Context and objectives

Quadruped robots have have seen rapid growth over the past decade, after a major breakthrough established with MIT Cheetah [Seok13, Katz19]. They provide robust mobility and remarkable agility in unstructured environments. They are almost systematically based on a similar rigid architecture, equipped with quasi direct drive pancake motors all positioned in the torso to minimize leg inertia [Wensing17]. Such rigid structures favor model accuracy and control tractability [Wensing23], but they also limit impact absorption and prevent the robot from exploiting local flexibility to improve mobility. Although quadrupeds are mature, their performance is plateauing far below that of biological counterparts.

Context and objective

The Extender project, led by a consortium of both academic, industrial and medical partners, aims at applying approaches developed in collaborative robotics research to assistive technology for people with disabilities. Indeed, installing an assistance robotic arm on a wheelchair is foreseen as an opportunity to help individuals with limited arm or hand mobility perform complex tasks, offering greater autonomy. This requires a user-centered approach to ensure the technology meets specific needs, is adaptable, and easy to use, driving adoption. This project is part of the France 2030 program, which promotes the transfer of technological building blocks from laboratories to innovative companies. The involved robotics research partners, such as the Auctus team, apply state-of-the-art robotic control approaches to propose innovative solutions for disability assistance. We specifically focus on developing a range of control methods, that vary teleoperation modalities and levels of robotic assistance, while enforcing safety constraints to ensure secure human-robot interaction. All developments are integrated and tested in real-world settings with the EXPLORER arm from the industrial partner ORTHOPUS.

Context and objectives

Recent progress in assistive robotics and human-robot collaboration could enable a reorganization of activities as a means to preserve the health of human workers by improving their working conditions. At the same time, this approach could enhance the value of human expertise and skills. However, although collaborative robots tend toward light-weight architectures, suited to the safety needs of physical interaction with humans, they remain designed with maximum performance and versatility in mind. This quest of versatility results in fixed and oversized robotic solutions, which are the sum of the prerequisites for all the tasks considered. When climate change makes environmental resources scarcer, such oversized robots may no longer be acceptable; instead, more specialized robots tailored to the specific needs of each activity should be considered. While the protection of workers’ health must be a universal societal concern, the accessibility and sustainability of robotic assistance solutions can no longer be ignored in our design approaches.

Context

The Extender project, led by a consortium of both academic, industrial and medical partners, aims at applying approaches developed in collaborative robotics research to assistive technology for people with disabilities. Indeed, installing an assistance robotic arm on a wheelchair is foreseen as an opportunity to help individuals with limited arm or hand mobility perform complex tasks, offering greater autonomy. This requires a user-centered approach to ensure the technology meets specific needs, is adaptable, and easy to use, driving adoption. This project is part of the France 2030 program, which promotes the transfer of technological building blocks from laboratories to innovative companies.

Context and objective

Recent progresses in assistive robotics and human-robot collaboration could make a reorganization of activities possible, to preserve the health of human workers by improving their working conditions, while enhancing the value of human expertise and skills. Among industrial assistive solutions, exoskeletons are particularly promising as they provide motion-force support through direct interaction with the operator [DeLooze16],[Voilqué19].

Context and objective

Recent progresses in robotics allowed robots to be in physical contact with humans to assist them while keeping them safe. However, this physical assistance can produce a loss of feeling of control of the user when interacting with such robotics devices. This loss of feeling of control, or loss of agency [1], is well documented when interacting with more autonomous systems [2], but its sensorimotor mechanism is still not fully understood when the interaction is physical.

Context and objective

Recent progresses in assistive robotics and human-robot collaboration could make a reorganization of activities possible, to preserve the health of human workers by improving their working conditions, while enhancing the value of human expertise and skills. However, although collaborative robots tend toward light-weight architectures, suited to the safety needs of physical interaction with humans, they remain designed with maximum performance and versatility in mind. This quest of versatility results in fixed and oversized robotic solutions, which are the sum of the prerequisites for all the tasks considered. When climate change makes environmental resources scarcer, and while the protection of workers’ health must be a universal societal concern, the accessibility and sustainability of robotic assistance solutions can no longer be ignored in our design approaches.

Context and objective

Recently, modern robot control techniques based on numerical optimization have shown their potential in automating the synthesis and execution of complex motions online. This lies at the core of the impressive robot behaviors that have been seen recently on real hardware. But this effervescent research has also led to a fragmentation of the software landscape. Indeed, major optimal control libraries (Crocoddyl [1], Aligator [2], etc.) and especially solvers (mim_solvers [3], Acados [4], etc.) usually offer distinct APIs, making benchmarking difficult for specialists and increasing the barrier of entry to the field for non-specialists. In particular, mim_solvers [3] is a state-of-the-art numerical solver but only available for Crocoddyl users^{1 2}.

