Abstract
Publications home
Ad-hoc creativity methodology for haptic technologies
at
| Cécile Boulard, Sophie Zijp-Rouzier |
| 20th International Conference of the International Ergonomics Association (IEA), Florence, Italy, 26-30 August, 2018 |
| Download |
In many project, ergonomists may find themselves in a situation where engineering teams create a breakthrough technology, without any well-defined use case. This situation is not the one preferred by the ergonomists where prospective ergonomics would rather aim at identifying needs at earlier stage in design projects before finding appropriate technologies (Brangier and Robert, 2012). The intervention described in this paper relates to a new haptic technology and our goal as ergonomists in the project is focused on the possible use cases. We are typically in a techno-push context. The technology considered is about reproducing textures. There are two main difficulties for this kind of technology when considering the use cases. The first one relates to the specificities of the haptic technologies and our ability to discuss on sense of touch. Literature shows that we have difficulties to discuss and that we miss vocabulary to describe our feelings with the sense of touch (Dagman et al., 2010; O’Sullivan and Chang, 2006; Obrist et al., 2013). The other difficulty is the interaction situation that is imposed by the technology. If one wants to feel a texture, he needs to touch the surface while having a lateral movement. The specificities of this interaction situation make it difficult to bring people discuss potential use cases while the context of use is so specific and limited.
In order to generate ideas of use cases two methodologies are used in the project. The first one is a classical focus group lead by expert designers. Here the creativity is based on the group discussion.
The second methodology starts from the technology. The aim is to ask testers of the prototype to reflect upon the possible appropriate use cases. In the context of a perception test of textures on the prototype, we recruited 20 participants to follow our ad hoc methodology. The methodology is in two stages:
– Just after the test, the participants have an interview where they are invited to describe the possible use cases they can identify or imagine. Then there is a recall of the specificities of texture rendering. At the end of the interview, the participants are invited to think about the technology for a couple of days and then have another interview.
– Two days later, the participants are once more contacted to provide possible new use cases.
As a conclusion we can say that both methodologies can be seen as complementary. The ad hoc methodology permitted to have more targeted uses and very specific niches were identified for use cases. The drawback of such methodology is that we miss the group dynamic we can find in focus groups.
To make robots autonomous in real-world everyday spaces, they should be able to learn from their interactions within these spaces, how to best execute tasks specified by non-expert users in a safe and reliable way. To do so requires sequential decision-making skills that combine machine learning, adaptive planning and control in uncertain environments as well as solving hard combinatorial optimisation problems. Our research combines expertise in reinforcement learning, computer vision, robotic control, sim2real transfer, large multimodal foundation models and neural combinatorial optimisation to build AI-based architectures and algorithms to improve robot autonomy and robustness when completing everyday complex tasks in constantly changing environments.
VISION
The research we conduct on expressive visual representations is applicable to visual search, object detection, image classification and the automatic extraction of 3D human poses and shapes that can be used for human behavior understanding and prediction, human-robot interaction or even avatar animation. We also extract 3D information from images that can be used for intelligent robot navigation, augmented reality and the 3D reconstruction of objects, buildings or even entire cities.
Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios.
Furthermore, we believe that a modern computer vision system needs to be able to continuously adapt itself to its environment and to improve itself via lifelong learning. Our driving goal is to use our research to deliver embodied intelligence to our users in robotics, autonomous driving, via phone cameras and any other visual means to reach people wherever they may be.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.