Team Projects

Funded by the French Ministry of Education and Research and the French National Research Agency (ANR-17-CE22-0010)

Autonomous vehicles typically function well on large roads i.e. in structured and predictable environments. However and increasing trend in urban design is to promote shared spaces where segregation between pedestrains and vehicles is minimised by removing features such as kerbs, road markings, traffic signs and traffic lights. The context of the work is to focus on safe and predictable interaction between cyber-cars and other road users in complex and human populated urban environments (i.e. shared spaces). A social and cognitive dimension is required in the intelligent vehicles so that they will follow socially adapted behaviors that will be understood and predicted by passengers and pedestrians; will communicate their intentions to move or stop; and will increase safety. The vehicles will not simply stop during uncertain situations but will be proactive and negotiate their paths and velocities, by conveying their course and direction of travel to surrounding road users.

Models of human and crowd behavior will be built in order to give the autonomous car knowledge of its social environment in the present and the near future. These models will integrate knowledge from social sciences (proxemics, behaviorism) and will use agent based simulation. The trajectories of the autonomous vehicle are expected to be safe and socially compliant and the decisions of the vehicle will be based on the estimated intentions of all agents of the scene.

MUDAMO - Integration of multidisciplinary data for crisis modelling. Financed by IXXI Complex Systems Institute, Rhône-Alpes. (2015-2017)

The strongly multidisciplinary MUDAMO project aims to promote interoperability between disciplines (human and social sciences, computer science) that are involved in simulation for crisis management. It will develop a methodology to integrate the results of questionnaires and social surveys into multi-agent models. It will also produce a survey protocol that is specifically aimed at multi-agent modelling. The MUDAMO project uses the specific example of modelling post-seismic pedestrian mobility. A novel tool will be developed to promote dialogue between researchers from diffrent disciplines. These methods and tools will be disseminated as part of a research workshop.  Partners include: PACTE Lab, MAGMA-LIG, Images Solidaires.

Finance ANR | 2014 - 2018

SOMBRERO proposes to train humanoid robots (Nina and Roméo) i.e. provide them with socio-communicative abilities by immersive teleoperation i.e. “beaming” of human pilots. The SOMBRERO project has three main objectives:

Finance PRES de Grenoble – CNRS | 2013

ACCROSH est un projet de robotique sociale humanoïde. Ce champ de recherche considère que les robots sont voués à évoluer au sein de communautés humaines et que les tâches collaboratives dans lesquelles ils s’impliquent nécessitent des compétences sociales et cognitives avancées. Notre stratégie de recherche originale vise à « doter » d’abord un ensemble de robots humanoïdes de compétences sociales par télé-opération immersive (beaming) ; puis de faire l’analyse des traces d’Interaction Homme-Robot ainsi obtenues afin de progresser vers la gestion par le robot des boucles de perception-décision-action gérées initialement par le téléopérateur. Notre consortium pluridisciplinaire (STIC et SHS) propose de mettre en place une plateforme d’expérimentation et de réaliser une étude psychosociale des ressentis et comportements d’un panel de personnes ; de comparer les facteurs d’acceptabilité de l’interaction supervisée par beaming (baseline) d’une part, et par comportements autonomes d’autre part ; d’identifier les facteurs d’acceptabilité de ces robots.

Finance ANR | 2013 - 2016

Despite recent advances in robotics around autonomous machines, machines really capable of giving a real to humans, as part of everyday life, remains limited.On the other hand, the animal, especially dogs, has shown for many years the capacity to complete the man in his life in daily tasks, such as aid for service dogs, or in exceptional events such as avalanche or earthquakes intervention, or in professional life to search for drugs, for example. Nevertheless, each system, robot or dog has its own limits, for example: a step or a hole can be fatal to a robot, a cat turns "mad" a dog. The actual idea is to take the best of both entities to increase the performance of the couple animal/robot. In this context, the subject requires extensive research in particular on the development of interaction, communication or cooperation between a robot and a dog.

The Cochise project proposes a modest focus of this research, on a particular set of dogs: service dogs for people with mobility impairments. Service dogs assist the human in the gestures of everyday life and for this purpose the problem is clearly identified. In this context, we propose to design a robot to act on and with the service dog, to build a "couple" with high performance in regard to the problem. The machine will become a mediator robot that allows on one hand to "understand" the state of the dog and retransmit it to the man, and on the other hand to enable autonomous robot via the trigger sequences of behaviors on the dog. The question underlying the Cochise project is: how far a dog will accept to obey to a robot? and what type of robot should be designed for this?

Pages