# Energy-based Legged Robots Terrain Traversability Modeling via Deep Inverse Reinforcement Learning

arXiv: https://arxiv.org/abs/2207.03034 · HTML: https://mlsanity.com/paper/2207.03034/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Real-world robot offline RL, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 7 Jul 2022.

## Placed in

- Offline RL and imitation learning from data / [Real-world robot offline RL](https://mlsanity.com/offlinerl/real-world-robot-offline-rl/)

## Builds on (most cited first, 23 of 23)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Road Extraction by Deep Residual U-Net](https://mlsanity.com/paper/1711.10684/) (2017)
- [A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress](https://mlsanity.com/paper/1806.06877/) (2018)
- [Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations](https://mlsanity.com/paper/1904.06387/) (2019)
- [Maximum Entropy Deep Inverse Reinforcement Learning](https://mlsanity.com/paper/1507.04888/) (2015)
- [BADGR: An Autonomous Self-Supervised Learning-Based Navigation System](https://mlsanity.com/paper/2002.05700/) (2020)
- [Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans](https://mlsanity.com/paper/2001.00735/) (2020)
- [Bayesian Spatial Kernel Smoothing for Scalable Dense Semantic Mapping](https://mlsanity.com/paper/1909.04631/) (2019)
- [Find Your Own Way: Weakly-Supervised Segmentation of Path Proposals for Urban Autonomy](https://mlsanity.com/paper/1610.01238/) (2016)
- [Autonomous Navigation in Complex Environments with Deep Multimodal Fusion Network](https://mlsanity.com/paper/2007.15945/) (2020)
- [Off-road Autonomous Vehicles Traversability Analysis and Trajectory Planning Based on Deep Inverse Reinforcement Learning](https://mlsanity.com/paper/1909.06953/) (2019)
- [Legged Robot State Estimation using Invariant Kalman Filtering and Learned Contact Events](https://mlsanity.com/paper/2106.15713/) (2021)
- [Toward Safety-Aware Informative Motion Planning for Legged Robots](https://mlsanity.com/paper/2103.14252/) (2021)
- [Hybrid Imitative Planning with Geometric and Predictive Costs in Off-road Environments](https://mlsanity.com/paper/2111.10948/) (2021)
- [Integrating kinematics and environment context into deep inverse reinforcement learning for predicting off-road vehicle trajectories](https://mlsanity.com/paper/1810.07225/) (2018)
- [Multitask Learning for Scalable and Dense Multilayer Bayesian Map Inference](https://mlsanity.com/paper/2106.14986/) (2021)
- [An Error-State Model Predictive Control on Connected Matrix Lie Groups for Legged Robot Control](https://mlsanity.com/paper/2203.08728/) (2022)
- [Efficient Anytime CLF Reactive Planning System for a Bipedal Robot on Undulating Terrain](https://mlsanity.com/paper/2108.06699/) (2021)
- [Sampling-based Incremental Information Gathering with Applications to Robotic Exploration and Environmental Monitoring](https://mlsanity.com/paper/1607.01883/) (2016)
- [Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning](https://mlsanity.com/paper/2101.00186/) (2021)
- [Navigating by Touch: Haptic Monte Carlo Localization via Geometric Sensing and Terrain Classification](https://mlsanity.com/paper/2108.08015/) (2021)

## Built on by (most cited first, 5 of 5)

- [Fast Traversability Estimation for Wild Visual Navigation](https://mlsanity.com/paper/2305.08510/) (2023)
- [Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning](https://mlsanity.com/paper/2309.16074/) (2023)
- [Learning Implicit Social Navigation Behavior using Deep Inverse Reinforcement Learning](https://mlsanity.com/paper/2501.06946/) (2025)
- [SoLo T-DIRL: Socially-Aware Dynamic Local Planner based on Trajectory-Ranked Deep Inverse Reinforcement Learning](https://mlsanity.com/paper/2209.07996/) (2022)
- [Avoidance of an unexpected obstacle without reinforcement learning: Why not using advanced control-theoretic tools?](https://mlsanity.com/paper/2509.03721/) (2025)

## Abstract (arXiv)

This work reports on developing a deep inverse reinforcement learning method for legged robots terrain traversability modeling that incorporates both exteroceptive and proprioceptive sensory data. Existing works use robot-agnostic exteroceptive environmental features or handcrafted kinematic features; instead, we propose to also learn robot-specific inertial features from proprioceptive sensory data for reward approximation in a single deep neural network. Incorporating the inertial features can improve the model fidelity and provide a reward that depends on the robot's state during deployment. We train the reward network using the Maximum Entropy Deep Inverse Reinforcement Learning (MEDIRL) algorithm and propose simultaneously minimizing a trajectory ranking loss to deal with the suboptimality of legged robot demonstrations. The demonstrated trajectories are ranked by locomotion energy consumption, in order to learn an energy-aware reward function and a more energy-efficient policy than demonstration. We evaluate our method using a dataset collected by an MIT Mini-Cheetah robot and a Mini-Cheetah simulator. The code is publicly available at https://github.com/ganlumomo/minicheetah-traversability-irl.