Context and objective

Recent progresses in assistive robotics and human-robot collaboration could make a reorganization of activities possible, to preserve the health of human workers by improving their working conditions, while enhancing the value of human expertise and skills. However, although collaborative robots tend toward light-weight architectures, suited to the safety needs of physical interaction with humans, they remain designed with maximum performance and versatility in mind. This quest of versatility results in fixed and oversized robotic solutions, which are the sum of the prerequisites for all the tasks considered. When climate change makes environmental resources scarcer, and while the protection of workers’ health must be a universal societal concern, the accessibility and sustainability of robotic assistance solutions can no longer be ignored in our design approaches.

Context and objective

The scapulo-humeral rhythm, defined as the kinematic coordination between the scapula and the humerus during arm elevation, is a fundamental mechanism for shoulder mobility and stability. A precise understanding of this rhythm is crucial for clinical diagnosis, rehabilitation planning, and the design of assistive systems. However, its exact nature remains debated, particularly regarding the influence of muscular activation (in vivo conditions) versus purely mechanical and ligamentous constraints (simulated ex vivo using cadaveric specimens).

Context and problem statement

While the first industrial robots were conceived to relieve humans from strenuous and hazardous tasks, robots are now primarily seen as a means to enhance productivity - both in mass production environments and in settings that demand industrial agility. Nevertheless, humans remain, for both organizational and societal reasons, the cornerstone of industry at large. Fully replacing them is still far from being technically feasible - despite the media hype following recent advancements in artificial intelligence - and remains highly debatable from a societal model perspective. It is therefore of paramount importance to continue improving workers’ health and working conditions. This is not only an ethical imperative but also an economic necessity [1], particularly in the context of a rapidly aging European workforce.

Context

A postdoctoral position is opened within the Inria-KAIST partnership. It is part of the SHAARE associate team, initiated between the Auctus team at Inria and the IRiS lab at KAIST that focuses on haptics and shared teleoperation. Together, we aim at developing shared-control approaches that, either, better guide the human through adaptive haptic guidance, or adjust the robot behavior according to the human gestures.

The postdoc contract will have a duration of 12 to 24 months. The start date will be between November 1st, 2024, and not later than January 1st, 2025, depending on the candidate availability. The postdoctoral fellow will be recruited by the Inria center of the University of Bordeaux (Auctus team) in France, where he/she will start the research contract. The project duration will be half-time divided between France and South Korea, with exchange periods at KAIST (IRiS lab) to share the works and progresses.

Positioning and Objectives

The Inria Center at the University of Bordeaux hosts various research teams that incorporate robots into their projects (e.g. Auctus team or Manao team). The Experimental and Development Service (SED) is responsible for establishing and maintaining the experimental platforms of the center, including the maintenance of its robots. These robots operate within ecosystems that encompass various sensors such as cameras and lasers, and they are controlled using the ROS middleware. Currently, ROS2, the second version of ROS, is at a relatively stable development stage, and we are seeking to migrate all of our platforms to ROS2. Furthermore, Inria has recently acquired a new robot, a KUKA IIWA 14. The objective of this internship is to commission this robot and then develop a ROS2-based solution that can seamlessly integrate into the existing experimental environment.

Context

This internship is part of a research project on haptic guidance. Haptic guidance provides force feedback to help an operator to remotely operate a robot thanks to a haptic interface. The purpose of these forces is to induce a certain behavior of the robot with respect to the task, such as following a reference trajectory or applying a precise interaction force. The advantage of using such guidance methods is to relieve the user’s cognitive workload during the teleoperation through proper assistance, while allowing him to control the task.

Context

Recent progresses in robotics, which tend toward assistive systems or versatile collaborative robots, could make a reorganization of industrial sites possible in order to preserve the health of human workers, by improving their working conditions, while enhancing the value of human expertise and skills. Such a transformation of work requires to rethink robotic control approaches, both in terms of safety and physical capabilities, to enable the robots to help humans in their activity and evolve in a shared environment. The conventional architectures of industrial robots, which are heavy and rigid, must also be adapted to the needs of interaction with humans (safety, perception), in the present context of climate change that cannot be ignored (energy consumption).

Context

A postdoctoral position is opened in collaboration between the AUCTUS team at Inria and the IRiS lab at KAIST, about shared control and skill transfer in haptic teleoperation.

The postdoc contract will have a duration of one year, later extendable. The postdoctoral fellow will be recruited at the Inria center of the University of Bordeaux (AUCTUS team), where he/she will start the research project. A six-month exchange period will be planned at KAIST (IRiS lab) to share the works and progresses.

Contexte

Dans le cadre des tâches de télérobotique et de collaboration homme-robot, il est essentiel de connaître à tout moment la position des objets dans l’environnement du robot. Cela peut être réalisé à l’aide de divers capteurs : parmi ceux-ci, les systèmes de motion capture constituent une option intéressante.

