The RobotSlang Benchmark: Dialog-guided Robot Localization and Navigation

TL;DR

RobotSlang introduces a benchmark for natural language dialog-based robot localization and navigation, enabling research on cooperative communication between humans and robots in real-world tasks.

Contribution

The paper presents RobotSlang, a new benchmark dataset with dialog-based navigation tasks, and an initial model demonstrating the feasibility of dialog-guided robot control.

Findings

A new dataset with 169 dialogs and 5k utterances for robot localization and navigation.

An initial model can follow dialog instructions to control a physical robot.

Simulation-trained agents can operate in real-world robot platforms.

Abstract

Autonomous robot systems for applications from search and rescue to assistive guidance should be able to engage in natural language dialog with people. To study such cooperative communication, we introduce Robot Simultaneous Localization and Mapping with Natural Language (RobotSlang), a benchmark of 169 natural language dialogs between a human Driver controlling a robot and a human Commander providing guidance towards navigation goals. In each trial, the pair first cooperates to localize the robot on a global map visible to the Commander, then the Driver follows Commander instructions to move the robot to a sequence of target objects. We introduce a Localization from Dialog History (LDH) and a Navigation from Dialog History (NDH) task where a learned agent is given dialog and visual observations from the robot platform as input and must localize in the global map or navigate towards the next target object, respectively. RobotSlang is comprised of nearly 5k utterances and over 1k minutes of robot camera and control streams. We present an initial model for the NDH task, and show that an agent trained in simulation can follow the RobotSlang dialog-based navigation instructions for controlling a physical robot platform. Code and data are available at https://umrobotslang.github.io/.