Throughout history, knights have shared epic tales of horses that brought them home through dark, misty nights. Legendary animals even transported wounded soldiers to combat zones.

Sensitive and highly trained, these horses resemble fully autonomous robots, especially cars, like the computer scientist and roboticist, Eakta Jain.

Today’s vehicles have varying levels of range, with zero level or relative anti-lock braking system. Levels two or three have adaptive cruise control, the ability to follow lanes or park. This will develops at level five, which is total autonomy.

These horses that carry a home knight are level five, said Jain. “You trust them with your life.”

Interested in how this trust develops and if it can help improve human-robot interactions, Jain from the University of Florida in Gainesville, immersed in the horse world during a sabbatical year ending in 2022. and collected a wealth of information to answer open-ended questions about how humans should interact with robots of varying levels of autonomy.

“Only recently have researchers begun to focus on the early stages of human-robot interaction, such as making first impressions,” Jain and a colleague at the University of Florida wrote. Christina Garner McCunein the proceedings of the April 2023 CHI Conference on Human Factors in computer systems. “Our work seeks to unravel the principles of the scene after the first encounter”.

Lessons with horses

During his sabbatical, Jain took equine classes at his university, where he took notes based on his observations. and conversations with students, teaching assistants, and the instructor. She also spoke to other trainers and horse owners. And she learned to ride a horse.

“I had never interacted with a horse before,” says Jain. “I was a new rider learning to interact with an animal that was not a new horse (to ride), but it was still the beginning of building a relationship,” he said. .

When working with horses that are new to human interaction, theAnimals must be taught to interpret and react appropriately, as handlers perform basic handling such as leading and grooming them. This training helps prepare horses for more advanced handling, such as accepting a saddle and bridle and carrying a human for first rides. New knights must learn the intricacies of how the horse’s behavior communicates information and what cues handlers can use to direct them to desired actions or correct the horse when it does not behave as expected.

Likewise, people must learn to command robots to perform specific tasks. They also need to learn what to do when interactions with bots don’t go as planned. Robots must respond to human input in predictable ways. But more autonomous robots, like horses, also need to react dynamically to changing conditions, like a self-driving car stopping to avoid hitting something even when humans tell it to keep moving.

In human-horse partnerships, horses communicate mostly non-vocally. For example, your ears tend to point to what you are paying attention to. This behavior can inspiring the creation of robots with electronic “ears” that can swivel towards a ringing doorbell or people talking near an autonomous vehicle, thereby alerting humans to these sounds, Jain says. “Instead of the robot saying, ‘Knock on the door. Beep, beep, if its ears were pointed towards the door, that would be a much less jarring and much more subtle way of letting people know that the robot is listening to something it’s paying attention to.”

Non-verbal horse communication

Such subtlety can also be used as a sign of respect. Trainers and riders work intensely with the horses to enforce them. Horses nonverbally communicate their respect for their trainers and riders, adapting to their pace or providing them with a safe personal space when they walk. The horses’ ears even point to the trainers as a sign of respect when they pay attention. Trainers require horses to show signs of respect in basic interactions before “moving on to the next more complicated interaction,” says Jain. Respect can turn into trust. But even with experienced horses and riders, confidence is not guaranteed.

There may be a similar limitation with robots. “Perhaps the same types of nonverbal expressiveness used in the human-horse context could be used to communicate that the robot respects the human,” says Jain, which “may make humans feel more safe around robots. This might make them more open to working with them.

Probing what it means for robots and humans to respect and trust each other is largely uncharted territory, says Jain. Understanding how respect and trust grow between horse and human can be a game changer.

By rationalist universe
Translated and adapted by Mateus Lynniker from ScienceNews
Photo: Brianne Lehan/University of Florida

Read more news here.