Ces systèmes correspondent à un ensemble de caméras infrarouges, capables de déterminer les poses 3D de corps rigides à haute fréquence. Cependant, l’estimation de ces poses peut être erronée ou impossible, principalement à cause d’une absence de visibilité de l’objet par un nombre suffisant de caméras. Assurer l’efficacité de ce système nécessite alors un positionnement optimisé des caméras dans l’espace devant être observé. [1]

Contexte

Vous êtes spécialisé.e ou passionné.e de robotique? Vous aimez résoudre des problèmes complexes et concrets ?

Le Service de Robotique Interactive du CEA Tech et l’équipe Auctus du centre Inria de l’Université de Bordeaux sont deux équipes spécialisées dans le domaine de l’interaction homme-robot et le développement des robots collaboratifs du futur. Leurs activités couvrent notamment les domaines de la robotique d’assistance au geste, la cobotique (COllaborative roBOTICS), les exosquelettes mais aussi la télé-manipulation. Pour piloter ces robots, les laboratoires développent leurs propres outils logiciels, du contrôleur robotique temps réel aux IHM de supervision 3D et de programmation intuitive. Les vidéos suivantes fournissent un aperçu des travaux des deux équipes:

A propos du centre ou de la direction fonctionnelle

Le centre Inria Bordeaux - Sud-Ouest est un des neuf centres d’Inria et compte une vingtaine d’équipes de recherche. Le centre Inria est un acteur majeur et reconnu dans le domaine des sciences numériques. Il est au cœur d’un riche écosystème de R&D et d’innovation : PME fortement innovantes, grands groupes industriels, pôles de compétitivité, acteurs de la recherche et de l’enseignement supérieur, laboratoires d’excellence, institut de recherche technologique…

Entreprise et responsable industriel de la thèse

Farm3, Verrières de Joux (25) & Paris

• Romain SCHMITT, Président Farm3, romain.schmitt@farmcube.eu

Laboratoires partenaires et encadrement de la thèse

Equipe AUCTUS, Inria Bordeaux Sud-Ouest, Talence (33)

• David DANEY, Chargé de Recherche Inria, HDR, directeur de l’équipe AUCTUS, david.daney@inria.fr

Equipe RoBioSS, Institut Pprime - CNRS, Université de Poitiers (86)

• Margot VULLIEZ, Maîtresse de Conférences, équipe RoBioSS, margot.vulliez@univ-poitiers.fr

Contexte et objectifs du projet

La société Farm3 développe Le Cube, une ferme de culture verticale robotisée et basée sur une technologie innovante à ultrasons (Fig.1). Ce nouveau mode de culture, dite culture en ultraponie [Brevet n° FR2001534], dans un espace fermé et contrôlé, assure un niveau d’oxygénation optimal et fournit la bonne quantité d’eau et de nutriments aux plantes. Le Cube favorise ainsi une production locale et de qualité d’espèces variées, en réduisant drastiquement les ressources en eau requises pour leur culture. Pour conserver le climat de croissance idéal pour les plantes, il est important de limiter la présence humaine dans le Cube. Cependant, certaines actions sur les plantes (éclaircir les semis, retirer les feuilles abimées, polliniser les fleurs…), pendant la croissance ou au moment de la récolte, demandent une expertise importante de l’ouvrier agricole. La téléopération est une solution qui permettrait, en ce sens, de préserver les compétences et le savoir-faire de l’humain sur ces gestes spécialisés, sans polluer l’environnement sensible de culture. Un bras robotique et un préhenseur, dédiés à la culture maraîchère en ultraponie, ont été conçus et intégrés au Cube pour réaliser ces opérations agricoles. Ils seront pilotés par l’agriculteur depuis l’extérieur du Cube, grâce à une interface de téléopération et un écran tactile, augmentée de suffisamment d’informations visuelles et haptiques sur les plantes et l’environnement pour pouvoir réaliser la tâche à distance.

Lieu du stage et encadrement

Le stage sera effectué dans le cadre d’une collaboration entre l’équipe projet AUCTUS (INRIA Bordeaux Sud Ouest, Rezzoug Nasser) et le laboratoire PsyClé EA 3273 (Université Aix-Marseille, Brice Isableu). Le stage se déroulera dans les locaux du laboratoire PsyClé (Aix en Provence) sous la direction de Brice Isableu (PU, centre PsyClé) pour les aspects contrôle moteur et de Nasser Rezzoug (MCF HDR, équipe projet AUCTUS BSO) pour les aspects biomécaniques.

The Auctus team focuses on developing the robot control and analysis techniques suitable for human-robot physical interaction, taking in consideration the true limitations/capabilities of the robot and its human counterpart. In order to gather real-time knowledge about the human’s capabilities it is necessary to measure its posture (joint angles, positions,…) in real-time as well. More specifically, in many cases we are only interested in acquiring posture of a specific part of the human body, for example the upper body, or one arm.