NAO robot. Image credits: Stephen Chin on Flickr [CC BY 2.0]
Created by the French company ‘Aldebaran Robotics’ in 2008, and acquired by ‘Softbank Robotics Japan’ in 2015, NAO is an autonomous and programmable humanoid robot that has been successfully applied to research and development applications for children and adults. More than 13,000 NAO robots are used in more than 70 countries around the world. Pretty much every lab working in human-robot interaction research owns a NAO making it the social robot that has been the most used in the history of the field.
In our paper ‘10 Years of Human-NAO Interaction Research: A Scoping Review’ published in Frontiers in Robotics and AI, we present an overview of the evolution of NAO’s technical capabilities. We also present the main results from a scoping review of the human-robot interaction research literature in which NAO was used.
Appearance-wise, NAO hasn’t aged a bit. The childish anthropomorphic appearance of the robot has stayed pretty much the same over the last 10 years. However, a lot of improvement has been made over the last versions of the robots.
Evolution of the NAO robot’s technical characteristic since 2008
We also note that the software environment for the robot has also improved over the years integrating new technologies and features as years passed: face recognition and tracking, semantic engine. The NAOqi API also supports various programming languages. In 2013, Aldebaran also created a developer community. This community platform allowed to share resources, behaviours and featured a forum. This has probably participated a lot in the expansion and adoption of robot with developers and researcher sharing designs of behaviours, and other games they developed with the robot.
Geographical distribution of the papers included in our scoping review
The geographical distribution of authors using NAO for their research in HRI is unprecedented for a social robot. NAO has been used in more than 50 countries all around the world. And we see from the above map that the distribution is well split between North-America, Europe and Asia. But still, just like in a lot of research field the global north, tends to publish more than southern countries.
In terms of the role of the robot, researchers have investigated different application domain with the robot being used as a peer or a demonstrator in public spaces, an educational and assistant for therapists (for children with ASD, learning disability or hearing disability) being the dominant ones.
Input data (left), output data (middle), equipment (right) for each application field
As mentioned above, NAO is equipped with various sensors and actuators allowing for multi-modal interaction. Often researchers have used the robot to speak and/or make gestures. On the perception side, the robot’s limited speech recognition and poor microphone quality refrained researcher to use NLP but instead made them rely on facial, and gesture recognition. We also noted in our analysis that researchers often used external devices such as RGBD cameras or tablets in order to capture other signals allowing to assess the situation.
Multiple studies reported how fun and enjoyable was the appearance of the robot. NAO is certainly not just an eye-catcher robot as its portability is highly appreciated by the researchers. NAO can be regarded as a plug-and-play robot due to its robust and easy setup characteristics. It has also been found affordable compared to other humanoid robots.
On the other side, several technical issues were reported such as low battery life and overheating issues. The speech recognition limits the interaction distance and context (i.e. noisy environments). Finally, not much embedded autonomous functionality could be used in the initial versions.
Over the years, several types of communities have formed around the NAO robotic platform.
In 2010, the University of Tokyo piloted a new educational program developed by Aldebaran Robotics that aimed to train students to use NAO. Along with some discounts to buy NAO for educational purposes, the company released some ebooks. The books and educational program cover both technical aspects of using the robot as well as more creative projects that can be given as exercise to students. The educational market certainly helped in making NAO widely used in the 2010’s.
In 2007, the Robocup decided to use the NAO robot as the official platform for its soccer league. As detailed in the review, this led to fruitful advancement on technical capabilities of the robot such as its locomotion and vision system.
More recently, the introduction of the Pepper robot as a new platform for the robocup@Home challenge certainly can let us think that it will boost the robot’s economical life and produce more advances in social and at home tasks with the robot.
Aldebaran had a strong Research & Development strategy in its early days and naturally became partner of several large European projects: ALIZ-E, DREAM, SQUIRREL, L2Tor. These strategies had the advantage to form the future researchers in the use of their platform and made NAO a dominant robot in human-robot interaction research between 2015 and 2019.
Image from RobotLab website visited on December 20th 2021
Recently a network of start-ups has woven around the NAO robot. Providing various services such as educational workshops, therapeutic sessions, or business and marketing services, the number of these start-ups have raised these past few years (e.g. Interactive Robotics, RobotLAB and Avatarion).
In our review, we present a comprehensive overview on the use of NAO, which is a remarkable social robot in many instances. So far, NAO has been exposed to a challenging yet rewarding journey. Its social roles have expanded thanks to its likeable appearance and multi-modal capabilities followed by its fitness to deliver socially important tasks. Still, there are gaps to be filled in view of sustainable and user-focused human-NAO interaction. We hope that our review can contribute to the field of HRI that needs more reflection and general evidence on the use of the social robots, such as NAO in a wide variety of contexts. An implication of the findings shows a greater need for increasing the value and practical application of NAO in user-centered studies. Future studies should consider the importance of real-world and unrestricted experiments with NAO and involve other humans that might facilitate human-robot interaction.
