# ArtPlanner: Robust Legged Robot Navigation in the Field

arXiv: https://arxiv.org/abs/2303.01420 · HTML: https://mlsanity.com/paper/2303.01420/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2023.

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

- [Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion](https://mlsanity.com/paper/2401.17583/) (2024)
- [Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots](https://mlsanity.com/paper/2405.01792/) (2024)
- [RoadRunner -- Learning Traversability Estimation for Autonomous Off-road Driving](https://mlsanity.com/paper/2402.19341/) (2024)
- [Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-End](https://mlsanity.com/paper/2310.03581/) (2023)
- [Spatially-Enhanced Recurrent Memory for Long-Range Mapless Navigation via End-to-End Reinforcement Learning](https://mlsanity.com/paper/2506.05997/) (2025)
- [Robot Navigation Using Physically Grounded Vision-Language Models in Outdoor Environments](https://mlsanity.com/paper/2409.20445/) (2024)
- [AINav: Large Language Model-Based Adaptive Interactive Navigation](https://mlsanity.com/paper/2503.22942/) (2025)
- [Robot Squid Game: Quadrupedal Locomotion for Traversing Narrow Tunnels](https://mlsanity.com/paper/2605.13665/) (2026)

## Abstract (arXiv)

Due to the highly complex environment present during the DARPA Subterranean Challenge, all six funded teams relied on legged robots as part of their robotic team. Their unique locomotion skills of being able to step over obstacles require special considerations for navigation planning. In this work, we present and examine ArtPlanner, the navigation planner used by team CERBERUS during the Finals. It is based on a sampling-based method that determines valid poses with a reachability abstraction and uses learned foothold scores to restrict areas considered safe for stepping. The resulting planning graph is assigned learned motion costs by a neural network trained in simulation to minimize traversal time and limit the risk of failure. Our method achieves real-time performance with a bounded computation time. We present extensive experimental results gathered during the Finals event of the DARPA Subterranean Challenge, where this method contributed to team CERBERUS winning the competition. It powered navigation of four ANYmal quadrupeds for 90 minutes of autonomous operation without a single planning or locomotion failure.