Advancements in Legged Robot Locomotion and Control

The field of legged robotics is rapidly advancing, with a focus on developing more efficient, robust, and adaptive locomotion and control systems. Researchers are exploring new approaches to integrate locomotion skills with navigation, minimize acoustic noise, and optimize motion control algorithms. The use of reinforcement learning, hierarchical control frameworks, and adaptive assistive forces is becoming increasingly popular. These advancements have the potential to enable legged robots to operate effectively in complex and dynamic environments, such as indoor spaces and unpredictable terrains. Noteworthy papers include:

Skill-Nav, which proposes a method for integrating quadrupedal locomotion skills into a hierarchical navigation framework.
HAC-LOCO, which presents a two-stage hierarchical learning framework for learning hierarchical active compliance control for quadruped locomotion under continuous external disturbances.

Sources

Skill-Nav: Enhanced Navigation with Versatile Quadrupedal Locomotion via Waypoint Interface

Minimizing Acoustic Noise: Enhancing Quiet Locomotion for Quadruped Robots in Indoor Applications

Learning Motion Skills with Adaptive Assistive Curriculum Force in Humanoid Robots

Motion Tracking with Muscles: Predictive Control of a Parametric Musculoskeletal Canine Model

Novel Design of 3D Printed Tumbling Microrobots for in vivo Targeted Drug Delivery

Mechanical Intelligence-Aware Curriculum Reinforcement Learning for Humanoids with Parallel Actuation

Learning Steerable Imitation Controllers from Unstructured Animal Motions

Jump-Start Reinforcement Learning with Self-Evolving Priors for Extreme Monopedal Locomotion

HAC-LOCO: Learning Hierarchical Active Compliance Control for Quadruped Locomotion under Continuous External Disturbances

Vibration of Soft, Twisted Beams for Under-Actuated Quadrupedal Locomotion