PRE2018 4 Group1

Group 1

Group members	Student number	Study
Lotte van Gessel	1237708	l.s.v.gessel@student.tue.nl
Piers da Camino Ancona Lopez Soligo	1015467	dit mail adres
Sander Poot	1017804	s.a.poot@student.tue.nl
Timon Heuwekemeijer	1003212	t.m.heukemeijer@student.tue.nl
Jan van Leeuwen	1261401	j.a.v.leeuwen@student.tue.nl

Subject

Researching and redesigning robotic substitutes for service dogs that help blind people navigate

State of the Art research

Robots that can adapt like animals

Relevance

When designing a robotic service dog, a problem that can occur will be that the dog can become damaged while the user is out with the service dog. The following article is about how a robot can cope with problems in a similar way animals do.

Summary

In this article, a trial and error algorithm is proposed so that the robots can adapt to damage is under two minutes in a similar manner as animals. Current recovery typically involves two phases. The robot first needs to diagnose itself, which is followed by selecting the best plan to fix the problem. Problem is that it could be that not every situation is foreseen by the designer, and the robot does not have the right diagnosis or contingency plan to cope with the inflicted damage. Animals deal with injuries in a more trail and error based way. A similar algorithm could be implemented in robots to learn the robot different behaviors to injuries without the limitations to the engineers possible damage scenario’s. The current state-of-the-art algorithms for this are not suitable since they can’t cope with the curse of dimensionality. Other algorithms take up about 15 minutes and need some human demonstrations of some kind. Animals can do it in 2 minutes, so for robots it would be more practical to do so in a similar time. The main difference between animals and robots is that animals know the search space of behaviors and can therefore adapt intelligently. Robots would need to do the same in order to achieve a similar behavior. Robots used in the article store knowledge in a behavior-performance space. This helps them to cope with injuries by quickly discovering the behavior that would help in the injury at hand. [1]

Ethorobotics: A New Approach to Human-Robot Relationship.

Relevance

The robotic service dog should, besides it’s service duty, also serve as a kind of companion robot in order to build a good relationship with the user.

Summary

This article proposes a new approach to the relationship between the human and the robot. It focusses on the uncanny valley hypothesis. The uncanny valley states that humans will be more likely to interact between things that are more human-like, but when they become too similar they tend to avoid them.  

It is stated that biological agents need to be able to make a difference in one of the following categories: same vs different species, familiar vs unfamiliar conspecifics and familiar conspecifics vs individuals. The division in these categories determine the way in which both agents will interact with one another. The way in which humans can divide in these categories is learned by some specific pattern of cues. This learning can take place in a certain period in the development of the person. The uncanny valley hypothesis offers two options for social robots. They should either achieve perfect similarity to humans, or humans need to be exposed to social robots from their first year of life on, so they can become more used to the robot. Both options have some problems. It is then argued that the hypothesis can be extended to a symmetric landscape, in which there is also a part after perfect similarity.

The ethological approach proposed is focused on the function of behavior, related to the environment in which the species is evolved. It states that instead of aiming for human similarity, we should aim that the robot is most suited to the function and environment that it will need to operate in. This way, the uncanny valley is avoided on both sides of the landscape. A robot designed in this way, would have its own niche in the environment. This approach has the following benefits:

• Robots have their own evolution, without interfering with that of the human they interact with
• There is no competition between humans and robots
• If the robots function is no longer needed, or it does not live up to the humans expectations, it can simply be seen as irrelevant and go extinct.

The interaction between robots and humans can be linked to that of humans and dogs. In this relationship, the human interact with a morphologically very different species, which also behaves differently, in a sophisticated way. Dogs have a certain social competence, something that a social robot will also need to get so they can be integrated in society. This approach of ethorobotics suggests that social robots should be seen as a new species, and have their own niche in the environment at hand. In this way, the similarity to humans is irrelevant. Only resemblances to humans will be those needed to do its function. [2]

References

[3]

• Legged robots- an overview https://journals.sagepub.com/doi/pdf/10.1177/0142331207075610
• Robots that can adapt like animals https://www.nature.com/articles/nature14422
• Ethorobotics: A New Approach to Human-Robot Relationship https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5465277/