Morti, the first robot dog that learns to walk alone in an hour!

Spinal cord research

This robot dog, dubbed Morti by the researchers, was designed to study an important structure of the central nervous system in mammals, the spinal cord. More rarely called spinal cord, it is inserted within the vertebral column itself in the vertebral canal. It starts from the medulla oblongata located at the level of the brainstem at the base of the brain and ends with the conus medullaris which is at the level of the last lumbar vertebrae.

Like the brain, the spinal cord is made up of white matter and gray matter. The white matter that lies in the periphery of the marrow includes the extensions of neurons called axons with their myelin sheath. The gray matter, inside the marrow, is made up of the cell bodies of neurons.

The spinal cord is used to transmit nerve impulses. It carries sensory information to the brain and motor impulses to different parts of the body such as the legs for example. The spinal cord is also the coordination center for motor automatisms where it is involved in reflex reactions.

At birth, most animals quickly learn to walk. It is a question of survival since walking and especially running allow them to escape their predators. To do this, they are equipped from the moment they come into the world with a complex network of muscular coordination in their spinal cord.

At first, their first steps and movements are a bit uncertain and clumsy and they often stumble. With a little practice, they quickly end up coordinating their muscles and tendons to move much smoother and faster.

(Also read: Robots in the kitchen)

Reflex movements without brain intervention


This video shows the robot dog Morti learning to walk. Source: Science X-Tech Xplore/YouTube

These uncertain movements at the beginning, followed by muscular coordination, are the result of a mechanism that exists in animals and humans. This mechanism includes a system known as the central pattern generator or CPG. It is a circuit of neurons that produces periodic muscle contractions without the intervention of the brain. It can therefore operate completely autonomously to generate a movement such as walking, for example. It is also this mechanism that comes into play during the blinking of the eyes or the peristaltic movements of the intestine during digestion.

Shortly after birth, when the young animal tries to take its first steps, the CPG system does not yet work perfectly and requires adjustments. This is why when it encounters an obstacle such as a hollow during its beginner’s course, the young animal stumbles and very often falls. Fortunately, in animals and humans, learning allows the improvement of the walking movement.

Because this phenomenon is still largely unknown, scientists have decided to use robotics. Engineers and roboticists have made a robot with reflexes similar to a young animal learning to walk. They then equipped this robot dog with a virtual spinal cord managed by a learning algorithm.

(Also read: Me, robot and almost human: 6 challenges to overcome to imitate humans)

Morti robot dog’s virtual spinal cord powered by learning algorithm

This learning algorithm, which somehow simulates a CPG system, allowed Morti to learn to walk in just one hour thanks to sensors attached to his feet. The information provided by these sensors was continuously compared to basic sensory data present in the robot’s memory.

Thanks to this algorithm which constantly monitored his paws, Morti adapted little by little and gradually improved his motor skills with lightning speed. At the beginning of the apprenticeship, each time Morti tripped, the program changed the amplitude and the speed of swinging of the legs, but also the length of time each leg remained on the ground.

The computer that controls the walk of the robot dog Morti is energy efficient since it consumes only 5 watts, which is very little compared to robots used in industry. Very often the algorithms and controllers of these machines are adapted to the mass of the robot, but also to its geometry.

Thanks to the robot dog Morti, scientists now have a model allowing them to study the functioning of the spinal cord, a structure of the nervous system which remains very difficult to study on a living animal.

(Also read: How can this cheetah robot run so fast?)

Source: Ruppert, F., Badri-Spröwitz, A., “Learning plastic matching of robot dynamics in closed-loop central pattern generators”, Nature Machine Intelligence, 4, 652–660 (2022), https://doi.org/10.1038/s42256-022-00505-4

Leave a Comment