Front view of the flying robot. Image credit: Dr Tim Helps
This new advance, published in the journal Science Robotics, could pave the way for smaller, lighter and more effective micro flying robots for environmental monitoring, search and rescue, and deployment in hazardous environments.
Until now, typical micro flying robots have used motors, gears and other complex transmission systems to achieve the up-and-down motion of the wings. This has added complexity, weight and undesired dynamic effects.
Taking inspiration from bees and other flying insects, researchers from Bristol’s Faculty of Engineering, led by Professor of Robotics Jonathan Rossiter, have successfully demonstrated a direct-drive artificial muscle system, called the Liquid-amplified Zipping Actuator (LAZA), that achieves wing motion using no rotating parts or gears.
The LAZA system greatly simplifies the flapping mechanism, enabling future miniaturization of flapping robots down to the size of insects.
In the paper, the team show how a pair of LAZA-powered flapping wings can provide more power compared with insect muscle of the same weight, enough to fly a robot across a room at 18 body lengths per second.
They also demonstrated how the LAZA can deliver consistent flapping over more than one million cycles, important for making flapping robots that can undertake long-haul flights.
The team expect the LAZA to be adopted as a fundamental building block for a range of autonomous insect-like flying robots.
Dr Tim Helps, lead author and developer of the LAZA system said: “With the LAZA, we apply electrostatic forces directly on the wing, rather than through a complex, inefficient transmission system. This leads to better performance, simpler design, and will unlock a new class of low-cost, lightweight flapping micro-air vehicles for future applications, like autonomous inspection of off-shore wind turbines.”
Professor Rossiter added: “Making smaller and better performing flapping wing micro robots is a huge challenge. LAZA is an important step toward autonomous flying robots that could be as small as insects and perform environmentally critical tasks such as plant pollination and exciting emerging roles such as finding people in collapsed buildings.”
The 35th conference on Neural Information Processing Systems (NeurIPS2021) featured eight invited talks. In this post, we give a flavour of the final presentation.
Radhika’s research focusses on collective intelligence, with the overarching goal being to understand how large groups of individuals, with local interaction rules, can cooperate to achieve globally complex behaviour. These are fascinating systems. Each individual is miniscule compared to the massive phenomena that they create, and, with a limited view of the actions of the rest of the swarm, they achieve striking coordination.
Looking at collective intelligence from an algorithmic point-of-view, the phenomenon emerges from many individuals interacting using simple rules. When run by these large, decentralised groups, these simple rules result in highly intelligent behaviour.
The subject of Radhika’s talk was army ants, a species which spectacularly demonstrate collective intelligence. Without any leader, millions of ants work together to self-assemble nests and build bridge structures using their own bodies.
One particular aspect of study concerned self-assembly of such bridges. Radhika’s research team, which comprised three roboticists and two biologists, found that the ants created bridges adapt to traffic flow and terrain. The ants also disassembled the bridge when the flow of ants had stopped and it wasn’t needed any more.
The team proposed the following simple hypothesis to explain this behaviour using local rules: if an ant is walking along, and experiences congestion (i.e. another ant steps on it), then it becomes stationary and turns into a bridge, allowing other ants to walk over it. Then, if no ants are walking on it any more, it can get up and leave.
These observations, and this hypothesis, led the team to consider two research questions:
There were two motivations for these questions. Firstly, the goal of moving closer to realising robot swarms that can solve problems in a particular environment. Secondly, the use of a synthetic system to better understand the collective intelligence of army ants.
Screenshot from Radhika’s talk
Radhika showed a demonstration of the soft robot designed by her group. It has two feet and a soft body, and moves by flipping – one foot remains attached, while the other detaches from the surface and flips to attach in a different place. This allows movement in any orientation. Upon detaching, a foot searches through space to find somewhere to attach. By using grippers on the feet that can hook onto textured surfaces, and having a stretchable Velcro skin, the robots can climb over each other, like the ants. The robot pulses, and uses a vibration sensor, to detect whether it is in contact with another robot. A video demonstration of two robots interacting showed that they have successfully created a system that can recreate the simple hypothesis outlined above.
In order to investigate the high-level properties of army ant bridges, which would require a vast number of robots, the team created a simulation. Modelling the ants to have the same characteristics as their physical robots, they were able to replicate the high level properties of army ant bridges with their hypothesized rules.
