Hybrid Imitative Planning with Geometric and Predictive Costs in Offroad Environments

Nitish Dashora1, Daniel Shin1, Dhruv Shah2, Henry A Leopold3, David Fan4, Ali-Akbar Agha-Mohammadi5, Nicholas Rhinehart6, Sergey Levine1

  • 1UC Berkeley
  • 2University of California, Berkeley
  • 3University of Waterloo
  • 4NASA Jet Propulsion Laboratory
  • 5NASA-JPL, Caltech
  • 6Carnegie Mellon University

Details

10:40 - 10:45 | Wed 25 May | Room 115A | WeA06.07

Session: Integrated Planning and Learning

Abstract

Geometric methods for solving open-world off-road navigation tasks, by learning occupancy and metric maps, provide good generalization but can be brittle in outdoor environments that violate their assumptions (e.g., tall grass). Learning-based methods can directly learn collision-free behavior from raw observations, but are difficult to integrate with standard geometry-based pipelines. This creates an unfortunate conflict -- either use learning and lose out on well-understood geometric navigational components, or do not use it, in favor of extensively hand-tuned geometry-based cost maps. In this work, we reject this dichotomy by designing the learning and non-learning-based components in a way such that they can be effectively combined in a self-supervised manner. Both components contribute to a planning criterion: the learned component contributes predicted traversability as rewards, while the geometric component contributes obstacle cost information. We instantiate and comparatively evaluate our system in both in-distribution and out-of-distribution environments, showing that this approach inherits complementary gains from the learned and geometric components and significantly outperforms either of them.