- research
- write scientific papers
- present work at scientific conferences
- programming
- data management and curation
- interact with partners (scientists, engineers)
- write a doctoral thesis
- participate to demonstrations and showcases
- Master's Degree in the relevant field
- Strong background in machine learning, particularly reinforcement learning
- Proficiency in programming languages such as Python, C++
- Solid understanding of robotic systems and control challenges real-time performance and for real-world environments
- Familiarity with automated vehicles simulation environments
- Experience in developing control algorithms or motion planning strategies for autonomous vehicles
- Excellent problem-solving skills and the ability to work both independently and collaboratively in an interdisciplinary team.
- French optional but very desirable.
- Good level of English for communication (international team).
- Strong ability to work in groups,
- autonomy [essential],
- motivation,
- strength of initiative
- Subsidized meals
- Partial reimbursement of public transport costs
- Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
- Possibility of teleworking and flexible organization of working hours (after 6 months of employment)
- Professional equipment available (videoconferencing, loan of computer equipment, etc.)
- Social, cultural and sports events and activities
- Access to vocational training
- Social security coverage
-
Service & Application Engineer Drives & Automation
il y a 3 semaines
EarthStream Paris, France**Job Details**: · **Sector**: Automation**Location**: Paris**Job Ref**: PR/115756_ **Job Type**: Permanent**Salary**: Car, Bonus & Benefits per year**Expiry Date**: 20 January 2023**Contact**: Charles CuretonEarthstream are proud to be working with a Global Provider of Automatio ...
-
Service & Application Engineer Drives & Automation
il y a 1 jour
EarthStream Paris, France**Job Details**: · **Sector**: Automation**Location**: Paris**Job Ref**: PR/115756_ **Job Type**: Permanent**Salary**: Car, Bonus & Benefits per year**Expiry Date**: 09 April 2023**Contact**: Charles CuretonEarthstream are proud to be working with a Global Provider of Automation ...
-
Service & Application Engineer Drives & Automation
il y a 5 jours
EarthStream Paris, France**Job Details**: · **Sector**: Automation**Location**: Paris**Job Ref**: PR/115756_ **Job Type**: Permanent**Salary**: Car, Bonus & Benefits per year**Expiry Date**: 08 March 2023**Contact**: Charles CuretonEarthstream are proud to be working with a Global Provider of Automation ...
-
Test, Integration
il y a 3 semaines
Faurecia Paris, France**Forvia : Leader technologique de l'industrie** **automobile** · **FORVIA** regroupe les forces technologiques et industrielles complémentaires de **Faurecia et HELLA. **Avec plus de 300 sites industriels et 77 centres de R&D, personnes, dont plus de ingénieurs dans plus de 40 p ...
-
Apprentice Division Consolidation Controller
il y a 1 semaine
Faurecia Paris, France**Apprenti(e) Contrôleur Consolidation Division H/F**: · Apprentissage · **Forvia : Leader technologique de l'industrie** **automobile** · **FORVIA** regroupe les forces technologiques et industrielles complémentaires de **Faurecia et HELLA. **Avec plus de 300 sites industriels e ...
-
Systems Verification Engineer
il y a 1 semaine
Philips Paris, France**Job Title**: Systems Verification Engineer (BRITE) · The Philips **BR**eakthrough **I**nnovation **TE**ams (**BRITE**) are the embodiment of Philips' new approach to driving breakthrough innovation. The BRITE approach accelerates innovation by being the organizational sandbox t ...
-
Ai/ran Automation Data Driven Development
il y a 2 semaines
Ericsson Paris, FranceWe are building a new R&D team in Massy, France, including a Standards & Technology unit, part of Development Unit Network's global Standards & Technology organization. At Development Unit Networks, Standards & Technology secure technology leadership in Radio Access Networks (RAN ...
-
Ai/ran Automation
il y a 1 semaine
Ericsson Paris, FranceWe are building a new R&D team in Massy, France, including a Standards & Technology unit, part of Development Unit Network's global Standards & Technology organization. At Development Unit Networks, Standards & Technology secure technology leadership in Radio Access Networks (RAN ...
-
Automation Engineer
il y a 2 semaines
Tetra Pak Paris, FranceAt Tetra Pak we commit to making food safe and available, everywhere; and we protect what's good - protecting food, protecting people, and protecting the planet. By doing so we touch millions of people's lives every day. And we need people like you to make it happen._ · **Job Sum ...
