title | abstract | keywords | layout | series | id | month | tex_title | firstpage | lastpage | page | order | cycles | bibtex_author | author | date | address | publisher | container-title | volume | genre | issued | extras | ||||||||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Learning over Subgoals for Efficient Navigation of Structured, Unknown Environments |
We propose a novel technique for efficiently navigating unknown environments over long horizons by learning to predict properties of unknown space. We generate a dynamic action set defined by the current map, factor the Bellman Equation in terms of these actions, and estimate terms, such as the probability that navigating beyond a particular subgoal will lead to a dead-end, that are otherwise difficult to compute. Simulated agents navigating with our Learned Subgoal Planner in real-world floor plans demonstrate a 21% expected decrease in cost-to-go compared to standard optimistic planning techniques that rely on Dijkstra’s algorithm, and real-world agents show promising navigation performance as well. |
Navigation, POMDP, Deep Learning |
inproceedings |
Proceedings of Machine Learning Research |
stein18a |
0 |
Learning over Subgoals for Efficient Navigation of Structured, Unknown Environments |
213 |
222 |
213-222 |
213 |
false |
Stein, Gregory J. and Bradley, Christopher and Roy, Nicholas |
|
2018-10-23 |
PMLR |
Proceedings of The 2nd Conference on Robot Learning |
87 |
inproceedings |
|
|