— One of the most notable and recognizable features of robot motion is the abrupt transitions between actions in action sequences. In contrast, humans and animals perform sequenc...
We study the notion of class refinement in a concurrent object-oriented setting. Our model is based on a combination of action systems and classes. An action system describes the b...
Abstract. Two main challenges of robot action planning in real domains are uncertain action effects and dynamic environments. In this paper, an instance-based action model is lear...
Executable UML allows precisely describing the softtem at a higher level of abstraction. It bridges the semantics gap between the UML design models and the implementation. The exe...
In this paper, we present a reinforcement learning approach for mapping natural language instructions to sequences of executable actions. We assume access to a reward function tha...
S. R. K. Branavan, Harr Chen, Luke S. Zettlemoyer,...