ipp-marl

KO | EN

gitlite — search

#javascript #hacktoberfest #llm #golang #go #android #rust #linux #windows #awesome #awesome-list #security #ios #open-source

(★ 202)

Multi-UAV Adaptive Path Planning Using Deep Reinforcement Learning

File Explorer

Download Latest Version (.zip)

- - marl_framework.iml
  - misc.xml
  - modules.xml
  - vcs.xml
  - workspace.xml
- - __init__.cpython-38.pyc
  - actor_network.cpython-38.pyc
  - actor_network_input.cpython-38.pyc
  - agent_action_space.cpython-38.pyc
  - agent_state_space.cpython-38.pyc
  - batch_memory.cpython-38.pyc
  - buffer.cpython-38.pyc
  - cma_baseline.cpython-38.pyc
  - coma_wrapper.cpython-38.pyc
  - constants.cpython-38.pyc
  - critic_network.cpython-38.pyc
  - logger.cpython-38.pyc
  - mcts_baseline.cpython-38.pyc
  - mission_factories.cpython-38.pyc
  - missions.cpython-38.pyc
  - params.cpython-38.pyc
  - random_baseline.cpython-38.pyc
- - __init__.py
  - learner.py
  - network.py
  - transformations.py
- - __init__.py
  - action_space.py
  - agent.py
  - communication_log.py
  - state_space.py
- - __init__.py
  - learner.py
  - network.py
  - transformations.py
- - __init__.py
  - grid_maps.py
  - ground_truths.py
  - mappings.py
  - simulations.py
- - __init__.py
  - coma_mission.py
  - episode_generator.py
  - mission_factories.py
  - missions.py
- - __init__.py
  - cameras.py
- - __init__.py
  - action.py
  - optimization_helpers.py
  - plotting.py
  - reward.py
  - state.py
  - utils.py
- __init__.py
- batch_memory.py
- cd.save
- classification.py
- coma_test.py
- coma_wrapper.py
- constants.py
- IG_baseline.py
- IG_baseline.py.save
- lawn_mower.py
- logger.py
- main.py
- params.py
- params.yaml
- random_baseline.py
- README
README.md

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Multi-UAV Adaptive Path Planning Using Deep Reinforcement Learning

Jonas Westheider, Julius Rückin, Marija Popovic
University of Bonn

This repository contains the implementation of our paper [Multi-UAV Adaptive Path Planning Using Deep Reinforcement Learning](https://arxiv.org/pdf/2303.01150.pdf) submitted to IROS2023 (under review). The implementation is currently being cleaned up.

## Abstract

Efficient aerial data collection is important in many remote sensing applications. In large-scale monitoring scenarios, deploying a team of unmanned aerial vehicles (UAVs) offers improved spatial coverage and robustness against individual failures. However, a key challenge is cooperative path planning for the UAVs to efficiently achieve a joint mission goal. We propose a novel multi-agent informative path planning approach based on deep reinforcement learning for adaptive terrain monitoring scenarios using UAV teams. We introduce new network feature representations to effectively learn path planning in a 3D workspace. By leveraging a counterfactual baseline, our approach explicitly addresses credit assignment to learn cooperative behaviour. Our experimental evaluation shows improved planning performance, i.e. maps regions of interest more quickly, with respect to non-counterfactual vari- ants. Results on synthetic and real-world data show that our approach has superior performance compared to state-of-the-art non-learning-based methods, while being transferable to varying team sizes and communication constraints.

## Overview

At each time step during a mission, each UAV takes a measurement and updates its local map state. The local map is input to an actor network, which outputs a policy from which an action is sampled. During training, a centralised critic network is additionally trained using global map information and outputs Q-values for each action from the current state, i.e. the expected future return.

## Maintainer

Jonas Westheider, jwestheider@uni-bonn.de, Ph.D. student at PhenoRob - University of Bonn.

## Requirements

matplotlib==3.5.1
   
numpy==1.22.2
   
opencv-python==4.5.5.62
   
scipy==1.8.1
   
torch==1.13.0+cu117

## Funding

This work was funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy - EXC 2070 – 390732324. Authors are with the Cluster of Excellence PhenoRob, Institute of Geodesy and Geoinformation, University of Bonn.

ipp-marl

File Explorer

Today's picks

Was this content helpful?

Recent Feedback

ipp-marl

File Explorer

Today's picks

Was this content helpful?

Recent Feedback

Download README