Download:
by Ru Cocora, Kristian Kersting, Christian Plagemann, Wolfram Burgard, Luc De Raedt
Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS
http://www.informatik.uni-freiburg.de/~plagem/bib/cocora06iros.pdf
Add To MetaCart
Abstract:
Abstract — Navigation is one of the fundamental tasks for a mobile robot. The majority of path planning approaches has been designed to entirely solve the given problem from scratch given the current and goal configurations of the robot. Although these approaches yield highly efficient plans, the computed policies typically do not transfer to other, similar tasks. We propose to learn relational decision trees as abstract navigation strategies from example paths. Relational abstraction has several interesting and important properties. First, it allows a mobile robot to generalize navigation plans from specific examples provided by users or exploration. Second, the navigation policy learned in one environment can be transferred to unknown environments. In several experiments with real robots in a real environment and in simulated runs, we demonstrate the usefulness of our approach. I.
Citations
|
3215
|
C4.5: Programs for Machine Learning
– Quinlan
- 1993
|
|
1673
|
Reinforcement learning: An introduction
– Sutton, Barto
- 1998
|
|
1560
|
Robot Motion Planning
– Latombe
- 1991
|
|
1397
|
Dynamic Programming
– Bellman
- 1957
|
|
345
|
Inductive logic programming : Theory and methods
– Muggleton, Raedt
- 1994
|
|
293
|
Real-time heuristic search
– Korf
- 1990
|
|
149
|
Explanation-based learning: A problem solving perspective
– Minton, Carbonell, et al.
- 1989
|
|
126
|
The focussed D* algorithm for real-time replanning
– Stentz
- 1995
|
|
121
|
Planning Algorithms
– LaValle
- 2006
|
|
100
|
SPUDD: Stochastic planning using decision diagrams
– Hoey, St-Aubin, et al.
- 1999
|
|
90
|
Raedt. Top-down induction of first order logical decision trees
– Blockeel, De
- 1998
|
|
76
|
Symbolic dynamic programming for first-order MDPs
– Boutilier, Reiter, et al.
- 2001
|
|
68
|
A robot navigation architecture based on partially observable markov decision process models
– Koenig, Simmons
|
|
60
|
Principles of Robot Motion: Theory, Algorithms, and Implementations
– Choset, Lynch, et al.
- 2005
|
|
42
|
Explanation-based learning: A survey of programs and perspectives
– Ellman
- 1989
|
|
34
|
Explanation-based learning and reinforcement learning: A unified view
– Dietterich, Flann
- 1997
|
|
33
|
Relational reinforcement learning
– Dˇzeroski, Raedt, et al.
- 1998
|
|
22
|
Agent-centered search
– Koenig
- 2001
|
|
19
|
Learning procedural knowledge through observation
– Lent, Laird
- 2001
|
|
16
|
Supervised learning of places from range data using adaboost
– Mozos, Stachniss, et al.
|
|
16
|
Bellman goes relational
– Kersting, Otterlo, et al.
- 2004
|
|
10
|
Place classification of indoor environments with mobile robots using boosting
– Rottmann, Mozos, et al.
- 2005
|
|
1
|
Solving Relational MDPs with First-Order
– Mausam, Weld
- 2003
|
