Deep Reinforcement Learning for Bipedal Locomotion: A Brief Survey

Abstract

Bipedal robots are gaining global recognition due to their potential applications and advancements in artificial intelligence, particularly through Deep Reinforcement Learning (DRL). While DRL has significantly advanced bipedal locomotion, the development of a unified framework capable of handling a wide range of tasks remains an ongoing challenge. This survey systematically categorises, compares, and analyses existing DRL frameworks for bipedal locomotion, organising them into end-to-end and hierarchical control schemes. End-to-end frameworks are evaluated based on their learning approaches, while hierarchical frameworks are examined in terms of layered structures that integrate learning-based or traditional model-based methods. We provide a detailed evaluation of the composition, strengths, limitations, and capabilities of each framework. Additionally, this survey identifies key research gaps and proposes future directions aimed at creating a more integrated and efficient framework for bipedal locomotion, with wide-ranging applications in real-world environments.

Published in Artificial Intelligence Review

References in corpus (19)

• A Brief Survey of Deep Reinforcement Learning
• Learning agile and dynamic motor skills for legged robots
• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
• Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments
• Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning
• Learning Symmetric and Low-energy Locomotion
• RLOC: Terrain-Aware Legged Locomotion using Reinforcement Learning and Optimal Control
• Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?
• Cat-like Jumping and Landing of Legged Robots in Low-gravity Using Deep Reinforcement Learning
• DTC: Deep Tracking Control
• TAMOLS: Terrain-Aware Motion Optimization for Legged Systems
• Structured contact force optimization for kino-dynamic motion generation
• Learning natural locomotion behaviors for humanoid robots using human knowledge
• RL + Model-based Control: Using On-demand Optimal Control to Learn Versatile Legged Locomotion
• HumanMimic: Learning Natural Locomotion and Transitions for Humanoid Robot via Wasserstein Adversarial Imitation
• Learning Bipedal Walking for Humanoids with Current Feedback
• Learning Whole-body Motor Skills for Humanoids
• Robust and Versatile Bipedal Jumping Control through Reinforcement Learning
• AnyBipe: An End-to-End Framework for Training and Deploying Bipedal Robots Guided by Large Language Models