Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Zhehui, Yang, Zhaojing, Krupani, Rahul, Şenbaşlar, Baskın, Batra, Sumeet, Sukhatme, Gaurav S.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910435617275904
author Huang, Zhehui
Yang, Zhaojing
Krupani, Rahul
Şenbaşlar, Baskın
Batra, Sumeet
Sukhatme, Gaurav S.
author_facet Huang, Zhehui
Yang, Zhaojing
Krupani, Rahul
Şenbaşlar, Baskın
Batra, Sumeet
Sukhatme, Gaurav S.
contents End-to-end deep reinforcement learning (DRL) for quadrotor control promises many benefits -- easy deployment, task generalization and real-time execution capability. Prior end-to-end DRL-based methods have showcased the ability to deploy learned controllers onto single quadrotors or quadrotor teams maneuvering in simple, obstacle-free environments. However, the addition of obstacles increases the number of possible interactions exponentially, thereby increasing the difficulty of training RL policies. In this work, we propose an end-to-end DRL approach to control quadrotor swarms in environments with obstacles. We provide our agents a curriculum and a replay buffer of the clipped collision episodes to improve performance in obstacle-rich environments. We implement an attention mechanism to attend to the neighbor robots and obstacle interactions - the first successful demonstration of this mechanism on policies for swarm behavior deployed on severely compute-constrained hardware. Our work is the first work that demonstrates the possibility of learning neighbor-avoiding and obstacle-avoiding control policies trained with end-to-end DRL that transfers zero-shot to real quadrotors. Our approach scales to 32 robots with 80% obstacle density in simulation and 8 robots with 20% obstacle density in physical deployment. Video demonstrations are available on the project website at: https://sites.google.com/view/obst-avoid-swarm-rl.
format Preprint
id arxiv_https___arxiv_org_abs_2309_13285
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning
Huang, Zhehui
Yang, Zhaojing
Krupani, Rahul
Şenbaşlar, Baskın
Batra, Sumeet
Sukhatme, Gaurav S.
Robotics
Artificial Intelligence
Multiagent Systems
End-to-end deep reinforcement learning (DRL) for quadrotor control promises many benefits -- easy deployment, task generalization and real-time execution capability. Prior end-to-end DRL-based methods have showcased the ability to deploy learned controllers onto single quadrotors or quadrotor teams maneuvering in simple, obstacle-free environments. However, the addition of obstacles increases the number of possible interactions exponentially, thereby increasing the difficulty of training RL policies. In this work, we propose an end-to-end DRL approach to control quadrotor swarms in environments with obstacles. We provide our agents a curriculum and a replay buffer of the clipped collision episodes to improve performance in obstacle-rich environments. We implement an attention mechanism to attend to the neighbor robots and obstacle interactions - the first successful demonstration of this mechanism on policies for swarm behavior deployed on severely compute-constrained hardware. Our work is the first work that demonstrates the possibility of learning neighbor-avoiding and obstacle-avoiding control policies trained with end-to-end DRL that transfers zero-shot to real quadrotors. Our approach scales to 32 robots with 80% obstacle density in simulation and 8 robots with 20% obstacle density in physical deployment. Video demonstrations are available on the project website at: https://sites.google.com/view/obst-avoid-swarm-rl.
title Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning
topic Robotics
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2309.13285