MINI REVIEW article
Front. Robot. AI
Sec. Computational Intelligence in Robotics
Volume 12 - 2025 | doi: 10.3389/frobt.2025.1678567
This article is part of the Research TopicAI for Design and Control of Advanced RobotsView all articles
Imitation Learning for Legged Robot Locomotion: A Survey
Provisionally accepted
- 1Icahn School of Medicine at Mount Sinai Friedman Brain Institute, New York, United States
- 2The University of Texas at Austin, Austin, United States
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Imitation learning has fundamentally transformed the field of legged robot locomotion, removing the dependence on hand-engineered reward functions. Since 2019, this area of research has expanded rapidly, progressing from simple motion-capture replication to the generation of sophisticated policies using diffusion models. This survey offers a comprehensive analysis of 35 pivotal research works, employing a structured six-dimensional framework to investigate advancements using both quadrupedal and humanoid platforms. The review also pinpoints significant challenges related to deployment and outlines new research directions. A key finding from the survey indicate that Behavior Cloning is utilized in almost half of the analyzed studies. Moreover, data generated through Model-Predictive Control (MPC) now represents the most frequently used training data source for these advanced imitation learning systems.
Keywords: Imitation learning, reinforcement learning, Legged robotics, Locomotion control, sim-to-real transfer
Received: 02 Aug 2025; Accepted: 08 Oct 2025.
Copyright: © 2025 Mirza and Singh. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Shubham Singh, singh281@utexas.edu
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.