, K., Pereida, K., Shkurti, F., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.07489
“Similar simplifications are also made in the ball catching literature and work well in experiments [1], [2], [9], [22].”
ResultTactile-sensing apparatus for sensible catching of guided heavy masses
Schmidt, M., Müller, V., Althaus, H., & Elkmann, N. (2020) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa46521.2020.9212108
“They range from abstract structures as shown in [10], which uses oppositely placed rackets to throw and catch a ball, to a radial movable plate [6], to even complex robotic arms or robots [1, 2].”
Metadata
- Authors
- Kim, S., Shukla, A., & Billard, A.
- Affiliations
- École Polytechnique Fédérale de Lausanne (CH)
- ORCID
- Billard, Aude
- Venue
- IEEE Transactions on Robotics
- Published
- 2014-10
- Volume
- 30
- Issue
- 5
- Pages
- 1049-1065
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W2018020788
- Cited by
- 220
- References
- 52
- Citations by year
- 2026: 8 · 2025: 14 · 2024: 27 · 2023: 19 · 2022: 20 · 2021: 29 · 2020: 20 · 2019: 12 · 2018: 23 · 2017: 17 · 2016: 18 · 2015: 10 · 2014: 3
- FWCI
- 17.81
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- IEEE Transactions on Robotics (publishedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Funders
- EU Projects AMARSI (FP7-ICT-248311)
- FirstMM (FP7-248258)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Motor Control and Adaptation
- Keywords
- trajectory prediction, programming by demonstration, dynamical systems, sensor uncertainty, humanoid robots, robot manipulators, iCub
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.