Apprenticeship learning for motion planning, with application to parking lot navigation

Pieter Abbeel, Dmitri Dolgov, Andrew Ng, and Sebastian Thrun

In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-08). September 2008.

Abstract
Motion and path-planning algorithms often use complex cost functions for both global navigation and local smoothing of trajectories. Obtaining good results typically requires carefully hand-engineering the trade-offs between different terms in the cost function. In practice, it is often much easier to demonstrate a few good trajectories. In this paper, we describe an efficient algorithm which---when given access to a few trajectory demonstrations---can automatically infer good trade-offs between the different costs. In our experiments, we apply our algorithm to the problem of navigating a robotic car in a parking lot.


BibTex
@inproceedings{ abbeel08invrlIROS,
   paperID   = "IROS-08",
   month     = "September",
   author    = "Pieter Abbeel and Dmitri Dolgov and Andrew Ng and Sebastian Thrun",
   booktitle = "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-08)",
   address   = "Nice, France",
   title     = "Apprenticeship learning for motion planning, with application to parking lot navigation",
   publisher = "IEEE",
   year      = "2008"
}


Download:
pdf [pdf]        ps [ps.gz]