The project-team E-MOTION aims at developing algorithmic models and methods allowing to build artificial systems equipped with capacities of perception, decision, and action sufficiently advanced and robust to allow them to operate in open and dynamic environments (i.e. in partially known environments, where time and dynamics play a major role), and leading to varied interactions with human. Recent tehnological progresses on embedded computational power, on sensors technology, and on miniaturized mechatronic systems, make the required technological breakthroughs potentially possible (including from the scalability point of view). In order to try to reach this objective, we propose to combine the respective benefits of computational geometry, of probability theory and in certain cases of the biological inspiration (by working in cooperation with some neurophysiologists).
The main applications aimed by these research axes are those whose purpose is to introduce advanced and secured robotized systems into our “living space”, in order to increase the safety of people and the comfort of use of new technologies. This characteristic can be met in applications such as future cars and transportation systems, or service and intervention robotics (e.g. domestic tasks, civilian or military security, entertainment). We can also expect some other spin-offs of this research in various application domains such as the interaction with autonomous agents in a virtual world, the modeling of biological sensori-motor systems, or the diagnosis for the maintenance of large industrial plants or for financial applications (application domains currently covered by our start-up Probayes ).
- Multimodal and incremental modeling of space and motion. The problem is to incrementally build several types of models having complementary functional specializations (as suggested by the neurophysiologists) based on preliminary knowledge and a continuous flow of perceptive data. The intrinsic nature of the problem (world dynamicity, environment complexity, hazards, etc.) leads us to make use of an incremental approach involving techniques for predicting the motions of the potential sensed obstacles, and techniques for combining sensory data and executed actions.
- Motion planning for the physical world. The main problem is to simultaneously take into account various constraints of the physical world such as non-collision, environment dynamicity, or reaction time, while mastering the related algorithmic complexity. These problem characteristics leads us to develop techniques for reasoning on suitable representations of the space-time, e.g. space of instantaneous safe speeds or iterative planning under strong temporal constraints.
- Probabilistic inference for decision. The problem is to correctly reason about both the current knowledge of the system and its associated uncertainties. In order to cope with this problem, we propose to make use of the new paradigm of bayesian programming developed by our research team. This approach provides formal constructions and computational tools to carry out machine learning and reasoning based on probabilistic inference.
International and industrial relations
- Start-ups : Itmi (1982), Getris Images (1985), Aleph Technologies (1989), Aleph Med (1992), Probayes (2003).
- Technological transfers : Robot programming system LM, CAD-Robotics system ACT (in cooperation with the Prisme project at Inria Sophia-Antipolis), Dynamic simulator Aladyn2D, Probabilistic inference engine ProBT.
- Industrial collaborations : Robotsoft, Renault, PSA, AW Europe (linked to Toyota), XL-Studio, Aesculap, Teamlog, Kelkoo.
- Research contracts : Projects in national programmes Robea, ACI, RNTL, and inter-ministerial programme Predit ; European projects in FP5 (IST et IST-FET) and in FP6 (NoE, IST-IP).
- International cooperation : USA (Berkeley, Stanford, UCLA), Japan (Riken), Singapore (NTU et NUS), Mexico (Itesm Monterrey), Brasil (Brasilia), Europe (partners of NoE and et European projects).