keyword
locomotion controllers
A locomotion controller is a robotic control system that computes and coordinates actuator commands to enable an autonomous machine, such as a legged robot, to move across an environment while maintaining balance and stability. These controllers process sensory feedback, including proprioceptive signals from joint encoders and inertial measurement units, to track high-level velocity or trajectory targets. Traditionally implemented using model-based trajectory optimization and finite-state machines, modern locomotion controllers often utilize learned neural network policies trained through reinforcement learning, allowing robots to autonomously regulate gaits, recover from disturbances, and traverse complex or unmodeled terrain.
2 items
Learning quadrupedal locomotion over challenging terrain
Joonho Lee, Jemin Hwangbo, Lorenz Wellhausen, Vladlen Koltun, Marco Hutter
Why you should read this
Demonstrates that a reinforcement learning controller trained purely in simulation using proprioceptive feedback achieves zero-shot transfer to traverse extreme, unmodeled natural terrains such as mud, snow, and dynamic rubble on physical quadruped robots.
Some of the most challenging environments on our planet are accessible to quadrupedal animals but remain out of reach for autonomous machines. Legged locomotion can dramatically expand the operational domains of robotics. However, conventional controllers for legged locomotion are based on elaborate state machines that explicitly trigger the execution of motion primitives and reflexes. These designs have escalated in complexity while falling short of the generality and robustness of animal locomotion. Here we present a radically robust controller for legged locomotion in challenging natural environments. We present a novel solution to incorporating proprioceptive feedback in locomotion control and demonstrate remarkable zero-shot generalization from simulation to natural environments. The controller is trained by reinforcement learning in simulation. It is based on a neural network that acts on a stream of proprioceptive signals. The trained controller has taken two generations of quadrupedal ANYmal robots to a variety of natural environments that are beyond the reach of prior published work in legged locomotion. The controller retains its robustness under conditions that have never been encountered during training: deformable terrain such as mud and snow, dynamic footholds such as rubble, and overground impediments such as thick vegetation and gushing water. The presented work opens new frontiers for robotics and indicates that radical robustness in natural environments can be achieved by training in much simpler domains.
Added
2026-09-24
Learning agile and dynamic motor skills for legged robots
Jemin Hwangbo, Joonho Lee, Alexey Dosovitskiy, Dario Bellicoso, Vassilios Tsounis, Vladlen Koltun, Marco Hutter
Why you should read this
Develops a sim-to-real reinforcement learning pipeline that trains neural network policies in simulation and deploys them on physical quadruped robots, achieving fast running speeds, energy-efficient velocity tracking, and autonomous fall recovery.
Legged robots pose one of the greatest challenges in robotics. Dynamic and agile maneuvers of animals cannot be imitated by existing methods that are crafted by humans. A compelling alternative is reinforcement learning, which requires minimal craftsmanship and promotes the natural evolution of a control policy. However, so far, reinforcement learning research for legged robots is mainly limited to simulation, and only few and comparably simple examples have been deployed on real systems. The primary reason is that training with real robots, particularly with dynamically balancing systems, is complicated and expensive. In the present work, we introduce a method for training a neural network policy in simulation and transferring it to a state-of-the-art legged system, thereby leveraging fast, automated, and cost-effective data generation schemes. The approach is applied to the ANYmal robot, a sophisticated medium-dog-sized quadrupedal system. Using policies trained in simulation, the quadrupedal machine achieves locomotion skills that go beyond what had been achieved with prior methods: ANYmal is capable of precisely and energy-efficiently following high-level body velocity commands, running faster than before, and recovering from falling even in complex configurations.
Added
2026-09-18