1. |
|
|
2. |
|
|
3. |
|
|
4. |
|
|
5. |
|
|
6. |
|
|
7. |
|
|
8. |
- Grover, Kush, et al.
(author)
-
Semantic Abstraction-Guided Motion Planningfor scLTL Missions in Unknown Environments
- 2021
-
In: Robotics: Science and Systems. - : RSS FOUNDATION-ROBOTICS SCIENCE & SYSTEMS FOUNDATION.
-
Conference paper (peer-reviewed)abstract
- Complex mission specifications can be often specifiedthrough temporal logics, such as Linear Temporal Logic and itssyntactically co-safe fragment, scLTL. Finding trajectories thatsatisfy such specifications becomes hard if the robot is to fulfilthe mission in an initially unknown environment, where neitherlocations of regions or objects of interest in the environmentnor the obstacle space are known a priori. We propose an algorithmthat, while exploring the environment, learns importantsemantic dependencies in the form of a semantic abstraction,and uses it to bias the growth of an Rapidly-exploring randomgraph towards faster mission completion. Our approach leadsto finding trajectories that are much shorter than those foundby the sequential approach, which first explores and then plans.Simulations comparing our solution to the sequential approach,carried out in 100 randomized office-like environments, showmore than 50% reduction in the trajectory length.
|
|
9. |
|
|
10. |
|
|
11. |
|
|
12. |
|
|