Natural Language processing is a growing field and widely used in both industrial and and commercial cases. Though it is difficult to create a natural language system that can robustly react to and handle every situation it is quite possible to design the system to react to specific instruction or scenario. The problem with current natural language systems used in machines, though, is that they are focused on single instructions, working to complete the instruction given then waiting for the next instruction. In this way they are not set to respond to possible conditions that are explained to them.

In the system designed and explained in this thesis, the goal is to fix this problem by introducing a method of adjusting to these conditions. The contributions made in this thesis are to design a set of instruction types that can be used in order to allow for conditional statements within natural language instructions. To create a modular system using ROS in order to allow for more robust communication and integration. Finally, the goal is to also allow for an interconnection between the written text and derived instructions that will make the sentence construction more seamless and natural for the user.

The work in this thesis will be limited in its focus to pertaining to the objective of obstacle traversal. The ideas and methodology, though, can be seen to extend into future work in the area.