We are looking for applicants for a PhD position in Robotics at Inria Nancy.
Autonomy of robots often requires an internal representation of the current state of both the robot and his environment. Many state estimation techniques rely on a probabilistic representation wherein a probability distribution over the state space is recursively computed based on some observations and a model of the evolution of the system. There are several techniques (Kalman filters , HMM , particles filters ) that have been applied in robotics for various problems ranging from robot state estimation [4,5] to mapping the environment [6,7].
The aim of this PhD project is to advance the state of the art of filtering techniques in robotics along two principal dimensions. The first objective is to find way to propagate information between the different kind of filters: how to do efficient Bayesian inference with distinct distribution representations? An approach of this question could typically come from approximation techniques such as sampling or moment matching. The second objective will be to combine those model-based filtering techniques with machine learning. Indeed the models are never complete or correct and several techniques require approximations to become tractable. There are therefore systematic errors that could potentially be corrected by model-less learning techniques such as deep neural networks.
Finally, the emphasis will be laid on the experimentation and validation methodologies. The algorithms developed should be demonstrated and applied to concrete robotics problems, for instance in the context of the smart apartment. This experimental setup is a small flat equipped with a wide range of sensors from pressure tiles on the ground to RGB-D cameras. We dispose of several mobile robots from turtlebots to a Pepper robot as well as a motion capture system that can provide ground truth information for the pose of the robots and of humans. Right now, we can separately locate the robot, build a map of the obstacles, locate sound sources, locate people and assess their current activity, etc. The aim is to build an integrated representation of this all and to leverage the synergies to improve their respective estimates.
 Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Journal of basic Engineering, 82(1), 35-45.
 Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257-286.
 Doucet, A., De Freitas, N., Murphy, K., & Russell, S. (2000, June). Rao-Blackwellised particle filtering for dynamic Bayesian networks. In Proceedings of the Sixteenth conference on Uncertainty in artificial intelligence (pp. 176-183). Morgan Kaufmann Publishers Inc..
 Kubelka, V., Oswald, L., Pomerleau, F., Colas, F., Svoboda, T., & Reinstein, M. (2015). Robust data fusion of multimodal sensory information for mobile robots. Journal of Field Robotics, 32(4), 447-473.
 Hitz, G., Pomerlesau, F., Colas, F., & Siegwart, R. (2016). State estimation for shore monitoring using an autonomous surface vessel. In Experimental Robotics (pp. 745-760). Springer International Publishing.
 Durrant-Whyte, H., & Bailey, T. (2006). Simultaneous localization and mapping: part I. IEEE robotics & automation magazine, 13(2), 99-110.
 Nguyen, Q. V., Colas, F., Vincent, E., & Charpillet, F. (2016, October). Localizing an intermittent and moving sound source using a mobile robot. In Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on (pp. 1986-1991). IEEE.
Duration: 3 years
Starting date: between Oct. 1st 2018 and Jan. 1st 2019
Salary: 1982€ gross monthly (~1596€ net) during the first and the second years. 2085€ the last year (~1679€ net). Medical insurance is included.
Master in robotics, automation, or computer science with strong skills in Bayesian or probabilistic inference, robotics, and programming (C++ or Python preferred).
Willingness to combine theoretical work and robot experimentation will be useful.
Inria, the French National Institute for computer science and applied mathematics, promotes “scientific excellence for technology transfer and society”. Graduates from the world’s top universities, Inria's 2,700 employees rise to the challenges of digital sciences. Research at Inria is organised in “project teams” which bring together researchers with complementary skills to focus on specific scientific projects. With this open, agile model, Inria is able to explore original approaches with its partners in industry and academia and provide an efficient response to the multidisciplinary and application challenges of the digital transformation. The source of many innovations that add value and create jobs, Inria transfers expertise and research results to companies (startups, SMEs and major groups) in fields as diverse as healthcare, transport, energy, communications, security and privacy protection, smart cities and the factory of the future.
The Inria Nancy - Grand-Est centre conducts sustained activity in the sector of information science and technologies, including computer science, applied mathematics, control engineering and multidisciplined themes situated at the crossroads between information science and technologies and other scientific areas, including life sciences, physics and human and social sciences. We also have strong commitments linked to technology transfer. Our establishment at the heart of a major cross-border region, together with our industrial and university partnerships, constitute a major advantage in achieving these commitments.
All applications must follow the procedure here:
Deadline on May, 1st 2018.
Team Larsen, Loria -- C125
INRIA Nancy - Grand Est
615 rue du Jardin Botanique
54600 Villers-lès-Nancy, France
+33 3 54 95 86 30
robotics-worldwide mailing list
|Free forum by Nabble||Edit this page|