# Deep Reinforcement Learning-based Large-scale Robot Exploration

Source: [Deep Reinforcement Learning-based Large-scale Robot Exploration](<https://www.sota2.com/research/paper/68fa72961e209131cea5755a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:29:52.311Z

Authors: Yuhong Cao, Rui Zhao, Yizhuo Wang, Bairan Xiang, Guillaume Sartoretti

Published: 2024-03-16T06:56:32.000Z

## Abstract

In this work, we propose a deep reinforcement learning (DRL) based reactive planner to solve large-scale Lidar-based autonomous robot exploration problems in 2D action space. Our DRL-based planner allows the agent to reactively plan its exploration path by making implicit predictions about unknown areas, based on a learned estimation of the underlying transition model of the environment. To this end, our approach relies on learned attention mechanisms for their powerful ability to capture long-term dependencies at different spatial scales to reason about the robot's entire belief over known areas. Our approach relies on ground truth information (i.e., privileged learning) to guide the environment estimation during training, as well as on a graph rarefaction algorithm, which allows models trained in small-scale environments to scale to large-scale ones. Simulation results show that our model exhibits better exploration efficiency (12% in path length, 6% in makespan) and lower planning time (60%) than the state-of-the-art planners in a 130m x 100m benchmark scenario. We also validate our learned model on hardware.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Robotic Exploration on Gazebo 92m x 74m high-fidelity simulation (Scene 2)](<https://www.sota2.com/research/sota/robotic-exploration-on-gazebo-92m-x-74m-high-fidelity-simulation-scene-2.md>): Robotic Exploration; Gazebo 92m x 74m high-fidelity simulation (Scene 2); Distance (m): 759.88.

- [Autonomous Robotic Exploration on Warehouse Gazebo simulation (environment)](<https://www.sota2.com/research/sota/autonomous-robotic-exploration-on-warehouse-gazebo-simulation-environment.md>): Autonomous Robotic Exploration; Warehouse Gazebo simulation (environment); Exploration Distance (m): 521.

- [Robotic Exploration on Forest Gazebo simulation](<https://www.sota2.com/research/sota/robotic-exploration-on-forest-gazebo-simulation.md>): Robotic Exploration; Forest Gazebo simulation; Distance (m): 1320.

- [Robotic Exploration on Indoor Gazebo simulation (test)](<https://www.sota2.com/research/sota/robotic-exploration-on-indoor-gazebo-simulation-test.md>): Robotic Exploration; Indoor Gazebo simulation (test); Exploration Distance (m): 105363.

- [Robotic Exploration on Forest Gazebo simulation (test)](<https://www.sota2.com/research/sota/robotic-exploration-on-forest-gazebo-simulation-test.md>): Robotic Exploration; Forest Gazebo simulation (test); Distance (m): 132081.

- [Robotic Exploration on Warehouse Gazebo simulation (test)](<https://www.sota2.com/research/sota/robotic-exploration-on-warehouse-gazebo-simulation-test.md>): Robotic Exploration; Warehouse Gazebo simulation (test); Distance (m): 52116.

- [Robotic Exploration on Gazebo 64m x 85m high-fidelity simulation (Scene 1)](<https://www.sota2.com/research/sota/robotic-exploration-on-gazebo-64m-x-85m-high-fidelity-simulation-scene-1.md>): Robotic Exploration; Gazebo 64m x 85m high-fidelity simulation (Scene 1); Distance (m): 741.15.

- [Autonomous Exploration on Maze datasets](<https://www.sota2.com/research/sota/autonomous-exploration-on-maze-datasets.md>): Autonomous Exploration; Maze datasets; Distance (m): 575.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2403.10833>)

[PDF](<https://arxiv.org/pdf/2403.10833.pdf>)
