SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.11575 · ICCV · 2021

Learn-to-Race: A Multimodal Control Environment for Autonomous Racing

Abhinav Gupta, Jonathan Francis, Siddha Ganju, Bingqing Chen, Eric Nyberg, James Herman, Anirudh Koul, Alexey Skabelkin, Ivan Zhukov, Max Kumskoy

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Existing research on autonomous driving primarily focuses on urban driving, which is insufficient for characterising the complex driving behaviour underlying highspeed racing. At the same time, existing racing simulation frameworks struggle in capturing realism, with respect to visual rendering, vehicular dynamics, and task objectives, inhibiting the transfer of learning agents to realworld contexts. We introduce a new environment, where agents Learn-to-Race (L2R) in simulated competitionstyle racing, using multimodal information-from virtual cameras to a comprehensive array of inertial measurement sensors. Our environment, which includes a simulator and an interfacing training framework, accurately models vehicle dynamics and racing conditions. In this paper, we release the Arrival simulator for autonomous racing. Next, we propose the L2R task with challenging metrics, inspired by learning-to-drive challenges, Formulastyle racing, and multimodal trajectory prediction for autonomous driving. Additionally, we provide the L2R framework suite, facilitating simulated racing on high-precision models of real-world tracks. Finally, we provide an official L2R task dataset of expert demonstrations, as well as a series of baseline experiments and reference implementations. We make all code available: https://github. com/learn-to-race/l2r.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2103.11575")
get_code_for_paper("2103.11575")
have("2103.11575")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2103.11575.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2103.11575.svg)](https://syntology.ai/paper/2103.11575)

Connect an agent — have() is free.