-
Growth Director
il y a 3 semaines
Ridecell Paris, FranceMoving the world better - that's the backbone of everything we do. At Ridecell, we pride ourselves on helping the largest fleets in the world digitally transform their business operations to achieve their goals, no matter how big or adventurous. Our fleet automation and mobility ...
-
Customer Implementation Manager
il y a 3 semaines
Gorgias Paris, FranceOur one-of-a-kind product transforms how brands interact with their customers through unified customer conversations, AI automations that resolve up to 60% of support requests, and revenue-generating on-site campaigns. · As a leader in the CX space, Gorgias is committed to transf ...
-
Copy of Customer Implementation Manager
il y a 3 semaines
Gorgias Paris, FranceOur one-of-a-kind product transforms how brands interact with their customers through unified customer conversations, AI automations that resolve up to 60% of support requests, and revenue-generating on-site campaigns. · As a leader in the CX space, Gorgias is committed to transf ...
-
Marketing Automation Specialist
il y a 1 semaine
Cognism Paris, FranceCognism is a market leader in international sales intelligence. Access to our premium data, has helped a wide variety of global revenue teams change their approach to prospecting, resulting in predictable and prosperous outcomes. · As we grow, one of our main objectives is to con ...
-
Retrocession Analyst Intern
il y a 3 semaines
SCOR Paris, FranceAs an innovation booster, P&C Solutions enables deals and provides services, which will ultimately enhance relationships with (end-)clients and strengthen SCOR P&C positioning in the value chain. Within P&C Solutions, the Retrocession Department is an integral part of the underwr ...
-
Head of QA Hiring
il y a 2 semaines
Lydia Solutions Paris e, FranceWith 250 employees based in Paris, Nantes, Bordeaux and Lyon, Lydia has set itself the task of changing the codes of the bank by offering all the essential services to manage your money on a daily basis through a simple, accessible and enjoyable customer experience. · As the Head ...
-
Fp&a Analyst
il y a 1 semaine
Sage Group PLC Paris, France**Nom du poste à pourvoir** · - FP&A Analyst · **Description du poste** · - Working within our FP&A team, the Staff Cost Analyst role will be responsible for assisting Local FP&A Manager, Functionals analyst and Financial Business Partner with staff costs analysis, headcount anal ...
-
Sales Capture/strategic Pursuits Leader
il y a 2 semaines
Rockwell Automation Paris, FranceRockwell Automation is a global technology leader focused on helping the world's manufacturers be more productive, sustainable, and agile. With more than 25,000 employees who make the world better every day, we know we have something special. Behind our customers - amazing compan ...
-
Revenue Operations Manager
il y a 2 semaines
JLL Paris, FranceJLL supports the Whole You, personally and professionally. · Revenue Operations Manager, EMEA · **Purpose and Contribution to Strategy**: · About The Role · The Revenue Operations function is a new entity at JLL. With that, it's imperative that we have leadership in all regions i ...
-
Growth Marketing
il y a 1 semaine
P1 Security S.A.S. Paris, France**About Us**: · P1 Security secures Operators and Nation-states Critical Mobile Infrastructure to defend against cybersecurity threats and attacks. Founded in 2009, P1 Security is one of the most trusted companies in network security. In 2024, we want to launch a new chapter for ...
-
Growth Engineering Intern
il y a 3 semaines
Upflow Paris, France**About Upflow**: · Getting paid on time represents a significant problem for B2B companies. Unlike consumer payments, where we've seen massive amounts of innovation in the form of companies like Venmo & Revolut, B2B payments remain archaic, with most of the work being done in sp ...
PhD Position F/M PhD Thesis on RL-based Decision-Making and Planning for Automated Driving - Paris, France - INRIA
Description
Contexte et atouts du poste
You will work within the ASTRA team (Automated and Safe TRAnsportation systems), a joint team of scientists from Inria and Valeo led by Fawzi Nashashibi (Inria) and Benazouz Bradai (Valeo).
This team designs models and algorithms for the development of architectures for intelligent transport systems. It is involved in several projects financed by the French National Research Agency, which aim to welcome Valeo employees and recruit young PhD students.
The PhD thesis focuses on decision-making and planning for automated driving, using reinforcement learning (RL). It explores how autonomous vehicles make decisions (strategic, tactical, and operational) and plan their actions while considering safety, comfort constraints, and interactions with other road users.
Decision-making systems must generate collision-free trajectories in dynamic environments while anticipating the movements of other road users. Despite advancements, challenges persist, including improving motion prediction, completeness of decision-making approaches, and enhancing system robustness against environmental data uncertainty.
