Talk2Car: Taking Control of Your Self-Driving Car

TL;DR

This paper introduces Talk2Car, a novel dataset for natural language commands in autonomous driving, enabling research on grounding language in street scene visual data for vehicle control.

Contribution

The paper presents the first object referral dataset for self-driving cars, along with a performance analysis of state-of-the-art models on this challenging task.

Findings

Models show promising results but still need improvement in NLP and vision integration.

The dataset provides a new benchmark for natural language grounding in autonomous driving.

The task is challenging, highlighting the need for further research in multi-modal understanding.

Abstract

A long-term goal of artificial intelligence is to have an agent execute commands communicated through natural language. In many cases the commands are grounded in a visual environment shared by the human who gives the command and the agent. Execution of the command then requires mapping the command into the physical visual space, after which the appropriate action can be taken. In this paper we consider the former. Or more specifically, we consider the problem in an autonomous driving setting, where a passenger requests an action that can be associated with an object found in a street scene. Our work presents the Talk2Car dataset, which is the first object referral dataset that contains commands written in natural language for self-driving cars. We provide a detailed comparison with related datasets such as ReferIt, RefCOCO, RefCOCO+, RefCOCOg, Cityscape-Ref and CLEVR-Ref. Additionally, we include a performance analysis using strong state-of-the-art models. The results show that the proposed object referral task is a challenging one for which the models show promising results but still require additional research in natural language processing, computer vision and the intersection of these fields. The dataset can be found on our website: http://macchina-ai.eu/