loading page

Deep Meta-Learning Energy-Aware Path Planner for Unmanned Ground Vehicles in Unknown Terrains
  • +1
  • Marco Visca ,
  • Roger Powell ,
  • Yang Gao ,
  • Saber Fallah
Marco Visca
University of Surrey, University of Surrey

Corresponding Author:[email protected]

Author Profile
Roger Powell
Author Profile
Saber Fallah
Author Profile


This paper presents an adaptive energy-aware prediction and planning framework for vehicles navigating over terrains with varying and unknown properties. A novel feature of the method is the use of a deep meta-learning framework to learn a prior energy model, which can efficiently adapt to the local terrain conditions based on small quantities of exteroceptive and proprioceptive data. A meta-adaptive heuristic function is also proposed for the integration of the energy model into an A* path planner. The performance of the proposed approach is assessed in a 3D-body dynamic simulator over several typologies of deformable terrains, and compared with alternative machine learning solutions. We provide evidence of the advantages of the proposed method to adapt to unforeseen terrain conditions, thereby yielding more informed estimations and energy-efficient paths, when navigating on unknown terrains.
Submitted for revision to IEEE Transaction on Cybernetics.
2022Published in IEEE Access volume 10 on pages 30055-30068. 10.1109/ACCESS.2022.3155161