Epi: An open humanoid platform for developmental robotics

Johansson, Birger; Tjøstheim, Trond A.; Balkenius, Christian

doi:10.1177/1729881420911498

Cited by 12 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, multitask robots navigate dynamic systems and can perform multiple tasks simultaneously. Both these types of robots and systems are prevalent in different realworld applications, such as medical robots (Davies et al, 2000;, prosthetic arms (Fazeli et al, 2019), humanoid platforms (Johansson et al, 2020), and automated driving (Spielberg et al, 2019). These applications offer critical opportunities to advance the design of robot systems further.…”

Section: Advances In Neuro-robotics and Robotic Failures Go Hand In Handmentioning

confidence: 99%

When neuro-robots go wrong: A review

Khan

Olds²

2023

Front. Neurorobot.

View full text Add to dashboard Cite

Neuro-robots are a class of autonomous machines that, in their architecture, mimic aspects of the human brain and cognition. As such, they represent unique artifacts created by humans based on human understanding of healthy human brains. European Union’s Convention on Roboethics 2025 states that the design of all robots (including neuro-robots) must include provisions for the complete traceability of the robots’ actions, analogous to an aircraft’s flight data recorder. At the same time, one can anticipate rising instances of neuro-robotic failure, as they operate on imperfect data in real environments, and the underlying AI behind such neuro-robots has yet to achieve explainability. This paper reviews the trajectory of the technology used in neuro-robots and accompanying failures. The failures demand an explanation. While drawing on existing explainable AI research, we argue explainability in AI limits the same in neuro-robots. In order to make robots more explainable, we suggest potential pathways for future research.

show abstract

Section: Advances In Neuro-robotics and Robotic Failures Go Hand In Handmentioning

confidence: 99%

When neuro-robots go wrong: A review

Khan

Olds²

2023

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…Towards this end we have designed the robot Epi (Figure 1), which is an attempt at an honest humanoid design in the sense that it is clear that it is a robot while it still tries to mimic the details of human-human interaction and reproduce a number of subtle non-verbal signals (Johansson et al, 2020). The overall design of the robot is in no way unique.…”

Section: Toward An Honest Robot Designmentioning

confidence: 99%

“…The physically animated pupils of Epi can be used to communicate with humans in a way that influences them in a unconscious way (Johansson et al, 2020). The control system uses a model of the brain systems involved in pupil control to let the pupil size reflect a number of inner processes including emotional and cognitive functions (Johansson and Balkenius, 2016;Balkenius et al, 2019).…”

Section: Toward An Honest Robot Designmentioning

confidence: 99%

Almost Alive: Robots and Androids

Balkenius

Johansson

2022

Front. Hum. Dyn.

Self Cite

View full text Add to dashboard Cite

Life-likeness is a property that can be used both to deceive people that a robot is more intelligent than it is or to facilitate the natural communication with humans. Over the years, different criteria have guided the design of intelligent systems, ranging from attempts to produce human-like language to trying to make a robot look like an actual human. We outline some relevant historical developments that all rely on different forms of mimicry of human life or intelligence. Many such approaches have been to some extent successful. However, we want to argue that there are ways to exploit aspects of life-likeness without deception. A life-like robot has advantages in communicating with humans, not because we believe it to be alive, but rather because we react instinctively to certain aspects of life-like behavior as this can make a robot easier to understand and allows us to better predict its actions. Although there may be reasons for trying to design robots that look exactly like humans for specific research purposes, we argue that it is subtle behavioral cues that are important for understandable robots rather than life-likeness in itself. To this end, we are developing a humanoid robot that will be able to show human-like movements while still looking decidedly robotic, thus exploiting the our ability to understand the behaviors of other people based on their movements.

show abstract

“…The robot was able to successfully interact in real time with a diverse group of people, accurately detecting a person's facial expression and computing the appropriate emotional response, happy for smiling, distressed for frowning, and neutral for a neutral FIGURE 13 | Examples of neurorobotics increasing AI understandability through interaction with people. (A) Epi, a humanoid child-like robot with the ability to change iris color and pupil size (Johansson et al, 2020). (B) Berenson, a humanoid robot capable of making facial expressions in line with its emotions regarding different art pieces (Pereira, 2016).…”

Section: Neuromorphic Robotsmentioning

confidence: 99%

“…The physical display of arousal works as a social cue, affecting interactions with other agents. Through a special eye design involving circles of overlapping blades as irises (Johansson et al, 2020), they showed that a robot can display mental state through stages of alertness and arousal during problem solving and decision making ( Figure 13A). An image of the robot is seen in Figure 13B.…”

Section: Affective Cognitionmentioning

confidence: 99%

Neurorobots as a Means Toward Neuroethology and Explainable AI

et al. 2020

View full text Add to dashboard Cite

Understanding why deep neural networks and machine learning algorithms act as they do is a difficult endeavor. Neuroscientists are faced with similar problems. One way biologists address this issue is by closely observing behavior while recording neurons or manipulating brain circuits. This has been called neuroethology. In a similar way, neurorobotics can be used to explain how neural network activity leads to behavior. In real world settings, neurorobots have been shown to perform behaviors analogous to animals. Moreover, a neuroroboticist has total control over the network, and by analyzing different neural groups or studying the effect of network perturbations (e.g., simulated lesions), they may be able to explain how the robot's behavior arises from artificial brain activity. In this paper, we review neurorobot experiments by focusing on how the robot's behavior leads to a qualitative and quantitative explanation of neural activity, and vice versa, that is, how neural activity leads to behavior. We suggest that using neurorobots as a form of computational neuroethology can be a powerful methodology for understanding neuroscience, as well as for artificial intelligence and machine learning.

show abstract

Epi: An open humanoid platform for developmental robotics

Cited by 12 publications

References 27 publications

When neuro-robots go wrong: A review

When neuro-robots go wrong: A review

Almost Alive: Robots and Androids

Neurorobots as a Means Toward Neuroethology and Explainable AI

Contact Info

Product

Resources

About