You can read the round-ups of the other NeurIPS invited talks at these links:
#NeurIPS2021 invited talks round-up: part one – Duolingo, the banality of scale and estimating the mean
#NeurIPS2021 invited talks round-up: part two – benign overfitting, optimal transport, and human and machine intelligence
The roboticist Nialah Wilson along with the modular robot platform DONUts. [Image Credit: Scalable and Robust Fabrication, Operation, and Control of Compliant Modular Robots by Wilson*, Ceron*, Wilson, Horowitz and Petersen.]
The DONUts platform may look like a collection of bronze-colored, futuristic coffee cups, but everything becomes clearer as they begin to move. The group of modular robots dance in a well-choreographed symphony as magnets turn on and off allowing the modules to pull or push their neighbors. Using these simple interactions, the modular robots can achieve complex tasks such as energy harvesting [1].
Nialah Wilson is one of the key roboticists who helped bring these modular robots to life. Her team at the Collective Embodied Intelligence Lab from Cornell University needed to:
Taking advantage of the right message, passed at the right time, is also one of the things that led to Nialah’s career in robotics.
One of the competitions that I did in high school was through the NAACP, and I only heard about that because of someone in my church, and I only knew about that because I talked to them.
— Nialah
We are excited to highlight Nialah’s robotics journey as well as the lessons she learned along the way in this ‘Meet the Members’ post for Black In Robotics.
Nialah is from rural, Southwestern Virginia. A place that she is sure to remind you is the South. Despite the rural setting, Nialah had a plethora of opportunities to keep her curious mind busy.
I was always interested in taking stuff apart. My mom would always find different things like pens … destroyed around the house.
— Nialah
Her mom was wise enough to channel young Nialah’s knack for constructing and deconstructing devices into a competitive arena: robotics competitions.
“I was all-in” Nialah recalls when she talks about this time in her life. Initially, she was doing FIRST Lego Robotics League competitions in middle school and, later on, she was participating in whatever competitions she could find in high school (one of them being the longstanding tradition hosted by Virginia Western). Nialah’s experience made it a no-brainer for her to decide upon a degree in Mechanical Engineering when she arrived at Howard University.
She leveraged Howard’s powerful connections across the country to obtain a summer position at Sandia National Laboratories. Sandia had a lasting impact on Nialah; not only did she produce great work characterizing bellows systems that was later published [2], but she also found an interest in attending graduate school.
I was interested in grad school before [my internship at Sandia], but after that I was like ‘I gotta do a PhD.’ … I saw that the people doing the leading and pushing stuff forward all had PhDs and so I was like ‘Oh!’ if I get a PhD, then this can be my life…
— Nialah
When the time came to apply to graduate school, her mentor from Sandia was one of the key recommendation letters that supported her strong application.
Ultimately, Nialah picked the Collective Embodied Intelligence Lab at Cornell University for her PhD studies. There, she has moved away from working with experimental fluid theory and now works on many aspects of modular robots like the ones discussed above. To make groups of these robots achieve tasks in unstructured environments, she studies how to plan the group’s movement using gradient-based methods as well as how to make a group robust if an individual robot fails. In the future, she hopes to work more on how groups of such robots or drones interact with humans (i.e. Human Robot Interaction).
A group photo of the Collective Embodied Intelligence Lab at Cornell University including an excited Ms. Wilson (top left).
With the support of her strong Sandia mentor and others in her life, Nialah was well-prepared for many aspects of graduate school but highlighted a few challenges that she still had to overcome:
What makes these challenges difficult is that they’re typically all arising at the same time.
I was figuring out [all of this] while taking different courses.
— Nialah
She recommended that graduate students try the following to prevent or overcome these challenges as well:
Finally, Nialah offered the following words of wisdom for young roboticists:
One thing that I would say [to a younger version of myself] is: Look more into the different aspects of robotics, because robotics is a really big field. And I didn’t fully get [that] until I got to grad school…
— Nialah
And a few words for young people in general:
…that’s the biggest thing; finding people that are in the positions that I want to be in or are around those things and then reaching out to and talking to them. You learn new things and it opens doors for yourself as well.
— Nialah
If you would like to follow more of Nialah’s exploits, then feel free to follow her Google Scholar profile or her personal website.
[1] S. Ceron, N. Wilson, L. Horowitz and K. Petersen, “Comparative Analysis of Sensors in Rigid and Deformable Modular Robots for Shape Estimation,” 2019 International Symposium on Multi-Robot and Multi-Agent Systems (MRS), New Brunswick, NJ, USA, 2019, pp. 252–258, doi: 10.1109/MRS.2019.8901072.
[2] Nialah Jenae Wilson, “Bellows Characterization for Dynamic Systems with Damping and Multiphase Flow..” United States: N. p., 2015. Web.
Drafts of this article were corrected and improved by Nialah Wilson, Sophia Williams, and Nailah Seale. All current errors are the fault of Kwesi Rutledge. Please reach out to him if you spot any!