Reactive Nonholonomic Trajectory Generation via Parametric Optimal Control

By Alonzo James Kelly, B. Nagy. Int. J. Robotics Res., 2003

303 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/bf75144fa7ab13b04411a1413e376add909d7e98

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

Toward Reliable Off Road Autonomous Vehicles Operating in Challenging Environments (2006, methodology): “The space of robot poses (x,y,heading) is discretized into a dense 3D grid and the trajectory generator described in [7] is used to connect every node to every reachable neighboring node out to some practical radius.”
Planning algorithms (2006, methodology): “There is also interest in nonoptimal curves that nevertheless have good properties, especially for use as a local planning method for car-like robots [31, 360, 523, 797, 850].”
Optimal trajectory generation for dynamic street scenarios in a Frenét Frame (2010, methodology): “[16], [1], [7]): A finite set of trajectories is computed, typically by forward integration of the differential equations that describe vehicle dynamics.”
Efficient Constrained Path Planning via Search in State Lattices (2005, methodology): “Since in our case we are mostly interested in generating paths in C-space, the method described in (3) lent itself very well for our purpose.”
Differentially constrained mobile robot motion planning in state lattices (2009, methodology): “A trajectory generator in Kelly and Nagy (2002) was used to generate the motions between the given values of robot state.”
Optimal Rough Terrain Trajectory Generation for Wheeled Mobile Robots (2007, methodology): “As in Kelly and Nagy (2003), this is accomplished using the method of Lagrange multipliers The Hamiltonian (H) is defined as the sum of the cost function and the product of the Lagrange multiplier vector (λ) with the constraints: H (p, λ)=J (p)+λT xf (p)=J (p)+λT ( xf −x ( tf )) .”
Motion planning for autonomous driving with a conformal spatiotemporal lattice (2011, methodology): “We compute paths between vertices in our conformed lattice using the iterative numerical method of [6], also used by the Tartan Racing team[1][4] in the 2007 DARPA Urban Challenge.”
A multirange architecture for collision‐free off‐road robot navigation (2009, background): “(Kelly and Nagy, 2003) points out the need for a parametric trajectory representation in contrast to the prohibitively large space required by pre-storing methods.”