Optimal Rough Terrain Trajectory Generation for Wheeled Mobile Robots

By Thomas M. Howard, Alonzo James Kelly. Int. J. Robotics Res., 2007

417 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/0515b1803656762dcad0ad66097578e810d7d5dd

How researchers see this paper

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

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

A unified approach to local trajectory planning and control for autonomous driving along a reference path (2014, methodology): “Howard and Kelly present a model predictive trajectory generation planner, which achieves a high degree of generality and efficiency for generating dynamically feasible trajectories in rough terrain environments by using the model reversion techniques and the parametric control model [10].”
Autonomous driving in urban environments: Boss and the Urban Challenge (2008, methodology): “A model-predictive trajectory generator originally presented in Howard and Kelly (2007) is responsible for generating dynamically feasible actions from an initial state x to a desired terminal state.”
Sampling-Based Robot Motion Planning: A Review (2014, methodology): “Control based methods require formulating accurate models for the robot and the environment [46], [47], which can be a rather daunting task.”
Real-Time Motion Planning With Applications to Autonomous Urban Driving (2009, background): “The existing randomized planning algorithms solve for the input to the vehicle either by sampling an input itself or by sampling a configuration and reverse calculating , typically with a lookup table [9], [10], [12]–[14].”
Planning Long Dynamically Feasible Maneuvers for Autonomous Vehicles (2008, methodology): “To generate the feasible actions we use a trajectory generation algorithm originally developed by Howard and Kelly [9].”
Team Cornell's Skynet: Robust perception and planning in an urban environment (2008, methodology): “A model-predictive trajectory generator originally presented in Howard and Kelly (2007) is responsible for generating dynamically feasible actions from an initial state x to a desired terminal state.”
A Review of Motion Planning Techniques for Automated Vehicles (2016, background): “Howard and Kelly applied state lattices in rough terrains for a wheeled mobile robot [49], where simulations give promising”
Differentially constrained mobile robot motion planning in state lattices (2009, methodology): “• Inverse: A desired state sampling can be chosen first, and boundary value problem solvers can be used to find the feasible motions (steering functions) that drive the system from one state value to another (e.g., Howard & Kelly, 2007; Kelly & Nagy, 2002).”
Motion planning in urban environments (2008, methodology): “Each candidate trajectory is computed using a modelpredictive trajectory generator from Howard and Kelly (2007) that produces dynamically feasible actions between initial and desired vehicle states.”
Self-Driving Cars: A Survey (2019, background): “dle of the driving corridor at a specified velocity, penalize strong acceleration, dampen rapid changes in acceleration, and attenuate high yaw rates. Model predictive methods for trajectory planning [HOW07] produce dynamically feasible control commands between car’s current state and next goal stat”
End-to-end dexterous manipulation with deliberate interactive estimation (2012, methodology): “Our approach extends state-space sampling techniques [25] for robotic torsos by solving for parameterized actions that satisfy intermediate and terminal joint constraints using the technique described in [26].”