[robotics-worldwide] [jobs] Internship at Valeo (Bobigny site, Paris Region)

Omar ISLAS omar.islas at valeo.com
Mon Mar 11 09:16:27 PDT 2019


Internship: Driving Situation

Team Description

InnoCoRe (Innovation and collaborative Research) team is a
multidisciplinary team of “Comfort and Driving Assistance” (CDA) Business
Group. The team’s objective is to explore the fields of autonomous driving,
connected car and user interaction for new technologies and new use cases.
Our work helps defining Valeo’s roadmaps (5-10 years), providing R&D teams
with innovative projects to pursue Engineers, UX designers and project
managers located in France, Germany and California team-up around a common
mission to design and experiment new concepts and services to create added
value for existing Valeo technologies. Their collaboration with Valeo’s
academic network and start-ups ecosystem is key for leveraging scientific
expertise and agility within projects.

Project: Driving Situation

A driving situation corresponds to a representation of the world collected
and/or perceived around a main vehicle in a given instantaneous moment.
This representation is composed of (a) the information that can be
collected in a moment by sensors (Cameras, Lidar, GPS) and (b) information
coming from other services, e.g. related to the road and the weather. A
Situation can be useful to understand the own vehicle status, understand
the status of the surrounding environment and understand the state of the
perceived objects.
These key elements defines the “driving situation” that the driver is
currently facing. Hence, the analysis of a sequence of these instants can
lead to a near future decisions.

The missions
You’ll work within the project driving situations in the following topics.
State of the art:
Study and implementation of methodologies such as Markov Chain and Markov
Decision Processes (MDP) for multi dimensional state spaces.
Feature extraction and Algorithm development:
Extract relevant information given a set of data either with feature
engineering or machine learning techniques, e.g. SVM, PCA, CNN, LSTM, and
Auto-encoders.
Metric Analysis:
Compare performance of the developed algorithms based on either state of
the art scoring systems or ad-hoc systems.

Technical Tools
We are searching for highly motivated, curious and independent students
with the following knowledge:
- General purpose programming language (Python, C++)
- First hands-on experience with a Machine Learning/Deep Learning
framework  (i.e. Scikit-learn, Tensorflow, PyTorch)
- Full proficiency in English (speaking, writing)
- 2nd year of Master’s Degree in  Robotics, Computer Science, Applied
Mathematics or Similar.
Good to have:
- Familiarity in using a multisensor middleware (i.e. ROS, RTMaps)
- Familiarity with simulators (Gazebo, ODE, Carla)
- Experience in coding with OpenCV
- Knowledge about publisher / subscriber systems (i.e. ZeroMQ, MQTT,
RabbitMQ)
- Containerization (Docker) and orchestration (swarm, kubernetes)
- Driving License

Contact

Please send your applications to omar.islas at valeo.com and add
julien.moizard at valeo.com and kevin.nguyen at valeo.com to copy.

-- 
*This e-mail message is intended for the internal use of the intended 
recipient(s) only.
The information contained herein is 
confidential/privileged. Its disclosure or reproduction is strictly 
prohibited.
If you are not the intended recipient, please inform the sender 
immediately, do not disclose it internally or to third parties and destroy 
it.

In the course of our business relationship and for business purposes 
only, Valeo may need to process some of your personal data. 
For more 
information, please refer to the Valeo Data Protection Statement and 
Privacy notice available on Valeo.com 
<https://urldefense.proofpoint.com/v2/url?u=https-3A__www.valeo.com_en_ethics-2Dand-2Dcompliance_-23principes&d=DwIFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=sqahwKPZotKy52gtBulSiHOzD_oywDtkDcDJSjDkRas&s=F5zrZ4S3uDrDH9p9rqTYVl8WMt4NxVDeNXSx13x3Cgk&e=>*


More information about the robotics-worldwide mailing list