Deep Local Trajectory Replanning and Control for Robot Navigation

We present a navigation system that combines ideas from hierarchical planning and machine learning. The system uses a traditional global planner to compute optimal paths towards a goal, and a deep local trajectory planner and velocity controller to compute motion commands. The latter components of t...

Full description

Saved in:
Bibliographic Details
Main Authors: Pokle, Ashwini, Martin-Martin, Roberto, Goebel, Patrick, Chow, Vincent, Ewald, Hans M., Yang, Junwei, Wang, Zhenkai, Sadeghian, Amir, Sadigh, Dorsa, Savarese, Silvio, Vazquez, Marynel
Format: Conference Proceeding
Language:English
Subjects:
Laser radar
Navigation
Planning
Robot kinematics
Robot sensing systems
Trajectory
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a navigation system that combines ideas from hierarchical planning and machine learning. The system uses a traditional global planner to compute optimal paths towards a goal, and a deep local trajectory planner and velocity controller to compute motion commands. The latter components of the system adjust the behavior of the robot through attention mechanisms such that it moves towards the goal, avoids obstacles, and respects the space of nearby pedestrians. Both the structure of the proposed deep models and the use of attention mechanisms make the system's execution interpretable. Our simulation experiments suggest that the proposed architecture outperforms baselines that try to map global plan information and sensor data directly to velocity commands. In comparison to a hand-designed traditional navigation system, the proposed approach showed more consistent performance.
ISSN:2577-087X
DOI:10.1109/ICRA.2019.8794062