Smoothness maximization along a predefined path accurately predicts the speed profiles of complex arm movements.

By E. Todorov, Michael I. Jordan. 1998

How researchers see this paper

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

Citations in the corpus

The Dynamics of Legged Locomotion: Models, Analyses, and Challenges (2006, background): “generation whose cost functionals can be shown to generate signals that respect such power laws [319, 272].”
Three-dimensional arm movements at constant equi-affine speed. (2009, unknown): “However, deviations from piecewise-planar drawing in 3D have been observed (Gusis, 1995), and indeed this hypothesis does not seem to be supported by a more recent study involving 3D shape tracing hand movements (Todorov and Jordan, 1998).”
Action and behavior: a free-energy formulation (2010, background): “Todorov and Jordan 1998; Nakano et al. 1999; Berret et al. 2008).”
DexMV: Imitation Learning for Dexterous Manipulation from Human Videos (2021, methodology): “To generate the action for state-action demonstrations, we first fit the hand pose sequence with min-jerk cubic spline model [81] for time parameterization.”
Geometrical Invariance and Smoothness Maximization for Task-Space Movement Generation (2016, methodology): “For path-constrained jerk minimization [4], we proved that any optimal solution must satisfy a Euclidean constraint, namely, that the sixth-order time derivative is perpendicular to the tangent to the curve (12).”
Segmenting sign language into motor primitives with Bayesian binning (2013, methodology): “, snap, crackle and so on (Flash and Hogan, 1985; Todorov and Jordan, 1998).”
Models of human movement: Trajectory planning and inverse kinematics studies (2013, unknown): “The constrained minimum-jerk model aimed to explain the preferred kinematics of the hand while tracing a predefined path [20,29].”
Movement Smoothness Changes during Stroke Recovery (2002, methodology): “Smoothness in the minimum-jerk sense has been used to identify presymptomatic individuals with Huntington’s disease (Smith et al., 2000) and has also been shown to account for the two-thirds power law, widely considered an invariant in human movement (Wann et al., 1988; Gribble and Ostry, 1996; Tod”
Keyframe-based Learning from Demonstration (2012, methodology): “Another approach is to optimize the minimum jerk cost with respect to the velocities and accelerations given durations and positions, as done in [26].”
Movement Timing and Invariance Arise from Several Geometries (2009, methodology): “Similarly, when the path is fully prescribed, the constrained minimum jerk model successfully predicts the velocities along such paths [44,50].”
Optimal feedback control as a theory of motor coordination (2002, unknown): “, because certain empirical results—most notably the smoothnes”