TY - GEN
T1 - MIDGARD: A Robot Navigation Simulator for Outdoor Unstructured Environments
AU - Vecchio, Giuseppe
AU - Sarpietro, Riccardo E.
AU - Cancelliere, Francesco
AU - Palazzo, Simone
AU - Guastella, Dario C.
AU - Strano, Alessandro
AU - Carlucho, Ignacio
AU - Muscato, Giovanni
AU - Albrecht, Stefano V.
AU - Spampinato, Concetto
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
PY - 2025/1/1
Y1 - 2025/1/1
N2 - We present MIDGARD, a simulation platform based on Unreal Engine for training autonomous robots in complex outdoor unstructured environments. It offers photorealistic 3D scenes, procedural scene generation, and integration with ROS and OpenAI Gym. The focus of MIDGARD is on navigation, where an autonomous agent travels from random initial positions to designated target locations avoiding obstacles, enabling researchers to develop and evaluate novel algorithms and navigation methods. We evaluate MIDGARD’s suitability as a research tool by training navigation algorithms based on reinforcement learning; we also assess sim-to-real transfer capabilities in a traversable horizon prediction task, using deep learning models on RGB images only. MIDGARD builds and docs are available at www.midgardsim.org.
AB - We present MIDGARD, a simulation platform based on Unreal Engine for training autonomous robots in complex outdoor unstructured environments. It offers photorealistic 3D scenes, procedural scene generation, and integration with ROS and OpenAI Gym. The focus of MIDGARD is on navigation, where an autonomous agent travels from random initial positions to designated target locations avoiding obstacles, enabling researchers to develop and evaluate novel algorithms and navigation methods. We evaluate MIDGARD’s suitability as a research tool by training navigation algorithms based on reinforcement learning; we also assess sim-to-real transfer capabilities in a traversable horizon prediction task, using deep learning models on RGB images only. MIDGARD builds and docs are available at www.midgardsim.org.
KW - robot navigation
KW - simulation
KW - unstructured environments
UR - http://www.scopus.com/inward/record.url?scp=85215799060&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-76424-0_22
DO - 10.1007/978-3-031-76424-0_22
M3 - Conference contribution
AN - SCOPUS:85215799060
SN - 9783031764233
SN - 9783031764264
VL - 1
T3 - Springer Proceedings in Advanced Robotics
SP - 120
EP - 125
BT - European Robotics Forum 2024
A2 - Secchi, Cristian
A2 - Marconi, Lorenzo
PB - Springer
T2 - 15th European Robotics Forum, ERF 2024
Y2 - 13 March 2024 through 15 March 2024
ER -