Grounding Verbs of Motion in Natural Language Commands to Robots. Kollar, T., Tellex, S., Roy, D., & Roy, N.
Paper abstract bibtex To be useful teammates to human partners, robots must be able to follow spoken instructions given in natural language. An important class of instructions in-volve interacting with people, such as " Follow the person to the kitchen " or " Meet the person at the elevators. " These instructions require that the robot fluidly react to changes in the environment, not simply follow a pre-computed plan. We present an algorithm for understanding natural language commands with three components. First, we create a cost function that scores the language according to how well it matches a candidate plan in the environment, defined as the log-likelihood of the plan given the command. Components of the cost function include novel models for the meanings of motion verbs such as " follow, " " meet, " and " avoid, " as well as spa-tial relations such as " to " and landmark phrases such as " the kitchen. " Second, an inference method uses this cost function to perform forward search, finding a plan that matches the natural language command. Third, a high-level controller repeat-edly calls the inference method at each timestep to compute a new plan in response to changes in the environment such as the movement of the human partner or other people in the scene. When a command consists of more than a single task, the con-troller switches to the next task when an earlier one is satisfied. We evaluate our approach on a set of example tasks that require the ability to follow both simple and complex natural language commands.
@article{
title = {Grounding Verbs of Motion in Natural Language Commands to Robots},
type = {article},
id = {7f0544a7-0932-3ce1-802d-50cb4888b6c3},
created = {2017-09-01T15:53:36.922Z},
file_attached = {true},
profile_id = {80da7853-f7b7-36a9-8e4c-d7ddb2d9e538},
group_id = {a2333ea3-15a4-3d40-8d36-f0d9590ca926},
last_modified = {2017-09-01T15:53:37.109Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {false},
hidden = {false},
abstract = {To be useful teammates to human partners, robots must be able to follow spoken instructions given in natural language. An important class of instructions in-volve interacting with people, such as " Follow the person to the kitchen " or " Meet the person at the elevators. " These instructions require that the robot fluidly react to changes in the environment, not simply follow a pre-computed plan. We present an algorithm for understanding natural language commands with three components. First, we create a cost function that scores the language according to how well it matches a candidate plan in the environment, defined as the log-likelihood of the plan given the command. Components of the cost function include novel models for the meanings of motion verbs such as " follow, " " meet, " and " avoid, " as well as spa-tial relations such as " to " and landmark phrases such as " the kitchen. " Second, an inference method uses this cost function to perform forward search, finding a plan that matches the natural language command. Third, a high-level controller repeat-edly calls the inference method at each timestep to compute a new plan in response to changes in the environment such as the movement of the human partner or other people in the scene. When a command consists of more than a single task, the con-troller switches to the next task when an earlier one is satisfied. We evaluate our approach on a set of example tasks that require the ability to follow both simple and complex natural language commands.},
bibtype = {article},
author = {Kollar, Thomas and Tellex, Stefanie and Roy, Deb and Roy, Nicholas}
}