ANYmal parkour: Learning agile navigation for quadrupedal robots
Science Robotics · 13.03.2024 · 9 (88)
DOI: 10.1126/scirobotics.adi7566 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Robotics, erschienen am 13.03.2024. Verfasst von David Hoeller und 3 weiteren Autor:innen. Beteiligte Einrichtung: Robotic Systems Lab, ETH Zurich, Zurich, Switzerland. Hauptthemen laut MEDLINE: Robotics. Die Arbeit wurde bisher 305-mal zitiert (Crossref) und nennt 43 Literaturangaben.
Abstract (Originalsprache)
Performing agile navigation with four-legged robots is a challenging task because of the highly dynamic motions, contacts with various parts of the robot, and the limited field of view of the perception sensors. Here, we propose a fully learned approach to training such robots and conquer scenarios that are reminiscent of parkour challenges. The method involves training advanced locomotion skills for several types of obstacles, such as walking, jumping, climbing, and crouching, and then using a high-level policy to select and control those skills across the terrain. Thanks to our hierarchical formulation, the navigation policy is aware of the capabilities of each skill, and it will adapt its behavior depending on the scenario at hand. In addition, a perception module was trained to reconstruct obstacles from highly occluded and noisy sensory data and endows the pipeline with scene understanding. Compared with previous attempts, our method can plan a path for challenging scenarios without expert demonstration, offline computation, a priori knowledge of the environment, or taking contacts explicitly into account. Although these modules were trained from simulated data only, our real-world experiments demonstrate successful transfer on hardware, where the robot navigated and crossed consecutive challenging obstacles with speeds of up to 2 meters per second.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Robotic Systems Lab, ETH Zurich, Zurich, Switzerland.
- NVIDIA, Zurich, Switzerland.
ORCID-Profile: David Hoeller, Nikita Rudin, Marco Hutter
Zitieren
APA
Hoeller, D., Rudin, N., Sako, D., & Hutter, M. (2024). ANYmal parkour: Learning agile navigation for quadrupedal robots. Science Robotics, 9(88). https://doi.org/10.1126/scirobotics.adi7566
Vancouver
Hoeller D, Rudin N, Sako D, Hutter M. ANYmal parkour: Learning agile navigation for quadrupedal robots. Science Robotics. 2024;9(88). doi:10.1126/scirobotics.adi7566
BibTeX
@article{Hoeller2024,
author = {Hoeller, David and Rudin, Nikita and Sako, Dhionis and Hutter, Marco},
title = {ANYmal parkour: Learning agile navigation for quadrupedal robots},
journal = {Science Robotics},
year = {2024},
volume = {9},
number = {88},
doi = {10.1126/scirobotics.adi7566}
}
EUVIMED