Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2021 Sep 13;8:738113. doi: 10.3389/frobt.2021.738113

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

Copyright © 2021 Larsen, Teigen, Laache, Varagnolo and Rasheed.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

PMC Copyright notice

Instances of each training environment used to evaluate the applicability of different RL algorithms on the dual task of path following and collision avoidance. Before defining the path, the start and goal positions are initialized at random but with a fixed distance (8000m) apart. Env0, the trivial case, contains only a straight path. Env1 creates a curved path. Env2 inherits Env0 and places 4 static obstacles randomly along the path. Env3 inherits the properties of Env2 and adds 17 dynamic obstacles with random headings, sizes, and velocities around the path. Env4 inherits Env3 and adds curvature to the path. Finally, MovingObstaclesNoRules increases the number of static obstacles from 4 to 11 and scatters them randomly on and around the path; this represents the original training environment as defined in Meyer et al. (2020b).