9 October 2018: Till Hofmann

Despite promising advances in planning and reasoning systems, they only see little use in actual robotic environments. One reason is that solving a planning task or defining an abstract agent program is not sufficient to accomplish high-level behavior control of a robot. To execute such a plan on a robot, additional constraints of the robot platform (i.e., its hardware and low-level software components) need to be considered, which are typically ignored in the high-level behavior control.

In this talk, I sketch a framework that transforms an abstract plan into an action sequence that is executable on a robot. For this purpose, we specify a model of the robot's components and define constraints on that platform in a variant of the Situation Calculus. Based on the platform model and constraints, an abstract plan (e.g., a Golog program or a PDDL plan) is augmented with platform-specific actions that make sure that the platform constraints are satisfied.

After sketching the general idea of the framework, I will focus on an extension to a modal variant of the Situation Calculus that allows temporal reasoning with metric time. Finally, I will outline how a probabilistic extension may be useful to model non-deterministic aspects of a real-world robot.

Oct 09 2018 -

9 October 2018: Till Hofmann

Constraint-Based Online Transformation of Abstract Plans into Executable Robot Actions

IF 4.31/4.33