The use of reinforcement learning (RL) offers promising opportunities to enhance driving policies, trajectory planning, and decision-making processes. Recent studies have demonstrated the effectiveness of RL, particularly in safe autonomous driving, multi-agent traffic management, and real-world deployment scenarios.
Mission confiée
During the PhD thesis, the general objective is to:
• Develop an RL-based decision-making and planning framework for automated driving systems. It is only natural to begin turning to the standard model for sequential decision making: the Markov Decision Process. At first glance, this framework shines with its simplicity and elegance, but also its apparent generality and representation power. An (observable) state space, a (hierarchical) action space, a (quasi-linear) system dynamics and a (dense) reward function are to be addressed for a large class of behavioural planning tasks.
• Optimize driving policies using RL algorithms to ensure safety, efficiency, and adaptability. The study in [8] explores several fundamental algorithms in Deep RL to improve automated driving performance, namely Proximal Policy Optimization (PPO), Deep Q-network (DQN), and Deep Deterministic Policy Gradient (DDPG). The paper documents a comparative analysis of these three prominent algorithms—based on their speed, accuracy, and overall performance. After a thorough evaluation, the research indicates that the DQN surpassed the other existing algorithms
• Evaluate the performance of the proposed RL system through simulations and real-world testing.
This is achieved regarding the following key points:
– Create a diverse set of driving scenarios representative of real-world conditions, including highway driving, urban environments, intersections, pedestrian crossings, adverse weather conditions, etc.
– Integrate the RL algorithm into a simulation/testing environment including real vehicle dynamics, sensor inputs, environmental factors, and interactions with other agents (e.g., vehicles, pedestrians).
– Define relevant performance metrics to evaluate the RL system's behavior. Metrics may include safety (e.g., collision rate), efficiency (e.g., average speed, fuel consumption), adherence to traffic rules, and comfort (e.g., smoothness of maneuvers).
– Compare the performance of the RL-based system against baseline methods, such as rule-based controllers or handcrafted algorithms, to demonstrate its superiority.
In conclusion, the proposed research project holds immense potential in advancing RL applications in automated driving systems by developing a sophisticated decision-making framework that prioritizes safety, efficiency, and adaptability. Through rigorous evaluation and testing, this project aims to contribute valuable insights to the field of autonomous vehicle technology, ultimately leading to safer, more efficient, and intelligent autonomous driving solutions.
References
[1] Laurène Claussmann, Marc Revilloud, Dominique Gruyer, and Sébastien Glaser. A review of motion planning for highway autonomous driving. IEEE Transactions on Intelligent Transportation Systems,21:1826–1848, 2020.
[2] Fernando Garrido and Paulo Resende. Review of decision-making and planning approaches in automated driving. IEEE Access,10:100348–100366, 2022.
[3] D. González, J. Pérez, V. Milanés, and F. Nashashibi. A review of motion planning techniques for automated vehicles. IEEE Transactions on Intelligent Transportation Systems, 17:1135–1145, April 2016.
[4] B Ravi Kiran, Ibrahim Sobh, Victor Talpaert, Patrick Mannion, Ahmad A. Al Sallab, Senthil Yogamani, and Patrick Pérez. Deep reinforcement learning for autonomous driving: A survey. IEEE Transactions on Intelligent Transportation Systems, 23:4909–4926, 2022.
[5] Hanna Krasowski, Yinqiang Zhang, and Matthias Althoff. Safe reinforcement learning for urban driving using invariably safe braking sets. In 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), pages 2407–2414, 2022.
[6] Shahrokh Paravarzar and Belqes Mohammad. Motion prediction on self-driving cars: A review, 2020.
[7] Stefano Pini, Christian S. Perone, Aayush Ahuja, Ana Sofia Rufino Ferreira, Moritz Niendorf, and Sergey Zagoruyko. Safe real-world autonomous driving by learning to predict and plan with a mixture
of experts. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 10069–10075, 2023.
[8] Akshaj Tammewar, Nikita Chaudhari, Bunny Saini, Divya Venkatesh, Ganpathiraju Dharahas, Deepali Vora, Shruti Patil, Ketan Kotecha, and Sultan Alfarhood. Improving the performance of autonomous driving through deep reinforcement learning. Sustainability, 15, 2023.
[9] Shijie Wang and Shangbo Wang. A novel multi-agent deep rl approach for traffic signal control,
Principales activités
Main activities:
Compétences
Candidate Profile :
Languages :
Additional skills:
Avantages