Towards Automatic State Recovery for Replanning
Authors/Creators
- 1. Institute of Mechanism Theory, Machine Dynamics and Robotics, RWTH Aachen University
- 2. Department of Informatics, King's College London
Description
Integrated planning and execution on embodied agents necessarily means dealing with execution failures, and it is common to employ on-board replanning to overcome such failures. However, describing the activities of the agent as action definitions appropriate for planning often requires a discrete abstraction of continuous state. As a result, action failure can result in “improper” planning states that are inconsistent with the ground truth. Attempting to generate a plan in these states can result in planning failure, even in cases where the executive actually has the capability to reach the goal. In this paper, we formalize the concept of proper states, the mappings between planning states and underlying execution structures, and lay the grounds towards developing automatic recovery behaviors when execution failures leave the execution in an artificially incorrect planning state.
Files
planning_state_recovery_IntExWS_ICAPS2022.pdf
Files
(483.8 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:53be54d6d011f7a6effcd6157fe985dd
|
483.8 kB | Preview Download |