# Hybrid Imitative Planning with Geometric and Predictive Costs in Off-road Environments

arXiv: https://arxiv.org/abs/2111.10948 · HTML: https://mlsanity.com/paper/2111.10948/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2021.

## Built on by (most cited first, 8 of 8)

- [Sim-to-Real via Sim-to-Seg: End-to-end Off-road Autonomous Driving Without Real Data](https://mlsanity.com/paper/2210.14721/) (2022)
- [Reinforcement Learning for Wheeled Mobility on Vertically Challenging Terrain](https://mlsanity.com/paper/2409.02383/) (2024)
- [Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction](https://mlsanity.com/paper/2306.03857/) (2023)
- [Energy-based Legged Robots Terrain Traversability Modeling via Deep Inverse Reinforcement Learning](https://mlsanity.com/paper/2207.03034/) (2022)
- [Learning to navigate efficiently and precisely in real environments](https://mlsanity.com/paper/2401.14349/) (2024)
- [Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning](https://mlsanity.com/paper/2204.03597/) (2022)
- [VertiSelector: Automatic Curriculum Learning for Wheeled Mobility on Vertically Challenging Terrain](https://mlsanity.com/paper/2409.17469/) (2024)
- [Training Generalist Navigation Policies via Action Self-Distillation](https://mlsanity.com/paper/2610.17593/) (2026)

## Abstract (arXiv)

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. Videos of our results are hosted at https://sites.google.com/view/hybrid-imitative-planning