Construction and optimal search of interpolated motion graphs

By Alla Safonova, Jessica K. Hodgins. ACM Transactions on Graphics, 2007

336 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/f218856694d2f834c1180d9286efa8d7c54f0287

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

An Invitation to Imitation (2015, background): “[Safonova and Hodgins, 2007 , Mülling et al., 2013 ], show that a library of trajectories can indeed be made to generalize very broadly through clever arbitration and blending.”
Manipulators and Manipulation in high dimensional spaces (2016, methodology): “While the focus has always been on full body movements, motion capture techniques have been used for hand movement synthesis [119] [87].”
Real-time behaviour synthesis for dynamic hand-manipulation (2014, methodology): “While the focus has always been on full body movements, motion capture techniques have been used for hand movement synthesis [14] [15].”
Action-Reaction: Forecasting the Dynamics of Human Interaction (2014, background): “Furthermore, there are actually many redundant actions for similar states that can be removed [23].”
Synthesizing object receiving motions of humanoid robots with human motion database (2013, methodology): “Previous work on motion graphs involved an optimization process that maps intuitive user inputs, such as walk paths [2] and start and goal configurations [3], to the character motion that best matches the input.”
DeepMimic (2018, background): “Given a dataset of motion clips, controllers can be built to select the appropriate clip to play in a given situation, e.g., [Agrawal and van de Panne 2016; Lee et al. 2010b; Safonova and Hodgins 2007].”
Neural state machine for character-scene interactions (2019, methodology): “Methods based on probabilistic roadmaps [Choi et al. 2003], rapidly exploring random trees [Choi et al. 2011], A* search [Safonova and Hodgins 2007] reinforcement learning [Lo et al. 2012; Lo and Zwicker 2008] and Maximum A Posteriori (MAP) estimation [Min and Chai 2012], local optimization…”
AMP (2021, background): “Given a motion dataset, controllers can be constructed to select an appropriate motion clip to play back for a particular scenario [Agrawal and van de Panne 2016; Safonova and Hodgins 2007; Treuille et al. 2007].”
Mode-adaptive neural networks for quadruped motion control (2018, background): “…2012; Safonova et al. 2004; Tautges et al. 2011], radial basis functions (RBF) [Kovar and Gleicher 2004; Rose et al. 1998], reinforcement learning [Safonova and Hodgins 2007] and Gaussian processes (GP) [Grochow et al. 2004; Ikemoto et al. 2009; Mukai and Kuriyama 2005] are studies to achieve…”
Robust motion in-betweening (2020, methodology): “Safonova and Hodgins [Safonova and Hodgins 2007] combine an interpolated motion graph to an anytime 𝐴 ∗ search algorithm in order produce transitions that respect some constraints.”