Using interpolation to improve path planning: The Field D* algorithm

By D. Ferguson, Anthony Stentz. J. Field Robotics, 2006

435 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Networks and Communications, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d8267119e6e69c528bc7bee010acfb41c9efd861

How researchers see this paper

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

In Computer Graphics and Computer-Aided Design

1. Nathan D. Ratliff
2. J. Bagnell
3. David Silver
4. Peter Stone
5. Bo Liu
6. Xuesu Xiao
7. Sven Koenig
8. Kenny Daniel

In Computer Networks and Communications

1. Anthony Stentz
2. Nathan D. Ratliff
3. J. Bagnell
4. David Silver
5. Peter Stone
6. Bo Liu
7. Xuesu Xiao
8. Sven Koenig

In Computer Vision and Pattern Recognition

1. J. Bagnell
2. Nathan D. Ratliff
3. Anthony Stentz
4. Peter Stone
5. David Silver
6. Bo Liu
7. Sven Koenig
8. Dmitry S. Yershov

Citations in the corpus

• Learning from Demonstration for Autonomous Navigation in Complex Unstructured Terrain (2010, methodology): “Owing to the dynamic nature of this cost data, the Field D* algorithm is utilized (Ferguson and Stentz 2006).”
• A Review of Motion Planning Techniques for Automated Vehicles (2016, background): “Several applications in mobile robotics have used as basis for improvement, such as the dynamic A∗ (D∗) [31], Field D∗ [32], Theta∗ [33], Anytime repairing A∗ (ARA∗) and Anytime D∗ (AD∗) [34], among others.”
• A Survey of Motion Planning and Control Techniques for Self-Driving Urban Vehicles (2016, methodology): “In addition, Field D* introduces linear-interpolation to the search procedure to produce smooth paths [123].”
• Theta*: Any-Angle Path Planning on Grids (2007, methodology): “The authors of FD* recognize this problem and suggest to use a one-step lookahead method during path extraction (Ferguson & Stentz 2006).”
• A Lifelong Learning Approach to Mobile Robot Navigation (2021, positive): “Dijkstra’s algorithm [33], A* [34] or D* [35]) generates a path connecting start and goal, and while navigating, the robot needs to produce motion commands which follow this global path, observe its kinodynamic constraints, and avoid obstacles.”
• Path Planning for the Mobile Robot: A Review (2018, background): “In addition, some scholars have researched the D* algorithm such as the field D* algorithm [20] and Theta* algorithm [21,22].”
• Lifelong Navigation (2020, neutral): “Dijkstra’s algorithm [30], A* [31] or D* [32]) generates a path connecting start and goal, and while navigating, the robot needs to produce motion commands which follow this global path, observe its kinodynamic constraints, and avoid obstacles.”
• Path Planning for Autonomous Underwater Vehicles (2007, methodology): “The Field D* algorithm [2] is another approach, which is close to the FM* algorithm in the sense that it is an interpolated version of the D* algorithm (described in [3]) to the continuous domain.”
• Real-Time Perception Meets Reactive Motion Generation (2017, neutral): “, [1], [2], [18], [19].”
• Learning to search: Functional gradient techniques for imitation learning (2009, methodology): “For example the interpolated A* algorithm ( Ferguson and Stentz 2006 ) used in Sect.”
• High Performance Outdoor Navigation from Overhead Data using Imitation Learning (2008, methodology): “Due to the dynamic nature of this fused cost map, the Field D* [11] algorithm is used for real-time global planning.”