RUM

Scientific description

Robots offer a unique way to bridge the virtual and physical worlds by enriching the user experience with digital content through contextual processing of the physical environment and by acting as digital agents in the physical world.

The RHUM Action Team is exploring new forms of active perception of the physical environment and will develop adaptive forms of social communication and interaction between humans and robots, which are viewed as digital agents in the physical world. The team will also study the learning of human- and situation-aware behaviors through the online and active exploration of multimodal data streams.

Key findings and future work

Learning and Adapting Robot Behaviors for Social Interaction

Equipping robots with social and communicative skills to enable effective human-robot interaction (HRI) is a major challenge. We explore several paradigms for training multimodal behavioral models based on human demonstrations: (a) learning through observation of human-robot interactions and adapting sensorimotor events to the target robot’s capabilities [1]; (b) learning from behaviors collected via immersive teleoperation of the robot by human operators [2]. Particular attention is also given to the evaluation of these HRI behaviors, notably through original online evaluation paradigms [3].

Omar Samir Mohammed’s thesis,“Acquiring Human-Robot Interaction Skills with Transfer Learning Techniques,” supervised by Gérard Bailly and Damien Pellier, will focus on the acquisition of new interactive skills through the transfer of prior experience or skills already mastered by another robot. We will also study the decomposition of tasks into generic sensorimotor skills and interactive skills. The first application will focus on learning cursive writing through transfer from drawings (i.e., subtitling) between the GIPSA-Lab’s iCub and the LIG’s Baxter.

Human-robot motion (HRM) 

HRM involves controlling how a robot moves among people. In this context, it is essential that the robot’s movements be both safe and appropriate. Safe means that the robot must not injure people by bumping into them, and appropriate means that its movements must conform to the social and cultural norms that govern human behavior—for example, by avoiding walking between two people who are talking.

The work conducted at RHUM has focused primarily on safety. Avoiding collisions with people is a challenge because their future behavior is uncertain and difficult to anticipate. This fact precludes any notion of "absolute" safety; in other words, collisions may be unavoidable under certain circumstances. Our goal is therefore to study the level of safety achievable in a given situation. By considering a bipedal robot and using tools previously developed within the team, we proposed a strategy allowing a bipedal robot to move through a crowd while maintaining its balance and ensuring passive safety—that is, in the event of a collision, the robot will come to a stop [4]. This work was further developed during Hang Yu’s master’s internship, funded by RHUM [5], which studied a more sophisticated safety level called “friendly passive safety,” meaning that in the event of a collision with a person, the robot will come to a stop and the person will be able to avoid the collision if they choose to do so. Matteo Ciocca’s PhD, funded by RHUM and supervised by Thierry Fraichard and Pierre-Brice Wieber, will build upon and expand the work carried out in [5].

Coordinators

Gérard Bailly (GIPSA-Lab)

Pierre-Brice Wieber (Inria/LJK)

Olivier Aycard (LIG)

Valuation

Several projects round out this action team:

• PSPC 1 ROMEO 2 "Development of a humanoid robot assistant and companion for daily life" (2012–2017, LJK-BIPOP) in collaboration with ALDEBARAN
• H2020 COMANOID "Multi-Contact Collaborative Humanoids in Aircraft Manufacturing" (2015–2019, LJK-BIPOP) with AIRBUS
• ANR SOMBRERO "Immersive teleoperation of humanoid robots and learning of socio-communicative behavior models" (2014–2018, GIPSA-CRISSP, LIG-MAGMA, LIP, and Lab-STICC) in collaboration with ALDEBARAN
• Rhône-Alpes Region ARC6 TENSIVE Project: "Telepresence Robots: Immersive Social Navigation and Verbal Interaction" (2016–2019, GIPSA-CRISSP and CITI-CHROMA) featuring AWABOT and HUMANOO

Notable publications

[1] A. Mihoub, G. Bailly, C. Wolf, and F. Elisei, "Graphical models for social behavior modeling in face-to-face interaction," Pattern Recognition Letters, vol. 74, 2016.

[2] G. Gomez, C. Plasson, F. Elisei, F. Noël, and G. Bailly, "Qualitative Assessment of a Beaming Environment for Collaborative Professional Activities," in European Conference on Virtual Reality and Augmented Reality (EuroVR), 2015.

[3] N. Duc-Canh, G. Bailly, and F. Elisei, "Conducting neuropsychological tests with a humanoid robot: design and evaluation," in IEEE International Conference on Cognitive InfoCommunications (CogInfoCom), 2016.

[4] N. Bohórquez, A. Sherikov, D. Dimitrov, and P.-B. Wieber, "Safe navigation strategies for a bipedal robot walking with
s in a crowd," in IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2016.

[5] H. Yu, "Safe Navigation of Biped Robots Subject to Passive Friendly Safety and Balance Constraints," Master's Thesis, University of Grenoble-Alpes, 2016.